diff --git a/kb-bilibili-content/SKILL.md b/kb-bilibili-content/SKILL.md new file mode 100644 index 0000000..4701426 --- /dev/null +++ b/kb-bilibili-content/SKILL.md @@ -0,0 +1,91 @@ +# KB Bilibili Content Skill + +**kb-bilibili-content** - Download Bilibili videos and extract content. + +## Features + +- Video download using **yt-dlp** (recommended) +- Subtitle extraction +- Article content extraction +- Multiple quality options (360P/480P/720P/1080P) +- Supports `BILIBILI_COOKIE` environment variable + +## Environment Variables + +| Variable | Required | Description | +|----------|----------|-------------| +| `BILIBILI_COOKIE` | No | B站登录 Cookie (for member-only videos) | + +## Commands + +```bash +# Download video (720P default) +python bilibili_content.py --id "BV1xx411c7mD" --type video --output "/path/to/downloads/" + +# Download video (1080P) +python bilibili_content.py --id "BV1xx411c7mD" --type video --quality 80 --output "/path/to/downloads/" + +# Download video (480P) +python bilibili_content.py --id "BV1xx411c7mD" --type video --quality 32 --output "/path/to/downloads/" + +# Extract subtitle +python bilibili_content.py --id "BV1xx411c7mD" --type subtitle --output "/path/to/subtitles/" + +# Get article content +python bilibili_content.py --id "cv43780186" --type article --output "/path/to/article.md" +``` + +## Output + +```json +{ + "success": true, + "type": "video", + "filename": "video_title.mp4", + "filepath": "/path/to/downloads/video_title.mp4", + "message": "下载完成: video_title.mp4" +} +``` + +## Cookie Setup + +### Get Cookie from Browser +1. Login to bilibili.com +2. Press F12 → Network → Refresh page +3. Copy Cookie from request headers + +### Set Environment Variable +```bash +# Add to ~/.bashrc for persistence +export BILIBILI_COOKIE="SESSDATA=xxx; bili_jct=xxx; DedeUserID=xxx; DedeUserID__ckMd5=xxx" + +# Or set temporarily +export BILIBILI_COOKIE="your_cookie_here" +``` + +## Installation + +```bash +cp -r kb-bilibili-content/ ~/skills/ +pip install aiohttp playwright +playwright install chromium +``` + +## How It Works + +Video download uses **yt-dlp** with Netscape-format cookie file: +1. Parses `BILIBILI_COOKIE` environment variable +2. Creates temporary Netscape-format cookie file +3. Runs `yt-dlp --cookies -f -o ` +4. Cleans up temporary file + +## Quality Options + +| Quality | ID | Resolution | Notes | +|---------|-----|------------|-------| +| 16 | 360P | 640x360 | Fastest | +| 32 | 480P | 852x480 | Default for low bandwidth | +| 64 | 720P | 1280x720 | **Recommended** | +| 80 | 1080P | 1920x1080 | Best quality | + +Default quality: **64 (720P)** diff --git a/kb-bilibili-content/__pycache__/bilibili_content.cpython-312.pyc b/kb-bilibili-content/__pycache__/bilibili_content.cpython-312.pyc new file mode 100644 index 0000000..d8b5ed3 Binary files /dev/null and b/kb-bilibili-content/__pycache__/bilibili_content.cpython-312.pyc differ diff --git a/kb-bilibili-content/bilibili_content.py b/kb-bilibili-content/bilibili_content.py new file mode 100644 index 0000000..08bfbef --- /dev/null +++ b/kb-bilibili-content/bilibili_content.py @@ -0,0 +1,419 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +""" +Bilibili Content Downloader - B站内容获取工具 + +功能: +- download_video(bvid, quality=480) - 下载视频（使用 yt-dlp） +- extract_subtitle(bvid) - 提取字幕 +- extract_article(cvid) - 获取专栏全文（使用Playwright） +- 命令行参数支持 +- JSON 输出 +""" + +import argparse +import asyncio +import json +import os +import re +import subprocess +import sys +import tempfile +from datetime import datetime +from pathlib import Path +from typing import Optional, Dict, Any, List + + +class BilibiliContent: + """B站内容获取器""" + + def __init__(self, output_dir: str = "./output", cookie: str = None): + self.output_dir = Path(output_dir) + self.output_dir.mkdir(parents=True, exist_ok=True) + self.cookie = cookie + + def _create_cookie_file(self) -> str: + """创建 Netscape 格式的 Cookie 文件""" + if not self.cookie: + return None + + # 解析 Cookie 字符串 + cookies = {} + for item in self.cookie.split(';'): + item = item.strip() + if '=' in item: + key, value = item.split('=', 1) + cookies[key.strip()] = value.strip() + + # 创建 Netscape 格式的 Cookie 文件 + cookie_content = """# Netscape HTTP Cookie File +# Generated by bilibili_content.py + +""" + + for name, value in cookies.items(): + cookie_content += f".bilibili.com\tTRUE\t/\tFALSE\t0\t{name}\t{value}\n" + + # 写入临时文件 + fd, path = tempfile.mkstemp(suffix='.txt') + with os.fdopen(fd, 'w') as f: + f.write(cookie_content) + + return path + + async def download_video(self, bvid: str, quality: int = 64) -> Dict[str, Any]: + """下载B站视频（使用 yt-dlp）""" + result = {"success": False, "bvid": bvid, "message": "", "filepath": None, "metadata": {}} + + try: + # 先获取视频信息 + print(f"获取视频信息: {bvid}") + + cookie_file = self._create_cookie_file() + url = f"https://www.bilibili.com/video/{bvid}" + + try: + # 获取视频标题（用于文件名） + if cookie_file: + cmd = ["yt-dlp", "--cookies", cookie_file, "--get-title", url] + else: + cmd = ["yt-dlp", "--get-title", url] + + proc = await asyncio.create_subprocess_exec( + *cmd, + stdout=asyncio.subprocess.PIPE, + stderr=asyncio.subprocess.PIPE + ) + stdout, stderr = await proc.communicate() + + title = stdout.decode('utf-8').strip() + if not title or 'error' in title.lower(): + # 尝试备用方法 + title = f"video_{bvid}" + except Exception as e: + title = f"video_{bvid}" + + # 构建 yt-dlp 命令 + safe_title = "".join(c for c in title if c.isalnum() or c in (' ', '-', '_', '丨')).strip()[:50] + + # 选择视频格式 + if quality == 80: + # 1080P + format_str = "30112+30280" + elif quality == 64: + # 720P + format_str = "30064+30280" + elif quality == 32: + # 480P + format_str = "30032+30280" + else: + # 360P + format_str = "30016+30280" + + print(f"下载视频: {title}") + print(f"格式: {format_str}") + + output_template = str(self.output_dir / f"{safe_title}.%(ext)s") + + cmd = [ + "yt-dlp", + "-f", format_str, + "-o", output_template, + "--no-download-archive", + "-q", + url + ] + + if cookie_file: + cmd.extend(["--cookies", cookie_file]) + + print(f"执行命令: {' '.join(cmd[:4])}...") + + proc = await asyncio.create_subprocess_exec( + *cmd, + stdout=asyncio.subprocess.PIPE, + stderr=asyncio.subprocess.PIPE + ) + stdout, stderr = await proc.communicate() + + # 查找下载的文件 + downloaded_files = list(self.output_dir.glob(f"{safe_title}.*")) + if downloaded_files: + video_file = downloaded_files[0] + result["success"] = True + result["filepath"] = str(video_file) + result["message"] = f"下载完成: {video_file.name}" + result["metadata"] = {"title": title, "bvid": bvid} + print(f"✅ {result['message']}") + else: + result["message"] = "未找到下载的文件" + print(f"❌ {result['message']}") + + # 清理临时 Cookie 文件 + if cookie_file and os.path.exists(cookie_file): + os.remove(cookie_file) + + except Exception as e: + result["message"] = f"错误: {str(e)}" + print(f"❌ {result['message']}") + + return result + + async def extract_subtitle(self, bvid: str) -> Dict[str, Any]: + """ + 提取字幕 + + 注意：没有找到官方字幕是正常的！很多视频没有自动生成的字幕。 + 返回 success=True 即使没有字幕，让工作流继续执行后续步骤（如 Whisper）。 + """ + result = {"success": False, "bvid": bvid, "subtitles": [], "has_subtitle": False, "message": ""} + + try: + import aiohttp + + api_url = f"https://api.bilibili.com/x/player/pagelist?bvid={bvid}" + + async with aiohttp.ClientSession() as session: + async with session.get(api_url) as resp: + data = await resp.json() + + pages = data.get('data', []) + if not pages: + result["message"] = "未找到分P（这是正常的）" + # 仍然返回 success=True，让工作流继续 + result["success"] = True + return result + + cid = pages[0].get('cid', '') + + async with aiohttp.ClientSession() as session: + async with session.get(f"https://api.bilibili.com/x/player/v2?bvid={bvid}&cid={cid}") as resp: + sub_data = await resp.json() + + subtitles = sub_data.get('data', {}).get('subtitle', {}).get('list', []) + + if not subtitles: + result["message"] = "没有官方字幕（这是正常的），将使用 Whisper 进行语音识别" + # 仍然返回 success=True，让工作流继续 + result["success"] = True + return result + + result["success"] = True + result["has_subtitle"] = True + result["subtitles"] = [{"lan": s.get('lan'), "title": s.get('lan_doc')} for s in subtitles] + result["message"] = f"✅ 找到 {len(subtitles)} 个字幕，将使用官方字幕进行深度分析" + print(result["message"]) + + except Exception as e: + result["message"] = f"获取字幕出错（这是正常的），将使用 Whisper: {str(e)}" + # 出错时也返回 success=True，让工作流继续 + result["success"] = True + + return result + + async def download_subtitle(self, bvid: str) -> Dict[str, Any]: + """ + 下载字幕并转换为 SRT 格式 + + 如果没有官方字幕，返回 success=True 但 has_subtitle=False， + 让工作流继续使用 Whisper 进行语音识别。 + """ + result = {"success": False, "bvid": bvid, "filepath": None, "has_subtitle": False, "message": ""} + + try: + import aiohttp + + # 获取 CID + api_url = f"https://api.bilibili.com/x/player/pagelist?bvid={bvid}" + + async with aiohttp.ClientSession() as session: + async with session.get(api_url) as resp: + data = await resp.json() + + pages = data.get('data', []) + if not pages: + result["message"] = "未找到分P，将使用 Whisper 进行语音识别" + result["success"] = True + return result + + cid = pages[0].get('cid', '') + + # 获取字幕列表 + async with aiohttp.ClientSession() as session: + async with session.get(f"https://api.bilibili.com/x/player/v2?bvid={bvid}&cid={cid}") as resp: + sub_data = await resp.json() + + subtitles = sub_data.get('data', {}).get('subtitle', {}).get('list', []) + + if not subtitles: + result["message"] = "没有官方字幕，将使用 Whisper 进行语音识别" + result["success"] = True + return result + + # 选择中文字幕，如果没有则选第一个 + zh_sub = None + for s in subtitles: + if s.get('lan') in ('ai-zh', 'zh-CN', 'zh'): + zh_sub = s + break + if not zh_sub: + zh_sub = subtitles[0] + + # 下载字幕文件 + sub_url = zh_sub.get('subtitle_url', '') + if not sub_url: + result["message"] = "字幕URL为空，将使用 Whisper" + result["success"] = True + return result + + if sub_url.startswith('//'): + sub_url = 'https:' + sub_url + + async with aiohttp.ClientSession() as session: + async with session.get(sub_url) as resp: + sub_content = await resp.json() + + # 转换为 SRT 格式 + body = sub_content.get('body', []) + if not body: + result["message"] = "字幕内容为空，将使用 Whisper" + result["success"] = True + return result + + def format_srt_time(t: float) -> str: + """将秒数转换为 SRT 时间格式""" + h = int(t // 3600) + m = int((t % 3600) // 60) + s = int(t % 60) + ms = int((t - int(t)) * 1000) + return f"{h:02d}:{m:02d}:{s:02d},{ms:03d}" + + srt_lines = [] + for i, line in enumerate(body, 1): + start = line.get('from', 0) + end = line.get('to', 0) + content = line.get('content', '') + srt_lines.extend([str(i), f"{format_srt_time(start)} --> {format_srt_time(end)}", content, ""]) + + srt_content = "\n".join(srt_lines) + + # 保存 SRT 文件 + output_path = self.output_dir / f"{bvid}.srt" + with open(output_path, 'w', encoding='utf-8') as f: + f.write(srt_content) + + result["success"] = True + result["has_subtitle"] = True + result["filepath"] = str(output_path) + result["message"] = f"✅ 官方字幕已下载: {output_path.name} ({len(body)}条)" + print(result["message"]) + + except Exception as e: + result["message"] = f"下载字幕出错: {str(e)}，将使用 Whisper" + result["success"] = True # 仍然返回成功，让工作流继续 + + return result + + async def extract_article(self, cvid: str) -> Dict[str, Any]: + """获取专栏全文（使用Playwright异步API）""" + result = {"success": False, "cvid": cvid, "title": "", "content": "", "message": ""} + + try: + from playwright.async_api import async_playwright + + cvid_clean = cvid.replace('cv', '') + url = f"https://www.bilibili.com/read/cv{cvid_clean}" + print(f"获取专栏: {url}") + + async with async_playwright() as p: + browser = await p.chromium.launch(headless=True) + page = await browser.new_page() + + await page.goto(url, wait_until="networkidle") + await page.wait_for_timeout(3000) + + # 提取标题 + title_elem = await page.query_selector('h1') + if title_elem: + result["title"] = (await title_elem.inner_text()).strip() + print(f"标题: {result['title'][:50]}...") + + # 提取正文内容 + content_elem = await page.query_selector('.read-article-holder') + if content_elem: + html_content = await content_elem.inner_html() + text_content = await content_elem.inner_text() + result["content"] = text_content.strip() + result["html_content"] = html_content.strip() + result["success"] = bool(result["title"] and result["content"]) + print(f"内容长度: {len(result['content'])} 字符") + else: + result["message"] = "未找到专栏内容" + + await browser.close() + + if result["success"]: + result["message"] = f"✅ 获取成功: {result['title'][:30]}..." + else: + result["message"] = f"获取失败: {result.get('message', '未知错误')}" + + except Exception as e: + result["message"] = f"错误: {str(e)}" + print(f"错误: {e}") + + return result + + +async def main(): + parser = argparse.ArgumentParser(description='Bilibili Content Downloader') + parser.add_argument('--id', '-i', required=True, help='B站内容ID') + parser.add_argument('--type', '-t', required=True, choices=['video', 'subtitle', 'subtitle-download', 'article'], help='内容类型') + parser.add_argument('--output', '-o', default='./output', help='输出目录') + parser.add_argument('--quality', '-q', type=int, default=64, help='视频质量: 16=360P, 32=480P, 64=720P, 80=1080P') + + args = parser.parse_args() + + cookie = os.environ.get('BILIBILI_COOKIE') + downloader = BilibiliContent(output_dir=args.output, cookie=cookie) + + if args.type == 'video': + result = await downloader.download_video(args.id, quality=args.quality) + elif args.type == 'subtitle': + result = await downloader.extract_subtitle(args.id) + elif args.type == 'subtitle-download': + # 下载并转换字幕为 SRT 格式 + result = await downloader.download_subtitle(args.id) + else: + result = await downloader.extract_article(args.id.replace('cv', '')) + + # 统一输出格式 + if result.get("success"): + output = { + "success": True, + "type": args.type, + "has_subtitle": result.get("has_subtitle", False), + "filename": Path(result.get('filepath', '')).name if result.get('filepath') else None, + "filepath": str(Path(result.get('filepath', '')).resolve()) if result.get('filepath') else None, + "message": result.get('message', '处理成功') + } + else: + output = { + "success": False, + "error": result.get('message', '处理失败'), + "detail": f"ID: {args.id}, 类型: {args.type}" + } + + print(json.dumps(output, ensure_ascii=False, indent=2)) + return result + + +if __name__ == '__main__': + try: + result = asyncio.run(main()) + sys.exit(0 if result.get("success") else 1) + except KeyboardInterrupt: + print(json.dumps({"success": False, "error": "用户取消"}, ensure_ascii=False, indent=2)) + sys.exit(1) + except Exception as e: + print(json.dumps({"success": False, "error": str(e)}, ensure_ascii=False, indent=2)) + sys.exit(1) diff --git a/kb-bilibili-content/bilibili_extractor.py b/kb-bilibili-content/bilibili_extractor.py new file mode 100644 index 0000000..971d239 --- /dev/null +++ b/kb-bilibili-content/bilibili_extractor.py @@ -0,0 +1,155 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +""" +B站视频提取脚本 +提取视频信息、统计数据、字幕并生成Markdown笔记 +""" + +import sys +import os +import json +import re +from datetime import datetime + +# 添加skills路径 +sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'skills', 'obsidian-kb')) + +from src.extractors.bilibili_extractor import BilibiliExtractor +from src.config import get_config + + +def format_number(num): + """格式化数字""" + if num >= 100000000: + return f"{num / 100000000:.1f}亿" + elif num >= 10000: + return f"{num / 10000:.1f}万" + else: + return f"{num:,}" + + +def generate_markdown(result, bvid): + """生成Markdown笔记""" + metadata = result['metadata'] + stats = result['stats'] + description = result['description'] + subtitle = result['subtitle'] + + # 获取当前时间 + now = datetime.now().strftime('%Y-%m-%d %H:%M:%S') + + md = f"""# {metadata['title']} + +> **来源**: [B站](https://www.bilibili.com/video/{bvid}) +> **作者**: {metadata['author']} +> **发布时间**: {metadata['pubtime']} +> **提取时间**: {now} +> **时长**: {metadata['duration']} + +## 📊 统计数据 + +| 指标 | 数量 | +|------|------| +| 👀 播放 | {format_number(stats['view'])} | +| 💬 弹幕 | {format_number(stats['danmaku'])} | +| 📝 评论 | {format_number(stats['reply'])} | +| ⭐ 收藏 | {format_number(stats['favorite'])} | +| 🪙 投币 | {format_number(stats['coin'])} | +| 🔗 分享 | {format_number(stats['share'])} | +| 👍 点赞 | {format_number(stats['like'])} | + +## 📝 视频简介 + +{description if description else '(暂无简介)'} + +## 📌 标签 + +{metadata['tags'] if metadata['tags'] else '(无标签)'} + +## 🎬 字幕 + +{subtitle if subtitle else '(无字幕)'} + +--- + +**元数据**: +- BV号: `{metadata['bvid']}` +- AV号: `{metadata['aid']}` +- UP主ID: `{metadata['mid']}` +""" + + return md + + +def main(): + """主函数""" + # BV号 + bvid = "BV1N5foBjE5K" # 从 https://b23.tv/btMGoOi 解析得到 + + print(f"开始提取B站视频: {bvid}") + print("=" * 60) + + # 获取配置 + try: + config = get_config() + except Exception as e: + print(f"⚠️ 获取配置失败，使用默认配置: {e}") + config = None + + # 创建提取器 + extractor = BilibiliExtractor(config=config) + + # 提取视频信息 + try: + result = extractor.extract(bvid) + + print("\n✅ 提取成功！\n") + print("=" * 60) + print("基本信息:") + print("=" * 60) + print(f"标题: {result['metadata']['title']}") + print(f"作者: {result['metadata']['author']}") + print(f"时长: {result['metadata']['duration']}") + print(f"发布: {result['metadata']['pubtime']}") + + print("\n" + "=" * 60) + print("统计数据:") + print("=" * 60) + print(f"播放: {format_number(result['stats']['view'])}") + print(f"弹幕: {format_number(result['stats']['danmaku'])}") + print(f"评论: {format_number(result['stats']['reply'])}") + print(f"收藏: {format_number(result['stats']['favorite'])}") + print(f"投币: {format_number(result['stats']['coin'])}") + print(f"点赞: {format_number(result['stats']['like'])}") + + # 生成 Markdown 笔记 + md_content = generate_markdown(result, bvid) + + # 确保 notes 目录存在 + notes_dir = "/home/admin/.openclaw/workspace/notes" + os.makedirs(notes_dir, exist_ok=True) + + # 生成文件名（使用BV号作为文件名） + filename = f"{bvid}.md" + filepath = os.path.join(notes_dir, filename) + + # 写入文件 + with open(filepath, 'w', encoding='utf-8') as f: + f.write(md_content) + + print("\n" + "=" * 60) + print(f"✅ Markdown笔记已生成: {filepath}") + print("=" * 60) + + # 返回笔记内容 + return md_content + + except Exception as e: + print(f"\n❌ 提取失败: {e}") + import traceback + traceback.print_exc() + return None + + +if __name__ == '__main__': + main() diff --git a/kb-bilibili-content/video_downloader.py b/kb-bilibili-content/video_downloader.py new file mode 100644 index 0000000..f5d25c4 --- /dev/null +++ b/kb-bilibili-content/video_downloader.py @@ -0,0 +1,175 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +""" +使用旧版 API 获取并下载视频流 +""" +import asyncio +import json +import os +from playwright.async_api import async_playwright + +async def download_video_stream(bvid, output_dir="/tmp/bilibili_downloads"): + """下载视频流""" + url = f"https://www.bilibili.com/video/{bvid}" + + # 创建输出目录 + os.makedirs(output_dir, exist_ok=True) + + async with async_playwright() as playwright: + browser = await playwright.chromium.launch(headless=True) + context = await browser.new_context() + page = await context.new_page() + + print(f"正在下载视频: {url}") + print("=" * 80) + + # 首先获取 aid 和 cid + print("\n1. 获取视频信息...") + try: + api_url = "https://api.bilibili.com/x/web-interface/view" + response = await page.request.get(api_url, params={'bvid': bvid}) + data = await response.json() + + if data.get('code') != 0: + print(f" ❌ 失败: {data.get('message')}") + await browser.close() + return None + + video_data = data.get('data', {}) + title = video_data.get('title') + aid = video_data.get('aid') + cid = video_data.get('cid') + duration = video_data.get('duration') + print(f" 标题: {title}") + print(f" 时长: {duration}秒") + except Exception as e: + print(f" ❌ 异常: {e}") + await browser.close() + return None + + # 获取视频流 URL + print("\n2. 获取视频流 URL...") + try: + playurl_api = "https://api.bilibili.com/x/player/playurl" + params = { + 'bvid': bvid, + 'cid': cid, + 'qn': 80, # 1080P + 'otype': 'json', + 'fnver': 0, + 'fnval': 0, # FLV 格式 + } + + playurl_response = await page.request.get(playurl_api, params=params) + + if not playurl_response.ok: + print(f" ❌ HTTP 错误: {playurl_response.status}") + await browser.close() + return None + + playurl_data = await playurl_response.json() + + if playurl_data.get('code') != 0: + print(f" ❌ API 错误: {playurl_data.get('message')}") + await browser.close() + return None + + play_data = playurl_data.get('data', {}) + + # 检查支持的清晰度 + print(f"\n 支持的清晰度:") + for i, (q, desc) in enumerate(zip(play_data.get('accept_quality', []), play_data.get('accept_description', []))): + current = " (当前)" if q == play_data.get('quality') else "" + print(f" {desc} ({q}){current}") + + # 获取视频 URL + durl = play_data.get('durl', []) + if not durl: + print(f" ❌ 没有找到视频流") + await browser.close() + return None + + print(f"\n 找到 {len(durl)} 个视频分段") + video_urls = [] + for i, segment in enumerate(durl): + segment_url = segment.get('url') + segment_size = segment.get('size', 0) + video_urls.append(segment_url) + print(f" 分段 {i+1}: {segment_size / 1024 / 1024:.2f}MB") + print(f" {segment_url[:100]}...") + + except Exception as e: + print(f" ❌ 异常: {e}") + import traceback + traceback.print_exc() + await browser.close() + return None + + # 下载视频 + print(f"\n3. 开始下载视频...") + all_segments = [] + total_size = 0 + + for i, video_url in enumerate(video_urls, 1): + print(f"\n 下载分段 {i}/{len(video_urls)}...") + + try: + # 添加必要的请求头 + headers = { + 'Referer': 'https://www.bilibili.com/', + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36', + } + + # 下载分段 + segment_response = await page.request.get( + video_url, + headers=headers, + timeout=60000 + ) + + if not segment_response.ok: + print(f" ❌ 下载失败: {segment_response.status}") + continue + + segment_data = await segment_response.body() + segment_size = len(segment_data) + total_size += segment_size + all_segments.append(segment_data) + + print(f" ✅ 下载成功: {segment_size / 1024 / 1024:.2f}MB") + + except Exception as e: + print(f" ❌ 下载异常: {e}") + continue + + if not all_segments: + print(f"\n ❌ 没有成功下载任何分段") + await browser.close() + return None + + # 合并分段 + print(f"\n4. 合并视频分段...") + video_data = b''.join(all_segments) + + # 保存文件 + safe_title = "".join(c for c in title if c.isalnum() or c in (' ', '-', '_')).strip()[:50] + output_path = os.path.join(output_dir, f"{safe_title}.flv") + + with open(output_path, 'wb') as f: + f.write(video_data) + + print(f" ✅ 视频已保存: {output_path}") + print(f" 文件大小: {total_size / 1024 / 1024:.2f}MB") + + await browser.close() + + return output_path + +if __name__ == '__main__': + bvid = "BV1KtFzzqEUG" + result = asyncio.run(download_video_stream(bvid)) + if result: + print(f"\n✅ 下载完成！") + print(f"文件路径: {result}") + else: + print(f"\n❌ 下载失败") diff --git a/kb-bilibili-metadata/SKILL.md b/kb-bilibili-metadata/SKILL.md new file mode 100644 index 0000000..d90d862 --- /dev/null +++ b/kb-bilibili-metadata/SKILL.md @@ -0,0 +1,46 @@ +# KB Bilibili Metadata Skill + +**kb-bilibili-metadata** - Extract Bilibili video/article/up主 metadata. + +## Features + +- Video metadata extraction +- Article (专栏) metadata extraction +- UP主 information extraction +- JSON output format +- Playwright + HTTP API fallback + +## Commands + +```bash +# Video metadata +python bilibili_metadata.py --id "BV1xx411c7mD" --type video + +# Article metadata +python bilibili_metadata.py --id "cv43780186" --type article + +# UP主 info +python bilibili_metadata.py --id "7770724" --type up +``` + +## Output + +```json +{ + "success": true, + "data": { + "platform": "bilibili", + "type": "video", + "id": "BV1xx411c7mD", + "title": "视频标题", + "author": "UP主名字", + "stats": {"view": 100000, "like": 5000} + } +} +``` + +## Installation + +```bash +cp -r kb-bilibili-metadata/ ~/skills/ +``` diff --git a/kb-bilibili-metadata/__init__.py b/kb-bilibili-metadata/__init__.py new file mode 100644 index 0000000..0614e1f --- /dev/null +++ b/kb-bilibili-metadata/__init__.py @@ -0,0 +1,8 @@ +""" +bilibili-metadata 技能包 + +B站元数据提取工具 +""" + +__version__ = "1.0.0" +__author__ = "OpenClaw" diff --git a/kb-bilibili-metadata/__pycache__/bilibili_extractor.cpython-312.pyc b/kb-bilibili-metadata/__pycache__/bilibili_extractor.cpython-312.pyc new file mode 100644 index 0000000..49393a3 Binary files /dev/null and b/kb-bilibili-metadata/__pycache__/bilibili_extractor.cpython-312.pyc differ diff --git a/kb-bilibili-metadata/bilibili_extractor.py b/kb-bilibili-metadata/bilibili_extractor.py new file mode 100644 index 0000000..86fee7b --- /dev/null +++ b/kb-bilibili-metadata/bilibili_extractor.py @@ -0,0 +1,666 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +""" +B站元数据提取器 + +独立版本，不依赖 obsidian-kb 结构 +支持视频、专栏、UP主信息提取 +""" + +import asyncio +import json +import logging +import re +from datetime import datetime +from typing import Dict, Any, Optional +from urllib.parse import urlparse + +logger = logging.getLogger(__name__) + +# 默认请求头 +DEFAULT_HEADERS = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', + 'Referer': 'https://www.bilibili.com/', + 'Accept': 'application/json, text/plain, */*', + 'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8', +} + +try: + from playwright.async_api import async_playwright + PLAYWRIGHT_AVAILABLE = True +except ImportError: + PLAYWRIGHT_AVAILABLE = False + +try: + from undetected_playwright import stealth_async + STEALTH_AVAILABLE = True +except ImportError: + STEALTH_AVAILABLE = False + +try: + import httpx + HTTPX_AVAILABLE = True +except ImportError: + HTTPX_AVAILABLE = False + + +class BilibiliExtractor: + """ + B站元数据提取器 + + 支持： + - 视频信息提取（标题、作者、统计数据、字幕等） + - 专栏文章提取 + - UP主信息提取 + """ + + # 正则模式 + BV_PATTERN = re.compile(r'BV[a-zA-Z0-9]{10}') + CV_PATTERN = re.compile(r'cv(\d+)') + URL_PATTERN = re.compile(r'https?://www\.bilibili\.com/video/(BV[a-zA-Z0-9]{10})') + ARTICLE_URL_PATTERN = re.compile(r'https?://www\.bilibili\.com/read/(cv\d+)') + UP_URL_PATTERN = re.compile(r'https?://space\.bilibili\.com/(\d+)') + + def __init__(self, headless: bool = True, timeout: int = 30): + """ + 初始化提取器 + + Args: + headless: 是否使用无头模式（浏览器） + timeout: 超时时间（秒） + """ + self.headless = headless + self.timeout = timeout * 1000 # 转换为毫秒 + + def extract_video_metadata(self, bvid: str) -> Dict[str, Any]: + """ + 提取视频元数据 + + Args: + bvid: B站视频BV号（如 BV1xx411c7mD） + + Returns: + Dict containing metadata, stats, description, subtitle + """ + # 验证并解析BV号 + bvid = self._resolve_bvid(bvid) + if not bvid: + raise ValueError(f"无效的BV号: {bvid}") + + # 使用异步方法提取 + return asyncio.run(self._extract_video_async(bvid)) + + def extract_article_metadata(self, cvid: str) -> Dict[str, Any]: + """ + 提取专栏元数据 + + Args: + cvid: B站专栏CV号（如 cv43780186） + + Returns: + Dict containing article metadata + """ + # 解析CV号 + cvid = self._resolve_cvid(cvid) + if not cvid: + raise ValueError(f"无效的CV号: {cvid}") + + return asyncio.run(self._extract_article_async(cvid)) + + def extract_up_metadata(self, mid: str) -> Dict[str, Any]: + """ + 提取UP主信息 + + Args: + mid: B站用户ID（如 7770724） + + Returns: + Dict containing UP主信息 + """ + # 解析MID + mid = self._resolve_mid(mid) + if not mid: + raise ValueError(f"无效的MID: {mid}") + + return asyncio.run(self._extract_up_async(mid)) + + def _resolve_bvid(self, source_id: str) -> Optional[str]: + """解析并返回BV号""" + source = source_id.strip() + + # 直接BV号 + if self.BV_PATTERN.fullmatch(source): + return source + + # 完整URL + match = self.URL_PATTERN.match(source) + if match: + return match.group(1) + + return None + + def _resolve_cvid(self, source_id: str) -> Optional[str]: + """解析并返回CV号""" + source = source_id.strip() + + # 直接CV号（带cv前缀） + if source.startswith('cv'): + match = self.CV_PATTERN.match(source) + if match: + return source + + # 纯数字 + if source.isdigit(): + return f"cv{source}" + + # 完整URL + match = self.ARTICLE_URL_PATTERN.match(source) + if match: + return match.group(1) + + return None + + def _resolve_mid(self, source_id: str) -> Optional[str]: + """解析并返回MID""" + source = source_id.strip() + + # 纯数字 + if source.isdigit(): + return source + + # 完整URL + match = self.UP_URL_PATTERN.match(source) + if match: + return match.group(1) + + return None + + async def _extract_video_async(self, bvid: str) -> Dict[str, Any]: + """异步提取视频信息""" + url = f"https://www.bilibili.com/video/{bvid}" + result = { + 'metadata': {}, + 'stats': {}, + 'subtitle': '', + 'description': '' + } + + if not PLAYWRIGHT_AVAILABLE: + # 使用 HTTP API + return await self._extract_video_by_api(bvid) + + async with async_playwright() as playwright: + try: + browser = await playwright.chromium.launch( + headless=self.headless, + args=[ + '--no-sandbox', + '--disable-setuid-sandbox', + '--disable-blink-features=AutomationControlled', + '--disable-dev-shm-usage', + ] + ) + + context = await browser.new_context( + viewport={'width': 1920, 'height': 1080}, + user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', + locale='zh-CN', + ) + + if STEALTH_AVAILABLE: + await stealth_async(context) + + page = await context.new_page() + await page.goto(url, wait_until='domcontentloaded', timeout=self.timeout) + await asyncio.sleep(2) + + content = await page.content() + video_data = await self._try_extract_video_methods(page, content, bvid) + + if video_data: + result['metadata'] = { + 'title': video_data.get('title', ''), + 'author': video_data.get('author', ''), + 'bvid': video_data.get('bvid', ''), + 'aid': video_data.get('aid', ''), + 'mid': video_data.get('mid', ''), + 'pubtime': video_data.get('pubtime', ''), + 'duration': video_data.get('duration', ''), + 'url': url, + 'tags': video_data.get('tags', ''), + } + result['stats'] = { + 'view': video_data.get('view', 0), + 'danmaku': video_data.get('danmaku', 0), + 'reply': video_data.get('reply', 0), + 'favorite': video_data.get('favorite', 0), + 'coin': video_data.get('coin', 0), + 'share': video_data.get('share', 0), + 'like': video_data.get('like', 0), + } + result['description'] = video_data.get('desc', '') + + await browser.close() + + except Exception as e: + logger.error(f"视频提取错误: {e}") + # 回退到 API + return await self._extract_video_by_api(bvid) + + return result + + async def _extract_video_by_api(self, bvid: str) -> Dict[str, Any]: + """使用B站API提取视频信息""" + result = { + 'metadata': {}, + 'stats': {}, + 'subtitle': '', + 'description': '' + } + + try: + async with httpx.AsyncClient(timeout=30.0, headers=DEFAULT_HEADERS) as client: + # 获取视频信息 + response = await client.get('https://api.bilibili.com/x/web-interface/view', params={'bvid': bvid}) + if response.status_code == 200: + data = response.json() + if data.get('code') == 0: + video_data = data.get('data', {}) + + result['metadata'] = { + 'title': video_data.get('title', ''), + 'author': video_data.get('owner', {}).get('name', ''), + 'bvid': video_data.get('bvid', ''), + 'aid': video_data.get('aid', ''), + 'mid': video_data.get('owner', {}).get('mid', ''), + 'pubtime': datetime.fromtimestamp(video_data.get('pubdate', 0)).strftime('%Y-%m-%d %H:%M:%S') if video_data.get('pubdate') else '', + 'duration': self._format_duration(video_data.get('duration', 0)), + 'url': f"https://www.bilibili.com/video/{bvid}", + 'tags': ', '.join([t.get('tag_name', '') for t in video_data.get('tag', [])]), + } + + stat = video_data.get('stat', {}) + result['stats'] = { + 'view': stat.get('view', 0), + 'danmaku': stat.get('danmaku', 0), + 'reply': stat.get('reply', 0), + 'favorite': stat.get('favorite', 0), + 'coin': stat.get('coin', 0), + 'share': stat.get('share', 0), + 'like': stat.get('like', 0), + } + result['description'] = video_data.get('desc', '') + + except Exception as e: + logger.error(f"API提取错误: {e}") + + return result + + async def _try_extract_video_methods(self, page, content: str, bvid: str) -> Dict[str, Any]: + """尝试多种方法提取视频信息""" + video_data = {} + + # 方法1: 从 __INITIAL_STATE__ + try: + initial_state = await page.evaluate('() => typeof window.__INITIAL_STATE__ !== "undefined" ? window.__INITIAL_STATE__ : null') + if initial_state: + video_data = self._parse_video_state(initial_state) + if video_data and video_data.get('title'): + return video_data + except: + pass + + # 方法2: 使用 API（更可靠） + return await self._extract_video_by_api(bvid) + + def _parse_video_state(self, data: Dict) -> Dict[str, Any]: + """解析 __INITIAL_STATE__ 数据""" + video_data = {} + try: + video = data.get('videoData', {}) + video_data['title'] = video.get('title', '') + video_data['bvid'] = video.get('bvid', '') + video_data['aid'] = video.get('aid', '') + owner = video.get('owner', {}) + video_data['author'] = owner.get('name', '') + video_data['mid'] = owner.get('mid', '') + stat = video.get('stat', {}) + video_data['view'] = stat.get('view', 0) + video_data['danmaku'] = stat.get('danmaku', 0) + video_data['reply'] = stat.get('reply', 0) + video_data['favorite'] = stat.get('favorite', 0) + video_data['coin'] = stat.get('coin', 0) + video_data['share'] = stat.get('share', 0) + video_data['like'] = stat.get('like', 0) + pubdate = video.get('pubdate', 0) + video_data['pubtime'] = datetime.fromtimestamp(pubdate).strftime('%Y-%m-%d %H:%M:%S') if pubdate else '' + video_data['duration'] = self._format_duration(video.get('duration', 0)) + video_data['desc'] = video.get('desc', '') + video_data['tags'] = ', '.join([t.get('tag_name', '') for t in video.get('tag', [])]) + except: + pass + return video_data + + async def _extract_article_async(self, cvid: str) -> Dict[str, Any]: + """异步提取专栏信息""" + result = {} + + if not HTTPX_AVAILABLE: + return {'error': 'httpx 未安装'} + + try: + async with httpx.AsyncClient(timeout=30.0, headers=DEFAULT_HEADERS) as client: + # 获取专栏信息 + response = await client.get('https://api.bilibili.com/x/article/viewinfo', params={'id': cvid[2:]}) + if response.status_code == 200: + data = response.json() + if data.get('code') == 0: + article = data.get('data', {}) + result = { + 'cvid': cvid, + 'title': article.get('title', ''), + 'author': article.get('author_name', ''), + 'mid': article.get('author_mid', ''), + 'publish_time': datetime.fromtimestamp(article.get('publish_time', 0)).strftime('%Y-%m-%d %H:%M:%S') if article.get('publish_time') else '', + 'view_count': article.get('stats', {}).get('view', 0), + 'like_count': article.get('stats', {}).get('like', 0), + 'coin_count': article.get('stats', {}).get('coin', 0), + 'share_count': article.get('stats', {}).get('share', 0), + 'reply_count': article.get('stats', {}).get('reply', 0), + 'url': f"https://www.bilibili.com/read/{cvid}", + 'summary': article.get('summary', ''), + 'word_count': article.get('words', 0), + } + except Exception as e: + logger.error(f"专栏提取错误: {e}") + result = {'error': str(e)} + + return result + + async def _extract_up_async(self, mid: str) -> Dict[str, Any]: + """ + 异步提取UP主信息（支持订阅跟踪） + + Args: + mid: UP主ID + + Returns: + Dict containing UP主完整信息 + """ + result = { + 'type': 'up', + 'mid': mid, + 'subscribed': False, + 'basic_info': {}, + 'subscription_info': {} + } + + if not HTTPX_AVAILABLE: + return {'error': 'httpx 未安装'} + + try: + async with httpx.AsyncClient(timeout=30.0, headers=DEFAULT_HEADERS) as client: + # 获取UP主基本信息 + response = await client.get('https://api.bilibili.com/x/space/acc/info', params={'mid': mid}) + if response.status_code == 200: + data = response.json() + if data.get('code') == 0: + up = data.get('data', {}) + result['basic_info'] = { + 'name': up.get('name', ''), + 'sex': up.get('sex', ''), + 'face': up.get('face', ''), + 'sign': up.get('sign', ''), + 'level': up.get('level', 0), + 'vip_type': up.get('vip', {}).get('type', 0), + 'vip_status': up.get('vip', {}).get('status', 0), + 'following_count': up.get('following', 0), + 'follower_count': up.get('follower', 0), + 'url': f"https://space.bilibili.com/{mid}", + } + + # 获取UP主视频统计 + stats_response = await client.get('https://api.bilibili.com/x/space/navnum', params={'mid': mid}) + if stats_response.status_code == 200: + stats_data = stats_response.json() + if stats_data.get('code') == 0: + result['basic_info']['video_count'] = stats_data.get('data', {}).get('video', 0) + + # 获取UP主专栏数量 + article_response = await client.get('https://api.bilibili.com/x/space/article', params={'mid': mid, 'pn': 1, 'ps': 1}) + if article_response.status_code == 200: + article_data = article_response.json() + if article_data.get('code') == 0: + result['basic_info']['article_count'] = article_data.get('data', {}).get('count', 0) + + # 获取UP主最近视频（用于跟踪更新） + video_response = await client.get('https://api.bilibili.com/x/space/arc/search', + params={'mid': mid, 'pn': 1, 'ps': 1, 'order': 'pubtime'}) + if video_response.status_code == 200: + video_data = video_response.json() + if video_data.get('code') == 0: + videos = video_data.get('data', {}).get('list', {}).get('vlist', []) + if videos: + latest_video = videos[0] + result['subscription_info'] = { + 'last_video_id': latest_video.get('bvid', ''), + 'last_video_title': latest_video.get('title', ''), + 'last_video_time': datetime.fromtimestamp(latest_video.get('created', 0)).strftime('%Y-%m-%d %H:%M:%S') if latest_video.get('created') else '', + } + + # 获取UP主最近专栏（用于跟踪更新） + article_response = await client.get('https://api.bilibili.com/x/space/article', + params={'mid': mid, 'pn': 1, 'ps': 1, 'sort': 'publish_time'}) + if article_response.status_code == 200: + article_data = article_response.json() + if article_data.get('code') == 0: + articles = article_data.get('data', {}).get('articles', []) + if articles: + latest_article = articles[0] + if 'last_article' not in result['subscription_info']: + result['subscription_info']['last_article'] = {} + result['subscription_info']['last_article'] = { + 'id': latest_article.get('id', 0), + 'title': latest_article.get('title', ''), + 'time': datetime.fromtimestamp(latest_article.get('publish_time', 0)).strftime('%Y-%m-%d %H:%M:%S') if latest_article.get('publish_time') else '', + } + + except Exception as e: + logger.error(f"UP主提取错误: {e}") + result = {'error': str(e)} + + return result + + def _format_duration(self, seconds: int) -> str: + """格式化时长（秒 -> HH:MM:SS）""" + if not seconds: + return '' + hours = seconds // 3600 + minutes = (seconds % 3600) // 60 + secs = seconds % 60 + if hours > 0: + return f"{hours:02d}:{minutes:02d}:{secs:02d}" + else: + return f"{minutes:02d}:{secs:02d}" + + async def _extract_series_async(self, mid: str, series_id: str) -> Dict[str, Any]: + """ + 异步提取系列合集信息（不包含列表内容） + + Args: + mid: UP主ID + series_id: 系列ID + + Returns: + Dict containing series basic info + """ + result = { + 'type': 'series', + 'series_id': series_id, + 'mid': mid, + 'subscribed': False, + 'basic_info': {} + } + + if not HTTPX_AVAILABLE: + return {'error': 'httpx 未安装'} + + try: + async with httpx.AsyncClient(timeout=30.0, headers=DEFAULT_HEADERS) as client: + # 获取系列信息 + response = await client.get('https://api.bilibili.com/x/space/series', + params={'mid': mid, 'series_id': series_id, 'pn': 1, 'ps': 1}) + if response.status_code == 200: + data = response.json() + if data.get('code') == 0: + series_info = data.get('data', {}).get('list', {}) + result['basic_info'] = { + 'title': series_info.get('title', ''), + 'description': series_info.get('desc', ''), + 'cover': series_info.get('cover', ''), + 'mid': mid, + 'creator_name': '', + 'total_count': series_info.get('cnt', 0), + 'last_updated': '', + 'update_count': 0 + } + + # 获取创作者信息 + up_info = await client.get('https://api.bilibili.com/x/space/acc/info', + params={'mid': mid}) + if up_info.status_code == 200: + up_data = up_info.json() + if up_data.get('code') == 0: + result['basic_info']['creator_name'] = up_data.get('data', {}).get('name', '') + + except Exception as e: + logger.error(f"系列合集提取错误: {e}") + result = {'error': str(e)} + + return result + + async def _extract_readlist_async(self, rl_id: str) -> Dict[str, Any]: + """ + 异步提取专栏合集信息（不包含列表内容） + + Args: + rl_id: 专栏合集ID (rl开头) + + Returns: + Dict containing readlist basic info + """ + result = { + 'type': 'readlist', + 'readlist_id': rl_id, + 'subscribed': False, + 'basic_info': {} + } + + if not HTTPX_AVAILABLE: + return {'error': 'httpx 未安装'} + + try: + async with httpx.AsyncClient(timeout=30.0, headers=DEFAULT_HEADERS) as client: + # 获取专栏合集信息 + response = await client.get('https://api.bilibili.com/x/article/readlist', + params={'id': rl_id.replace('rl', '')}) + if response.status_code == 200: + data = response.json() + if data.get('code') == 0: + list_info = data.get('data', {}) + result['basic_info'] = { + 'title': list_info.get('name', ''), + 'description': list_info.get('description', ''), + 'cover': list_info.get('cover', ''), + 'mid': list_info.get('mid', ''), + 'creator_name': '', + 'total_count': list_info.get('articles_count', 0), + 'last_updated': '', + 'is_public': list_info.get('public', True) + } + + # 获取创作者信息 + mid = list_info.get('mid', '') + if mid: + up_info = await client.get('https://api.bilibili.com/x/space/acc/info', + params={'mid': mid}) + if up_info.status_code == 200: + up_data = up_info.json() + if up_data.get('code') == 0: + result['basic_info']['creator_name'] = up_data.get('data', {}).get('name', '') + + except Exception as e: + logger.error(f"专栏合集提取错误: {e}") + result = {'error': str(e)} + + return result + + async def _extract_favlist_async(self, fid: str) -> Dict[str, Any]: + """ + 异步提取收藏夹信息（不包含列表内容） + + Args: + fid: 收藏夹ID + + Returns: + Dict containing favlist basic info + """ + result = { + 'type': 'favlist', + 'favlist_id': fid, + 'subscribed': False, + 'basic_info': {} + } + + if not HTTPX_AVAILABLE: + return {'error': 'httpx 未安装'} + + try: + async with httpx.AsyncClient(timeout=30.0, headers=DEFAULT_HEADERS) as client: + # 获取收藏夹信息 + response = await client.get('https://api.bilibili.com/x/space/favlist', + params={'fid': fid, 'pn': 1, 'ps': 1}) + if response.status_code == 200: + data = response.json() + if data.get('code') == 0: + fav_info = data.get('data', {}) + result['basic_info'] = { + 'title': fav_info.get('title', ''), + 'description': fav_info.get('intro', ''), + 'cover': fav_info.get('cover', ''), + 'mid': fav_info.get('mid', ''), + 'creator_name': '', + 'total_count': fav_info.get('media_count', 0), + 'is_public': fav_info.get('public', True), + 'like_count': fav_info.get('like', 0) + } + + # 获取创作者信息 + mid = fav_info.get('mid', '') + if mid: + up_info = await client.get('https://api.bilibili.com/x/space/acc/info', + params={'mid': mid}) + if up_info.status_code == 200: + up_data = up_info.json() + if up_data.get('code') == 0: + result['basic_info']['creator_name'] = up_data.get('data', {}).get('name', '') + + except Exception as e: + logger.error(f"收藏夹提取错误: {e}") + result = {'error': str(e)} + + return result + + +# 测试代码 +if __name__ == '__main__': + extractor = BilibiliExtractor() + + print("=" * 60) + print("B站元数据提取器测试") + print("=" * 60) + + # 测试视频 + print("\n测试视频提取: BV1MnFNz5EDL") + result = extractor.extract_video_metadata('BV1MnFNz5EDL') + print(json.dumps(result, ensure_ascii=False, indent=2)) diff --git a/kb-bilibili-metadata/bilibili_metadata.py b/kb-bilibili-metadata/bilibili_metadata.py new file mode 100644 index 0000000..f4635fd --- /dev/null +++ b/kb-bilibili-metadata/bilibili_metadata.py @@ -0,0 +1,228 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +""" +B站元数据提取 CLI 工具 + +支持命令行调用，输出 JSON 格式数据 +""" + +import argparse +import asyncio +import json +import os +import sys +from pathlib import Path +from typing import Dict, Any + +from bilibili_extractor import BilibiliExtractor + + +def format_number(num: int) -> str: + """格式化数字""" + if num >= 100000000: + return f"{num / 100000000:.1f}亿" + elif num >= 10000: + return f"{num / 10000:.1f}万" + else: + return f"{num:,}" + + +def extract_video(extractor: BilibiliExtractor, bvid: str, output_file: str = None) -> Dict[str, Any]: + """提取视频元数据""" + result = extractor.extract_video_metadata(bvid) + + # 如果需要输出到文件 + if output_file: + with open(output_file, 'w', encoding='utf-8') as f: + json.dump(result, f, ensure_ascii=False, indent=2) + + return result + + +def extract_article(extractor: BilibiliExtractor, cvid: str, output_file: str = None) -> Dict[str, Any]: + """提取专栏元数据""" + result = extractor.extract_article_metadata(cvid) + + if output_file: + with open(output_file, 'w', encoding='utf-8') as f: + json.dump(result, f, ensure_ascii=False, indent=2) + + return result + + +def extract_up(extractor: BilibiliExtractor, mid: str, output_file: str = None) -> Dict[str, Any]: + """提取UP主信息（包含订阅跟踪所需信息）""" + result = asyncio.run(extractor._extract_up_async(mid)) + + if output_file: + with open(output_file, 'w', encoding='utf-8') as f: + json.dump(result, f, ensure_ascii=False, indent=2) + + return result + + +def extract_series(extractor: BilibiliExtractor, mid: str, series_id: str, output_file: str = None) -> Dict[str, Any]: + """提取系列合集元数据""" + result = asyncio.run(extractor._extract_series_async(mid, series_id)) + + if output_file: + with open(output_file, 'w', encoding='utf-8') as f: + json.dump(result, f, ensure_ascii=False, indent=2) + + return result + + +def extract_readlist(extractor: BilibiliExtractor, rl_id: str, output_file: str = None) -> Dict[str, Any]: + """提取专栏合集元数据""" + result = asyncio.run(extractor._extract_readlist_async(rl_id)) + + if output_file: + with open(output_file, 'w', encoding='utf-8') as f: + json.dump(result, f, ensure_ascii=False, indent=2) + + return result + + +def extract_favlist(extractor: BilibiliExtractor, fid: str, output_file: str = None) -> Dict[str, Any]: + """提取收藏夹元数据""" + result = asyncio.run(extractor._extract_favlist_async(fid)) + + if output_file: + with open(output_file, 'w', encoding='utf-8') as f: + json.dump(result, f, ensure_ascii=False, indent=2) + + return result + + +def main(): + """主函数""" + parser = argparse.ArgumentParser( + description='B站元数据提取工具', + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +示例: + # 提取视频元数据 + python bilibili_metadata.py --id "BV1xx411c7mD" --type video + + # 提取专栏元数据 + python bilibili_metadata.py --id "cv43780186" --type article + + # 提取UP主信息 + python bilibili_metadata.py --id "7770724" --type up + + # 提取系列合集信息 + python bilibili_metadata.py --id "123456" --type series --mid "7770724" + + # 提取专栏合集信息 + python bilibili_metadata.py --id "rl123456" --type readlist + + # 提取收藏夹信息 + python bilibili_metadata.py --id "123456" --type favlist + + # 输出到文件 + python bilibili_metadata.py --id "BV1xx411c7mD" --type video --output result.json + """ + ) + + parser.add_argument( + '--id', + required=True, + help='B站资源ID（BV号、CV号或UP主ID）' + ) + parser.add_argument( + '--type', + required=True, + choices=['video', 'article', 'up', 'series', 'readlist', 'favlist'], + help='资源类型' + ) + parser.add_argument( + '--mid', + help='UP主ID (用于series类型)' + ) + parser.add_argument( + '--output', + '-o', + help='输出文件路径（JSON格式）' + ) + parser.add_argument( + '--headless', + action='store_true', + default=True, + help='使用无头模式（浏览器，默认开启，使用API）' + ) + parser.add_argument( + '--timeout', + type=int, + default=30, + help='超时时间（秒，默认30）' + ) + parser.add_argument( + '--pretty', + action='store_true', + default=True, + help='格式化输出（默认开启）' + ) + + args = parser.parse_args() + + # 创建提取器 + extractor = BilibiliExtractor(headless=args.headless, timeout=args.timeout) + + try: + # 根据类型提取数据 + if args.type == 'video': + result = extract_video(extractor, args.id, args.output) + elif args.type == 'article': + result = extract_article(extractor, args.id, args.output) + elif args.type == 'up': + result = extract_up(extractor, args.id, args.output) + elif args.type == 'series': + if not args.mid: + print(json.dumps({ + "success": False, + "error": "series类型需要提供 --mid 参数" + }, ensure_ascii=False, indent=2)) + sys.exit(1) + result = extract_series(extractor, args.mid, args.id, args.output) + elif args.type == 'readlist': + result = extract_readlist(extractor, args.id, args.output) + elif args.type == 'favlist': + result = extract_favlist(extractor, args.id, args.output) + else: + print(json.dumps({ + "success": False, + "error": f"不支持的类型 {args.type}" + }, ensure_ascii=False, indent=2)) + sys.exit(1) + + # 生成文件名 + platform = "bilibili" + filename = f"{platform}_{args.id}.meta.json" + filepath = args.output or filename + + # 统一输出格式 + output = { + "success": True, + "filename": filename, + "filepath": str(Path(filepath).resolve()) if filepath else None, + "message": f"{args.type}元数据提取成功" + } + + print(json.dumps(output, ensure_ascii=False, indent=2)) + + # 如果指定了输出路径，则写入文件 + if args.output: + with open(args.output, 'w', encoding='utf-8') as f: + json.dump(result, f, ensure_ascii=False, indent=2) + + except Exception as e: + print(json.dumps({ + "success": False, + "error": str(e), + "detail": type(e).__name__ + }, ensure_ascii=False, indent=2)) + sys.exit(1) + + +if __name__ == '__main__': + main() diff --git a/kb-deep-analyzer/SKILL.md b/kb-deep-analyzer/SKILL.md new file mode 100644 index 0000000..4cbf26c --- /dev/null +++ b/kb-deep-analyzer/SKILL.md @@ -0,0 +1,94 @@ +# KB Deep Analyzer Skill + +**kb-deep-analyzer** - AI-powered deep content analysis. + +## Features + +- Multi-type analysis (tutorial, documentation, news) +- Template-based output +- Quality scoring +- Automatic tagging +- **多格式元数据支持**: 支持扁平结构 `{"title":"xxx"}` 和嵌套结构 `{"data":{"metadata":{...}}}` + +## Commands + +```bash +# 分析内容（推荐：使用 -u 参数强制无缓冲输出） +AI_API_KEY="your-api-key" AI_PROVIDER="zhipu" AI_MODEL="glm-4.7" \ + python3 -u deep_analyzer.py --metadata meta.json --content content.json --output analysis.md + +# 指定类型 +python deep_analyzer.py --metadata meta.json --content content.json --type tutorial --output tutorial.md + +# 指定 AI 提供商 +python deep_analyzer.py -m meta.json -c content.json -o out.md --provider zhipu --model glm-4 +``` + +## 环境变量配置 + +**必须设置以下环境变量**： + +```bash +export AI_API_KEY="your-api-key" +export AI_PROVIDER="zhipu" # 或 openai, minimax +export AI_MODEL="glm-4.7" # 模型名称 +export AI_BASE_URL="https://..." # 可选，自定义 API 地址 +``` + +### 重要提示 + +**必须使用 `-u` 参数运行 Python**，确保输出实时显示在终端： + +```bash +python3 -u deep_analyzer.py ... +``` + +如果不使用 `-u` 参数，Python 的 stdout 缓冲会导致输出延迟或看不到进度。 + +## 执行方式选择 + +### 方式1: 并发执行（推荐，默认） +- 使用 `batch_size=3`（默认） +- 6个分片约 100 秒完成 +- 适合快速分析 + +```bash +python3 -u deep_analyzer.py --metadata meta.json --content content.json -o out.md +``` + +### 方式2: 顺序执行 +- 使用 `batch_size=1` +- 6个分片约 735 秒完成 +- 适合调试和问题排查 + +```bash +# 在代码中设置 batch_size=1 +# analyzer.analyze(metadata, content, "video", batch_size=1) +``` + +## Metadata Format + +支持两种元数据格式： + +```json +// 格式1: 扁平结构 +{ + "title": "视频标题", + "author": "作者名", + "duration": 619, + "bvid": "BVxxx" +} + +// 格式2: 嵌套结构（kb-bilibili-metadata 输出） +{ + "data": { + "metadata": { + "title": "视频标题", + "author": "作者名", + "duration": "10:19" + } + } +} +``` + +会自动转换为扁平格式进行分析。 diff --git a/kb-deep-analyzer/__pycache__/deep_analyzer.cpython-312.pyc b/kb-deep-analyzer/__pycache__/deep_analyzer.cpython-312.pyc new file mode 100644 index 0000000..4837a2e Binary files /dev/null and b/kb-deep-analyzer/__pycache__/deep_analyzer.cpython-312.pyc differ diff --git a/kb-deep-analyzer/ai_client.py b/kb-deep-analyzer/ai_client.py new file mode 100644 index 0000000..cee3c73 --- /dev/null +++ b/kb-deep-analyzer/ai_client.py @@ -0,0 +1,514 @@ +"""Obsidian KB - AI客户端 +支持多个 AI 提供商和 fallback 机制 +""" +import os +import json +import requests +from typing import Dict, Any, List, Optional, Tuple +from src.models import ContentType +from src.config import get_config +from src.content_chunker import ContentChunker, get_chunking_strategy, chunk_content + + +class AIClient: + """ + AI客户端 - 支持分段分析长视频内容和 fallback 机制 + """ + + def __init__(self): + self.config = get_config() + self.chunker = ContentChunker() + # 获取 AI 配置 + self._load_ai_config() + + def _load_ai_config(self) -> None: + """加载 AI 配置（主 provider + fallbacks）""" + self.ai_configs = [] + + # 加载主配置 + main_provider = self.config.get('ai.provider', 'openai') + main_config = { + 'provider': main_provider, + 'api_key': self.config.get('ai.api_key'), + 'model': self.config.get('ai.model', 'gpt-4'), + 'base_url': self.config.get('ai.base_url'), + 'is_primary': True + } + self.ai_configs.append(main_config) + + # 加载 fallback 配置 + fallbacks = self.config.get('ai.fallbacks', []) + for fb in fallbacks: + self.ai_configs.append({ + 'provider': fb.get('provider'), + 'api_key': fb.get('api_key'), + 'model': fb.get('model'), + 'base_url': fb.get('base_url'), + 'is_primary': False + }) + + def _call_api_with_fallback(self, prompt: str, max_tokens: int = 1000, response_format: str = 'text') -> Tuple[bool, str]: + """ + 使用 fallback 机制调用 API + + Args: + prompt: 提示词 + max_tokens: 最大 token 数 + response_format: 响应格式 ('text' 或 'json') + + Returns: + (success, response) 元组 + """ + last_error = None + + for i, ai_config in enumerate(self.ai_configs): + try: + if not ai_config.get('api_key'): + print(f"[AIClient] 跳过 {ai_config.get('provider')} - API Key 为空") + continue + + provider_type = ai_config.get('provider') + print(f"[AIClient] 尝试使用 {provider_type} (优先级 {i+1}/{len(self.ai_configs)})...") + + response = self._call_single_provider(ai_config, prompt, max_tokens, response_format) + return True, response + + except Exception as e: + last_error = e + print(f"[AIClient] {provider_type} 调用失败: {e}") + continue + + # 所有 provider 都失败了 + error_msg = f"所有 AI 提供商均失败，最后错误: {last_error}" if last_error else "没有可用的 AI 配置" + print(f"[AIClient] {error_msg}") + return False, self._mock_generate(prompt, max_tokens) # 返回 mock 响应作为兜底 + + def _call_single_provider(self, ai_config: Dict, prompt: str, max_tokens: int, response_format: str) -> str: + """ + 调用单个 AI 提供商 + + Args: + ai_config: AI 配置 + prompt: 提示词 + max_tokens: 最大 token 数 + response_format: 响应格式 + + Returns: + API 响应文本 + """ + provider = ai_config.get('provider') + api_key = ai_config.get('api_key') + model = ai_config.get('model') + base_url = ai_config.get('base_url') + + if provider == 'minimax': + return self._call_minimax(api_key, model, base_url, prompt, max_tokens, response_format) + elif provider == 'zhipu': + return self._call_zhipu(api_key, model, base_url, prompt, max_tokens, response_format) + elif provider == 'alibaba': + return self._call_alibaba(api_key, model, base_url, prompt, max_tokens, response_format) + elif provider == 'openai': + return self._call_openai(api_key, model, base_url, prompt, max_tokens, response_format) + else: + raise ValueError(f"不支持的 provider: {provider}") + + def _call_minimax(self, api_key: str, model: str, base_url: str, prompt: str, max_tokens: int, response_format: str) -> str: + """调用 MiniMax API (Anthropic Messages 兼容接口)""" + url = base_url or "https://api.minimaxi.com/anthropic/v1/messages" + + headers = { + "Authorization": f"Bearer {api_key}", + "Content-Type": "application/json" + } + + payload = { + "model": model, + "max_tokens": max_tokens, + "messages": [ + {"role": "user", "content": prompt} + ] + } + + if response_format == 'json': + payload['messages'][0]['content'] = prompt + "\n\n请直接返回 JSON 格式，不要有其他文字。" + + response = requests.post(url, headers=headers, json=payload, timeout=30) + response.raise_for_status() + data = response.json() + + # MiniMax 返回的是 Anthropic 格式，content 是一个数组 + # 需要找到 type='text' 的元素 + for item in data.get('content', []): + if item.get('type') == 'text': + return item.get('text', '') + + # 如果没有找到 text 类型，返回第一个元素的值（兼容旧格式） + return data.get('content', [{}])[0].get('text', '') + + def _call_zhipu(self, api_key: str, model: str, base_url: str, prompt: str, max_tokens: int, response_format: str) -> str: + """调用智谱 AI API (OpenAI 兼容接口)""" + # 确保 base_url 包含 /chat/completions + if base_url and not base_url.endswith('/chat/completions'): + url = f"{base_url}/chat/completions" + else: + url = base_url or "https://open.bigmodel.cn/api/paas/v4/chat/completions" + + headers = { + "Authorization": f"Bearer {api_key}", + "Content-Type": "application/json" + } + + payload = { + "model": model, + "max_tokens": max_tokens, + "messages": [ + {"role": "user", "content": prompt} + ] + } + + response = requests.post(url, headers=headers, json=payload, timeout=30) + response.raise_for_status() + data = response.json() + return data['choices'][0]['message']['content'] + + def _call_alibaba(self, api_key: str, model: str, base_url: str, prompt: str, max_tokens: int, response_format: str) -> str: + """调用阿里云通义千问 API (OpenAI 兼容接口)""" + url = f"{base_url}/chat/completions" + + headers = { + "Authorization": f"Bearer {api_key}", + "Content-Type": "application/json" + } + + payload = { + "model": model, + "max_tokens": max_tokens, + "messages": [ + {"role": "user", "content": prompt} + ] + } + + response = requests.post(url, headers=headers, json=payload, timeout=30) + response.raise_for_status() + data = response.json() + return data['choices'][0]['message']['content'] + + def _call_openai(self, api_key: str, model: str, base_url: str, prompt: str, max_tokens: int, response_format: str) -> str: + """调用 OpenAI API""" + url = base_url or "https://api.openai.com/v1/chat/completions" + + headers = { + "Authorization": f"Bearer {api_key}", + "Content-Type": "application/json" + } + + payload = { + "model": model, + "max_tokens": max_tokens, + "messages": [ + {"role": "user", "content": prompt} + ] + } + + response = requests.post(url, headers=headers, json=payload, timeout=30) + response.raise_for_status() + data = response.json() + return data['choices'][0]['message']['content'] + + def quick_generate(self, prompt: str, max_tokens: int = 100) -> str: + """快速生成（用于轻量扫描）""" + success, response = self._call_api_with_fallback(prompt, max_tokens, 'text') + return response + + def generate_json(self, prompt: str) -> Dict[str, Any]: + """生成JSON格式响应""" + success, response = self._call_api_with_fallback(prompt, 1000, 'json') + try: + return json.loads(response) + except: + return self._parse_json_from_text(response) + + def _deep_analyze(self, content_text: str, content_type: str, duration: Optional[int] = None) -> Dict[str, Any]: + """ + C5.3: 深度分析入口，根据内容时长决定是否分段分析 + + Args: + content_text: 内容文本 + content_type: 内容类型 + duration: 视频时长（秒） + + Returns: + 分析结果字典 + """ + duration = duration or 0 + + print(f"[AIClient] 深度分析: type={content_type}, duration={duration}s") + + # 长视频（>=30分钟）且是视频类型，使用分段分析 + if duration >= 1800 and content_type == "video": + print(f"[AIClient] 使用分段分析策略") + return self._analyze_in_chunks(content_text, duration) + + # 短视频直接分析 + print(f"[AIClient] 使用直接分析策略") + return self._analyze_direct(content_text) + + def _analyze_in_chunks(self, content_text: str, duration: int) -> Dict[str, Any]: + """ + C5.3: 分段分析长视频 + + Args: + content_text: SRT字幕文本 + duration: 视频时长（秒） + + Returns: + 合并后的分析结果 + """ + # 1. 获取分段策略 + strategy = get_chunking_strategy(duration) + print(f"[AIClient] 分段策略: {strategy['description']}") + + # 2. 执行分片 + chunks = chunk_content(content_text, duration) + print(f"[AIClient] 内容已分为 {len(chunks)} 段") + + # 3. 逐段分析 + chunk_summaries = [] + for i, chunk in enumerate(chunks): + print(f"[AIClient] 分析第 {i+1}/{len(chunks)} 段...") + summary = self._analyze_chunk(chunk.text, chunk.index) + + # 处理时间格式（可能是float秒数或字符串） + start_time = chunk.start_time + end_time = chunk.end_time + if isinstance(start_time, (int, float)): + start_time = self._format_time(start_time) + if isinstance(end_time, (int, float)): + end_time = self._format_time(end_time) + + chunk_summaries.append({ + 'index': chunk.index, + 'start_time': start_time, + 'end_time': end_time, + 'summary': summary + }) + + # 4. 合并所有段摘要 + print(f"[AIClient] 合并 {len(chunk_summaries)} 段分析结果") + final_result = self._merge_summaries(chunk_summaries, "video") + + # 5. 构建完整时间轴 + final_result['timeline'] = self._build_timeline_from_chunks(chunk_summaries) + + return final_result + + def _analyze_chunk(self, chunk_text: str, chunk_index: int) -> str: + """ + C5.3: 分析单个内容分片 + + Args: + chunk_text: 分片文本 + chunk_index: 分片索引 + + Returns: + 分片摘要（限制500字以内） + """ + # 截断文本避免过长 + text_sample = chunk_text[:3000] if len(chunk_text) > 3000 else chunk_text + + prompt = f"""请对以下视频片段进行简要分析（限制在300字以内）： + +片段内容： +{text_sample} + +请提供： +1. 这段的核心主题（50字以内） +2. 关键要点（3-5条） +3. 重要细节或引用 + +请用中文回答，控制在300字以内。""" + + try: + summary = self.quick_generate(prompt, max_tokens=500) + # 确保不超过500字 + if len(summary) > 500: + summary = summary[:497] + "..." + return summary + except Exception as e: + print(f"[AIClient] 分片 {chunk_index} 分析失败: {e}") + return f"第{chunk_index+1}段分析失败" + + def _merge_summaries(self, chunk_summaries: List[Dict], content_type: str) -> Dict[str, Any]: + """ + C5.3: 合并所有段摘要，生成完整分析报告 + + Args: + chunk_summaries: 各段摘要列表 + content_type: 内容类型 + + Returns: + 完整分析结果 + """ + # 构建合并提示 + summaries_text = "\n\n".join([ + f"=== 第{s['index']+1}段 ({s['start_time']}-{s['end_time']}) ===\n{s['summary']}" + for s in chunk_summaries + ]) + + prompt = f"""基于以下各段分析，生成完整的视频分析报告： + +{summaries_text} + +请提供以下格式的JSON： +{{ + "summary": "整体摘要（200字以内）", + "topics": ["主题1", "主题2", "主题3", "主题4"], + "insights": ["深入见解1", "深入见解2", "深入见解3"], + "actions": ["建议行动1", "建议行动2"], + "full_analysis": "详细分析（500字以内）" +}}""" + + try: + result = self.generate_json(prompt) + + # 确保必要字段存在 + if 'topics' not in result: + result['topics'] = ["主题A", "主题B", "主题C"] + if 'insights' not in result: + result['insights'] = ["重要见解1", "重要见解2"] + if 'actions' not in result: + result['actions'] = [] + if 'summary' not in result: + result['summary'] = "长视频分析完成" + if 'full_analysis' not in result: + result['full_analysis'] = summaries_text[:500] + + return result + + except Exception as e: + print(f"[AIClient] 合并摘要失败: {e}") + # 返回基础合并结果 + return { + 'summary': f'视频共分为{len(chunk_summaries)}个部分进行分析', + 'topics': [f"主题{i+1}" for i in range(min(4, len(chunk_summaries)))], + 'insights': ['从分段分析中综合得出'], + 'actions': [], + 'full_analysis': summaries_text[:800] + } + + def _analyze_direct(self, content_text: str) -> Dict[str, Any]: + """直接分析（不分段）""" + # 截断文本 + text_sample = content_text[:5000] if len(content_text) > 5000 else content_text + + prompt = f"""请分析以下内容，提供JSON格式结果： + +{text_sample} + +返回格式： +{{ + "summary": "整体摘要（150字以内）", + "topics": ["主题1", "主题2", "主题3"], + "insights": ["见解1", "见解2"], + "actions": ["行动建议1"], + "timeline": [ + {{"start_time": "00:00", "end_time": "05:00", "title": "第一部分", "summary": "..."}} + ] +}}""" + + try: + return self.generate_json(prompt) + except Exception as e: + print(f"[AIClient] 直接分析失败: {e}") + return { + 'summary': '分析失败', + 'topics': ['无法解析'], + 'insights': ['请检查内容格式'], + 'actions': [], + 'timeline': [] + } + + def _format_time(self, seconds: float) -> str: + """格式化秒数为时间字符串""" + hours = int(seconds // 3600) + minutes = int((seconds % 3600) // 60) + secs = int(seconds % 60) + if hours > 0: + return f"{hours:02d}:{minutes:02d}:{secs:02d}" + return f"{minutes:02d}:{secs:02d}" + + def _build_timeline_from_chunks(self, chunk_summaries: List[Dict]) -> List[Dict[str, Any]]: + """从分片摘要构建时间轴""" + timeline = [] + for summary in chunk_summaries: + timeline.append({ + 'index': summary['index'], + 'start_time': summary['start_time'], + 'end_time': summary['end_time'], + 'title': f"第{summary['index']+1}部分", + 'summary': summary['summary'][:200] + "..." if len(summary['summary']) > 200 else summary['summary'] + }) + return timeline + + def _mock_generate(self, prompt: str, max_tokens: int) -> str: + """模拟AI生成（实际实现应调用真实API）""" + # 根据prompt内容返回模拟响应 + prompt_lower = prompt.lower() + + if 'json' in prompt_lower or 'json格式' in prompt: + if '主题' in prompt or 'topic' in prompt_lower: + return json.dumps({ + 'summary': '这是一个关于人工智能和技术发展的内容，涵盖了多个重要主题。', + 'topics': ['人工智能', '机器学习', '未来发展', '技术趋势'], + 'insights': [ + 'AI正在改变我们的工作方式', + '机器学习应用越来越广泛', + '未来技术发展趋势值得关注' + ], + 'actions': ['深入研究相关技术', '关注行业动态'], + 'full_analysis': '详细分析内容...' + }, ensure_ascii=False) + return json.dumps({'result': '模拟JSON响应'}) + + if '摘要' in prompt or 'summary' in prompt_lower: + return '这是一段关于人工智能发展的重要讨论，涵盖了技术趋势和未来应用。' + + if '关键词' in prompt or 'keyword' in prompt_lower: + return '人工智能, 机器学习, 深度学习, 神经网络, 自然语言处理' + + return '模拟AI响应内容' + + def _parse_json_from_text(self, text: str) -> Dict[str, Any]: + """从文本中解析JSON""" + # 尝试提取JSON块 + import re + json_match = re.search(r'\{[\s\S]*\}', text) + if json_match: + try: + return json.loads(json_match.group()) + except: + pass + return {'raw_response': text} + + +class MultiAIClient: + """ + 多AI客户端 - 支持多种AI提供商的客户端 + """ + + def __init__(self): + self.config = get_config() + self.primary_client = AIClient() + self.clients = { + 'openai': self.primary_client, + 'local': AIClient(), # 可以配置为本地模型 + } + + def _deep_analyze(self, content_text: str, content_type: str, duration: Optional[int] = None) -> Dict[str, Any]: + """使用主客户端进行深度分析""" + return self.primary_client._deep_analyze(content_text, content_type, duration) + + def quick_generate(self, prompt: str, max_tokens: int = 100, provider: str = None) -> str: + """快速生成""" + client = self.clients.get(provider, self.primary_client) + return client.quick_generate(prompt, max_tokens) diff --git a/kb-deep-analyzer/deep_analyzer.py b/kb-deep-analyzer/deep_analyzer.py new file mode 100644 index 0000000..205f378 --- /dev/null +++ b/kb-deep-analyzer/deep_analyzer.py @@ -0,0 +1,511 @@ +#!/usr/bin/env python3 +"""Deep Analyzer - AI 深度内容分析工具 + +一次性调用 AI 生成完整深度分析报告。 + +Usage: + python deep_analyzer.py --metadata meta.json --content content.json --output analysis.md [--type video] + python deep_analyzer.py --help +""" + +import argparse +import json +import os +import sys +import re +from datetime import datetime +from pathlib import Path +from typing import Dict, Any, List +from dataclasses import dataclass, field + + +# ============== 数据模型 ============== + +@dataclass +class AnalysisResult: + """分析结果""" + summary: str = "" + main_topics: List[str] = field(default_factory=list) + key_insights: List[str] = field(default_factory=list) + recommended_tags: List[str] = field(default_factory=list) + full_analysis: str = "" + + +# ============== AI 客户端 ============== + +class SimpleAIClient: + """AI 客户端""" + + def __init__(self, api_key: str = None, provider: str = None, model: str = None, base_url: str = None): + self.api_key = api_key or os.environ.get("AI_API_KEY", "") + self.provider = provider or os.environ.get("AI_PROVIDER", "") + self.model = model or os.environ.get("AI_MODEL", "gpt-4") + self.base_url = base_url or os.environ.get("AI_BASE_URL", "") + self.max_retries = 3 + + def generate(self, prompt: str, max_tokens: int = 16000) -> str: + """生成文本""" + api_key = os.environ.get("AI_API_KEY", self.api_key) + provider = os.environ.get("AI_PROVIDER", self.provider) + model = os.environ.get("AI_MODEL", self.model) + base_url = os.environ.get("AI_BASE_URL", self.base_url) + + if not api_key: + raise ValueError("AI_API_KEY 未设置") + + for attempt in range(self.max_retries): + try: + import time + start_time = time.time() + print(f"[AI Client] 开始调用 AI...") + + if provider == "openai": + result = self._call_openai(prompt, max_tokens, api_key, model, base_url) + elif provider == "zhipu": + result = self._call_zhipu(prompt, max_tokens, api_key, model, base_url) + elif provider == "minimax": + result = self._call_minimax(prompt, max_tokens, api_key, model, base_url) + else: + raise ValueError(f"不支持的 AI 提供商: {provider}") + + elapsed = time.time() - start_time + print(f"[AI Client] AI 调用完成，耗时: {elapsed:.2f}秒") + return result + except Exception as e: + if attempt < self.max_retries - 1: + print(f"[AI Client] 第 {attempt + 1} 次调用失败，{self.max_retries - attempt - 1} 次重试剩余: {e}") + continue + else: + raise + + def _call_openai(self, prompt: str, max_tokens: int, api_key: str, model: str, base_url: str) -> str: + import requests + url = f"{base_url}/chat/completions" if base_url else "https://api.openai.com/v1/chat/completions" + headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"} + payload = {"model": model, "max_tokens": max_tokens, "messages": [{"role": "user", "content": prompt}]} + response = requests.post(url, headers=headers, json=payload, timeout=600) + response.raise_for_status() + return response.json()['choices'][0]['message']['content'] + + def _call_zhipu(self, prompt: str, max_tokens: int, api_key: str, model: str, base_url: str) -> str: + import requests + base_url = base_url or "https://open.bigmodel.cn/api/coding/paas/v4" + url = f"{base_url}/chat/completions" + headers = {"Authorization": f"Bearer {api_key}"} + payload = {"model": model, "messages": [{"role": "user", "content": prompt}], "max_tokens": max_tokens} + response = requests.post(url, headers=headers, json=payload, timeout=600) + response.raise_for_status() + data = response.json() + message = data.get('choices', [{}])[0].get('message', {}) + content = message.get('content', '') + reasoning = message.get('reasoning_content', '') + if not content and reasoning: + sentences = reasoning.strip().split('。') + useful = [s.strip() for s in sentences if s.strip() and len(s.strip()) > 10] + if useful: + return '。'.join(useful[-3:]) + '。' + return reasoning.strip()[:500] + return content + + def _call_minimax(self, prompt: str, max_tokens: int, api_key: str, model: str, base_url: str) -> str: + import requests + url = base_url or "https://api.minimaxi.com/anthropic/v1/messages" + headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"} + payload = {"model": model, "max_tokens": max_tokens, "messages": [{"role": "user", "content": prompt}]} + response = requests.post(url, headers=headers, json=payload, timeout=600) + response.raise_for_status() + data = response.json() + for item in data.get('content', []): + if item.get('type') == 'text': + return item.get('text', '') + return str(data) + + +# ============== 分析器 ============== + +class DeepAnalyzer: + """深度内容分析器""" + + def __init__(self, ai_client: SimpleAIClient = None): + self.ai_client = ai_client or SimpleAIClient() + + def analyze(self, metadata: Dict[str, Any], content: Dict[str, Any]) -> AnalysisResult: + """一次性调用 AI 生成完整分析报告""" + + # 标准化元数据 + metadata = self._normalize_metadata(metadata) + + title = metadata.get('title', '未知') + duration = metadata.get('duration', 0) + author = metadata.get('author', '') + pubtime = metadata.get('pubtime', '') + url = metadata.get('url', '') + bvid = metadata.get('bvid', '') + + # 获取内容 - 支持多种字段名 + text = content.get('text', '') or content.get('subtitle', '') or content.get('subtitles', '') or content.get('description', '') + + print(f"[DeepAnalyzer] 开始分析: {title}") + print(f"[DeepAnalyzer] 时长: {duration}秒, 内容长度: {len(text)} 字符") + + # 计算分片数（按10分钟分片） + num_chunks = max(1, (duration + 599) // 600) # 向上取整到10分钟 + print(f"[DeepAnalyzer] 将分 {num_chunks} 段分析") + + # 构建 prompt + prompt = self._build_prompt( + title=title, + duration=duration, + duration_str=self._format_duration(duration), + author=author, + pubtime=pubtime, + url=url, + bvid=bvid, + text=text, + num_chunks=num_chunks + ) + + # 调用 AI + try: + full_analysis = self.ai_client.generate(prompt, max_tokens=16000) + except Exception as e: + print(f"[DeepAnalyzer] AI 调用失败: {e}") + raise + + # 解析结果 + result = self._parse_analysis(full_analysis, text, duration) + + return result + + def _build_prompt(self, title: str, duration: int, duration_str: str, author: str, + pubtime: str, url: str, bvid: str, text: str, num_chunks: int) -> str: + """构建分析 prompt""" + + # 截取适当长度的文本（20-30K 字符） + max_chars = 30000 + if len(text) > max_chars: + text_sample = text[:max_chars] + "\n\n[...]" + else: + text_sample = text + + prompt = f"""你是一个专业的视频内容分析师。请根据以下信息生成深度分析报告： + +【视频信息】 +标题：{title} +作者：{author} +时长：{duration_str}（{duration}秒） +发布日期：{pubtime} +平台：bilibili +URL：{url} + +【内容】（完整字幕） +{text_sample} + +【输出要求】必须使用以下格式： + +## 标题 +[自己总结的简洁标题，禁止使用原标题] + +## 摘要 +[200-400字] + +## 主要主题 +[从内容中提取不超过10个主题，每个不超过10字] +- 主题1 +- 主题2 +... + +## 关键见解 +[若干条深刻见解] +- 见解1 +- 见解2 +... + +## 标签 +[从内容中提取3-5个精炼标签，每个不超过10字] +- 标签1 +- 标签2 +... + +## 时间轴 +### 第 1 部分 (00:00 - 10:00) +[详细分析，至少500字] + +### 第 2 部分 (10:00 - 20:00) +[详细分析，至少500字] + +...（以此类推） + +【重要】分析应足够详尽，读者阅读后可了解视频核心内容，无需再看原视频。""" + + return prompt + + def _parse_analysis(self, analysis_text: str, original_text: str, duration: int) -> AnalysisResult: + """解析 AI 返回的分析结果""" + result = AnalysisResult() + result.full_analysis = analysis_text + + # 提取各部分（使用正则） + lines = analysis_text.split('\n') + + # 简单解析：按 ## 标题分割 + current_section = "" + in_section = None + + for line in lines: + if line.startswith('##'): + # 保存上一个 section + if in_section: + self._store_section(result, in_section, current_section) + # 开始新 section + section_name = line.lstrip('#').strip() + in_section = section_name + current_section = "" + elif in_section: + current_section += line + "\n" + + # 存储最后一个 section + if in_section: + self._store_section(result, in_section, current_section) + + # 如果解析失败，使用原始文本 + if not result.summary: + result.summary = analysis_text[:500] + + return result + + def _store_section(self, result: AnalysisResult, section_name: str, content: str): + """存储解析到的 section""" + content = content.strip() + if not content: + return + + section_lower = section_name.lower() + + if '摘要' in section_lower: + result.summary = content[:500] + elif '主题' in section_lower: + # 提取主题 + topics = [] + for line in content.split('\n'): + line = line.strip().lstrip('-').strip() + if line and len(line) <= 15: + topics.append(line) + result.main_topics = topics[:10] + elif '见解' in section_lower or '观点' in section_lower: + # 提取见解 + insights = [] + for line in content.split('\n'): + line = line.strip().lstrip('-').strip() + if line and len(line) > 5: + insights.append(line) + result.key_insights = insights + elif '标签' in section_lower: + # 提取标签 + tags = [] + for line in content.split('\n'): + line = line.strip().lstrip('-').strip() + if line and len(line) <= 10: + tags.append(line) + result.recommended_tags = tags[:5] + + def _normalize_metadata(self, metadata: Dict) -> Dict: + """标准化元数据""" + if not metadata: + return {} + + # 如果已经扁平 + if 'title' in metadata: + duration = metadata.get('duration', 0) + if isinstance(duration, str) and ':' in duration: + parts = duration.split(':') + try: + metadata['duration'] = int(parts[0]) * 60 + int(parts[1]) + except: + pass + return metadata + + # 嵌套结构 + if 'metadata' in metadata: + meta = metadata['metadata'] + normalized = {} + for k, v in meta.items(): + normalized[k] = v + # 处理 duration + duration = normalized.get('duration', 0) + if isinstance(duration, str) and ':' in duration: + parts = duration.split(':') + try: + normalized['duration'] = int(parts[0]) * 60 + int(parts[1]) + except: + pass + return normalized + + return metadata + + def _format_duration(self, seconds: int) -> str: + """格式化时长""" + h = seconds // 3600 + m = (seconds % 3600) // 60 + s = seconds % 60 + if h > 0: + return f"{h}:{m:02d}:{s:02d}" + return f"{m}:{s:02d}" + + +# ============== 工具函数 ============== + +def load_json(file_path: str) -> Dict: + """加载 JSON 文件""" + if not file_path or not os.path.exists(file_path): + return {} + with open(file_path, 'r', encoding='utf-8') as f: + return json.load(f) + + +def generate_frontmatter(metadata: Dict, result: AnalysisResult) -> str: + """生成 Markdown frontmatter""" + # 提取标签 + tags = result.recommended_tags or [] + + # 格式化日期 + pubtime = metadata.get('pubtime', '') + if pubtime: + date_str = str(pubtime)[:10] + else: + date_str = datetime.now().strftime('%Y-%m-%d') + + fm = ["---", + f"title: \"{metadata.get('title', '未命名')}\"", + f"date: {date_str}", + f"duration: {metadata.get('duration_str', metadata.get('duration', 0))}", + f"author: {metadata.get('author', '未知')}", + f"bvid: {metadata.get('bvid', '')}", + f"platform: {metadata.get('platform', 'bilibili')}"] + + # 添加 URL + url = metadata.get('url', '') + if url: + fm.append(f"url: {url}") + + if tags: + fm.append("tags: [" + ", ".join(f'"{t}"' for t in tags) + "]") + + fm.append("---") + return '\n'.join(fm) + + +# ============== 主程序 ============== + +def main(): + parser = argparse.ArgumentParser(description="Deep Analyzer - AI 深度内容分析工具") + parser.add_argument("--metadata", "-m", required=True, help="元数据 JSON 文件路径") + parser.add_argument("--content", "-c", required=True, help="内容 JSON 文件路径") + parser.add_argument("--output", "-o", required=True, help="输出 Markdown 文件路径") + parser.add_argument("--type", "-t", default="video", choices=["video", "article"], help="内容类型") + parser.add_argument("--api-key", "-k", default=None, help="AI API Key") + parser.add_argument("--provider", "-p", default=None, choices=["openai", "zhipu", "minimax"], help="AI 提供商") + parser.add_argument("--model", default=None, help="AI 模型") + parser.add_argument("--base-url", "-u", default=None, help="API Base URL") + parser.add_argument("--no-frontmatter", action="store_true", help="不生成 frontmatter") + + args = parser.parse_args() + + # 加载数据 + print(f"[Main] 加载元数据: {args.metadata}") + raw_metadata = load_json(args.metadata) + + print(f"[Main] 加载内容: {args.content}") + content = load_json(args.content) + + # 标准化元数据 + metadata = {} + if 'title' in raw_metadata: + metadata = raw_metadata.copy() + # 处理 duration + duration = metadata.get('duration', 0) + if isinstance(duration, str) and ':' in duration: + parts = duration.split(':') + try: + metadata['duration'] = int(parts[0]) * 60 + int(parts[1]) + except: + pass + metadata['duration_str'] = format_duration(metadata.get('duration', 0)) + elif 'metadata' in raw_metadata: + meta = raw_metadata['metadata'] + metadata = meta.copy() + duration = metadata.get('duration', 0) + if isinstance(duration, str) and ':' in duration: + parts = duration.split(':') + try: + metadata['duration'] = int(parts[0]) * 60 + int(parts[1]) + except: + pass + metadata['duration_str'] = format_duration(metadata.get('duration', 0)) + + # 初始化 + ai_client = SimpleAIClient( + api_key=args.api_key or os.environ.get("AI_API_KEY", ""), + provider=args.provider or os.environ.get("AI_PROVIDER", ""), + model=args.model or os.environ.get("AI_MODEL", "gpt-4"), + base_url=args.base_url or os.environ.get("AI_BASE_URL", "") + ) + analyzer = DeepAnalyzer(ai_client) + + # 执行分析 + print(f"[Main] 开始分析...") + result = analyzer.analyze(metadata, content) + + # 使用 AI 生成的原始内容（保留 Markdown 格式） + full_analysis = result.full_analysis + + # 删除内容中的"标签" section（只保留 frontmatter 中的 tags） + # 匹配 ## 标签 或 标签（无##）到下一个 ## 或文件结尾之间的内容 + full_analysis = re.sub(r'(## ?)?标签\n[\s\S]*?(?=\n## ?|\n时间轴|---|\Z)', '', full_analysis) + # 清理多余的空行 + full_analysis = re.sub(r'\n{3,}', '\n\n', full_analysis) + + # 写入输出 + os.makedirs(os.path.dirname(os.path.abspath(args.output)), exist_ok=True) + + with open(args.output, 'w', encoding='utf-8') as f: + # 添加 frontmatter + if not args.no_frontmatter: + fm = generate_frontmatter(metadata, result) + f.write(fm + "\n\n") + + # 写入分析内容 + f.write(full_analysis) + + # 输出结果 + output = { + "success": True, + "filename": Path(args.output).name, + "filepath": str(Path(args.output).resolve()), + "message": "深度分析完成", + "stats": { + "summary_length": len(result.summary) if result.summary else 0, + "topics_count": len(result.main_topics), + "insights_count": len(result.key_insights), + "tags_count": len(result.recommended_tags) + } + } + print(json.dumps(output, ensure_ascii=False, indent=2)) + + +def format_duration(seconds: int) -> str: + """格式化时长""" + h = seconds // 3600 + m = (seconds % 3600) // 60 + s = seconds % 60 + if h > 0: + return f"{h}:{m:02d}:{s:02d}" + return f"{m}:{s:02d}" + + +if __name__ == "__main__": + try: + main() + except Exception as e: + print(json.dumps({"success": False, "error": str(e)}, ensure_ascii=False, indent=2)) + sys.exit(1) diff --git a/kb-deep-analyzer/deep_analyzer.py.bak b/kb-deep-analyzer/deep_analyzer.py.bak new file mode 100644 index 0000000..59c62c1 --- /dev/null +++ b/kb-deep-analyzer/deep_analyzer.py.bak @@ -0,0 +1,1727 @@ +#!/usr/bin/env python3 +"""Deep Analyzer - AI 深度内容分析工具 + +支持根据内容时长选择不同分析策略： +- 短视频 (<10分钟): 轻量分析 +- 长视频 (>=10分钟): 详细时间轴分析 + +Usage: + python deep_analyzer.py --metadata meta.json --content content.json --output analysis.md [--type video] + python deep_analyzer.py --help +""" + +import argparse +import json +import os +import sys +import re +from datetime import datetime +from pathlib import Path +from typing import Dict, Any, List, Optional, Tuple +from dataclasses import dataclass, field, asdict + + +# ============== 数据模型 ============== + +@dataclass +class TimelineEntry: + """时间轴条目""" + index: int = 0 + start_time: str = "" + end_time: str = "" + title: str = "" + summary: str = "" + + +@dataclass +class AnalysisResult: + """分析结果""" + summary: str = "" + main_topics: List[str] = field(default_factory=list) + key_insights: List[str] = field(default_factory=list) + action_items: List[str] = field(default_factory=list) + recommended_tags: List[str] = field(default_factory=list) + full_analysis: str = "" + timeline: List[Dict[str, Any]] = field(default_factory=list) + + +# ============== AI 客户端 ============== + +# ============== 流式写入器 ============== + +import threading + + +class StreamingWriter: + """ + 流式写入器 - 支持多线程并发写入到文档不同位置 + + 使用方法: + 1. 初始化: writer = StreamingWriter(output_path, num_chunks) + 2. 预先创建带占位符的文档结构 + 3. 每批完成后调用 writer.write_batch(batch_results) + 4. 完成后调用 writer.mark_complete() 清理占位符 + """ + + def __init__(self, output_path: str, num_chunks: int = 0, batch_size: int = 3): + self.output_path = Path(output_path) + self.num_chunks = num_chunks + self.batch_size = batch_size + self.lock = threading.Lock() + self.written = {} # 记录已写入的位置 + self.batch_num = 0 + + def initialize_document(self, metadata: Dict, num_chunks: int) -> str: + """ + 初始化文档结构，返回带占位符的内容 + + 文档结构: + --- + title: "xxx" + ... + --- + + # 标题 + + ## 摘要 + + ## 主要主题 + + ## 关键见解 + + ## 建议行动 + + ## 时间轴 + ### 第 N 部分 (00:00 - 00:00) + [ANALYZING...] + """ + self.num_chunks = num_chunks + + # 生成时间轴占位符 + timeline_placeholders = "" + for i in range(num_chunks): + timeline_placeholders += f"""### 第 {i + 1} 部分 (待分析) +[ANALYZING_BATCH_{i // self.batch_size + 1}] + +""" + + content = f"""--- +title: "{metadata.get('title', '未命名')}" +date: {datetime.now().strftime('%Y-%m-%d')} +duration: {format_duration(metadata.get('duration', 0))} +author: {metadata.get('author', '未知')} +analyze_time: {datetime.now().strftime('%Y-%m-%d %H:%M')} +bvid: {metadata.get('bvid', '')} +platform: {metadata.get('platform', 'bilibili')} +--- + +# {metadata.get('title', '未命名')} + +## 摘要 +[WAITING_FOR_ANALYSIS...] + +## 主要主题 +[WAITING_FOR_ANALYSIS...] + +## 关键见解 +[WAITING_FOR_ANALYSIS...] + +## 建议行动 +[WAITING_FOR_ANALYSIS...] + +## 时间轴 +{timeline_placeholders} + +--- +*分析时间: {datetime.now().strftime('%Y-%m-%d %H:%M')}* +""" + + # 写入初始化内容 + self.output_path.parent.mkdir(parents=True, exist_ok=True) + with open(self.output_path, 'w', encoding='utf-8') as f: + f.write(content) + + print(f"[StreamingWriter] 初始化文档: {self.output_path}") + return content + + def write_batch(self, batch_results: List[Dict], num_batches: int) -> None: + """ + 写入一批结果 + + Args: + batch_results: 当前批的结果列表 + num_batches: 总批次数 + """ + self.batch_num += 1 + + with self.lock: + # 读取当前内容 + if not self.output_path.exists(): + print(f"[StreamingWriter] 警告: 文件不存在 {self.output_path}") + return + + content = self.output_path.read_text(encoding='utf-8') + + for result in batch_results: + idx = result['index'] + start_time = result['start_time'] + end_time = result['end_time'] + summary = result['summary'] + + # 查找并替换占位符 + old_placeholder = f"### 第 {idx + 1} 部分 ({start_time} - {end_time})\n[ANALYZING_BATCH_{self.batch_num}]" + new_content = f"""### 第 {idx + 1} 部分 ({start_time} - {end_time}) +{summary}""" + + content = content.replace(old_placeholder, new_content, 1) + self.written[idx] = True + + print(f"[StreamingWriter] 写入段 {idx + 1}/{self.num_chunks}") + + # 如果这是最后一批，更新其他状态 + if self.batch_num >= num_batches: + # 更新摘要等 + pass + + # 写回文件 + self.output_path.write_text(content, encoding='utf-8') + print(f"[StreamingWriter] 批次 {self.batch_num}/{num_batches} 完成") + + def update_summary(self, summary_text: str, topics: List[str], insights: List[str]) -> None: + """更新摘要等全局内容""" + with self.lock: + if not self.output_path.exists(): + return + + content = self.output_path.read_text(encoding='utf-8') + + # 更新摘要 + if "[WAITING_FOR_ANALYSIS...]" in content: + content = content.replace("## 摘要\n[WAITING_FOR_ANALYSIS...]", f"## 摘要\n{summary_text}") + + # 更新主题 + topics_text = "\n".join(f"- {t}" for t in topics) + if "## 主要主题\n[WAITING_FOR_ANALYSIS...]" in content: + content = content.replace("## 主要主题\n[WAITING_FOR_ANALYSIS...]", f"## 主要主题\n{topics_text}") + + # 更新见解 + insights_text = "\n".join(f"- {i}" for i in insights) + if "## 关键见解\n[WAITING_FOR_ANALYSIS...]" in content: + content = content.replace("## 关键见解\n[WAITING_FOR_ANALYSIS...]", f"## 关键见解\n{insights_text}") + + self.output_path.write_text(content, encoding='utf-8') + print(f"[StreamingWriter] 更新摘要和主题") + + def cleanup_placeholder(self, placeholder: str) -> None: + """清理单个占位符""" + with self.lock: + if not self.output_path.exists(): + return + + content = self.output_path.read_text(encoding='utf-8') + content = content.replace(placeholder, "") + self.output_path.write_text(content, encoding='utf-8') + + +class SimpleAIClient: + """简化的 AI 客户端 - 支持多提供商 fallback""" + + # 时长阈值（秒） + SHORT_VIDEO_THRESHOLD = 600 # 10分钟 + LONG_VIDEO_THRESHOLD = 1800 # 30分钟 + + def __init__(self, api_key: str = None, provider: str = None, model: str = None, base_url: str = None): + self.api_key = api_key or os.environ.get("AI_API_KEY", "") + self.provider = provider or os.environ.get("AI_PROVIDER", "") + self.model = model or os.environ.get("AI_MODEL", "gpt-4") + self.base_url = base_url or os.environ.get("AI_BASE_URL", "") + self.max_retries = 3 # 最大重试次数 + self.max_concurrent = 3 # 最大并发数 + + def generate(self, prompt: str, max_tokens: int = 1000, task_info: str = None) -> str: + """生成文本，支持重试""" + # 每次调用时重新读取环境变量，解决 exec 传递问题 + api_key = os.environ.get("AI_API_KEY", self.api_key) + provider = os.environ.get("AI_PROVIDER", self.provider) + model = os.environ.get("AI_MODEL", self.model) + base_url = os.environ.get("AI_BASE_URL", self.base_url) + + if not api_key: + raise ValueError("AI_API_KEY 未设置，请配置环境变量") + + task_desc = f"[{task_info}]" if task_info else "" + + last_error = None + for attempt in range(self.max_retries): + try: + import time + start_time = time.time() + print(f"[AI Client] {task_desc} 开始调用 AI...") + + if provider == "openai": + result = self._call_openai(prompt, max_tokens, api_key, model, base_url) + elif provider == "zhipu": + result = self._call_zhipu(prompt, max_tokens, api_key, model, base_url) + elif provider == "minimax": + result = self._call_minimax(prompt, max_tokens, api_key, model, base_url) + else: + raise ValueError(f"不支持的 AI 提供商: {provider}") + + elapsed = time.time() - start_time + print(f"[AI Client] {task_desc} AI 调用完成，耗时: {elapsed:.2f}秒") + return result + except Exception as e: + elapsed = time.time() - start_time if 'start_time' in dir() else 0 + last_error = e + if attempt < self.max_retries - 1: + print(f"[AI Client] {task_desc} 第 {attempt + 1} 次调用失败 ({elapsed:.2f}秒)，{self.max_retries - attempt - 1} 次重试剩余: {e}") + continue + else: + print(f"[AI Client] {task_desc} 调用失败，已重试 {self.max_retries} 次: {e}") + raise + + def generate_json(self, prompt: str) -> Dict[str, Any]: + """生成 JSON 格式响应""" + response = self.generate(prompt, max_tokens=4000) + try: + return json.loads(response) + except json.JSONDecodeError: + # 尝试从文本中提取 JSON + return self._parse_json_from_text(response) + + def _call_openai(self, prompt: str, max_tokens: int, api_key: str = None, model: str = None, base_url: str = None) -> str: + """调用 OpenAI API""" + import requests + url = f"{self.base_url}/chat/completions" if self.base_url else "https://api.openai.com/v1/chat/completions" + + headers = { + "Authorization": f"Bearer {self.api_key}", + "Content-Type": "application/json" + } + + payload = { + "model": self.model, + "max_tokens": max_tokens, + "messages": [{"role": "user", "content": prompt}] + } + + response = requests.post(url, headers=headers, json=payload, timeout=600) + response.raise_for_status() + response.raise_for_status() + return response.json()['choices'][0]['message']['content'] + + def _call_zhipu(self, prompt: str, max_tokens: int, api_key: str = None, model: str = None, base_url: str = None) -> str: + """调用智谱 AI API - 返回 reasoning_content""" + import requests + base_url = self.base_url or "https://open.bigmodel.cn/api/coding/paas/v4" + url = f"{base_url}/chat/completions" + + headers = {"Authorization": f"Bearer {self.api_key}"} + payload = { + "model": self.model, + "messages": [{"role": "user", "content": prompt}], + "max_tokens": max_tokens + } + + response = requests.post(url, headers=headers, json=payload, timeout=600) + response.raise_for_status() + response.raise_for_status() + data = response.json() + + message = data.get('choices', [{}])[0].get('message', {}) + content = message.get('content', '') + reasoning = message.get('reasoning_content', '') + + # 如果 content 为空但有 reasoning_content，从 reasoning 中提取关键句 + if not content and reasoning: + # 从 reasoning_content 中提取最后几句话作为答案 + sentences = reasoning.strip().split('。') + # 取最后几个完整句子 + useful = [s.strip() for s in sentences if s.strip() and len(s.strip()) > 10] + if useful: + return '。'.join(useful[-3:]) + '。' + return reasoning.strip()[:500] + return content + + def _parse_json_from_text(self, text: str) -> Dict[str, Any]: + """从文本中解析 JSON，改进版本，支持更多格式""" + # 尝试直接解析 + try: + return json.loads(text) + except json.JSONDecodeError: + pass + + # 尝试提取 JSON 块 + json_match = re.search(r'```(?:json)?\s*([\s\S]*?)\s*```', text) + if json_match: + try: + return json.loads(json_match.group(1)) + except: + pass + + # 尝试匹配 { ... } + json_match = re.search(r'(\{[\s\S]*\})', text) + if json_match: + try: + return json.loads(json_match.group(1)) + except: + pass + + return {'raw_response': text} + + def _call_minimax(self, prompt: str, max_tokens: int, api_key: str = None, model: str = None, base_url: str = None) -> str: + """调用 MiniMax API""" + import requests + url = self.base_url or "https://api.minimaxi.com/anthropic/v1/messages" + + headers = { + "Authorization": f"Bearer {self.api_key}", + "Content-Type": "application/json" + } + + payload = { + "model": self.model, + "max_tokens": max_tokens, + "messages": [{"role": "user", "content": prompt}] + } + + response = requests.post(url, headers=headers, json=payload, timeout=600) + response.raise_for_status() + response.raise_for_status() + data = response.json() + for item in data.get('content', []): + if item.get('type') == 'text': + return item.get('text', '') + return str(data) + + + +# ============== 深度分析器 ============== + +class DeepAnalyzer: + """深度内容分析器""" + + SHORT_VIDEO_THRESHOLD = 600 # 10分钟 + LONG_VIDEO_THRESHOLD = 1800 # 30分钟 + + def __init__(self, ai_client: SimpleAIClient = None): + self.ai_client = ai_client or SimpleAIClient() + + def analyze( + self, + metadata: Dict[str, Any], + content: Dict[str, Any], + content_type: str = "video", + on_batch_complete: callable = None, + batch_size: int = 3 + ) -> AnalysisResult: + """ + 分析内容 + + Args: + metadata: 元数据字典 + content: 内容数据字典（包含 subtitle, description 等） + content_type: 内容类型 + on_batch_complete: 每批完成时的回调函数 (batch_results) => None + batch_size: 每批处理数（默认3） + + Returns: + AnalysisResult 分析结果 + """ + # 先标准化元数据 + metadata = normalize_metadata(metadata) + + title = metadata.get('title', '未知') + duration = metadata.get('duration', 0) + + # 支持多种内容格式 + text = content.get('text', '') or content.get('subtitle', '') or content.get('description', '') + segments = content.get('segments', []) + + has_content = bool(text and text.strip()) + has_segments = bool(segments) + + print(f"[DeepAnalyzer] 开始分析: {title}") + print(f"[DeepAnalyzer] 类型: {content_type}, 时长: {duration}秒") + print(f"[DeepAnalyzer] 文本存在: {has_content}, 分段数: {len(segments)}") + print(f"[DeepAnalyzer] 文本长度: {len(text) if text else 0} 字符") + + CHUNK_THRESHOLD = 3000 + use_chunking = has_content and len(text) > CHUNK_THRESHOLD + + if has_content or has_segments: + if use_chunking: + print(f"[DeepAnalyzer] 文本超过 {CHUNK_THRESHOLD} 字，使用批处理分块分析") + result = self._analyze_chunks_concurrent( + title, text, duration, segments, metadata, + batch_size=batch_size, + on_segment_complete=on_batch_complete + ) + elif duration < self.SHORT_VIDEO_THRESHOLD: + print(f"[DeepAnalyzer] 使用轻量分析策略 (时长 < 10分钟)") + result = self._analyze_short_with_subtitle(title, text, duration, segments) + else: + print(f"[DeepAnalyzer] 使用详细时间轴分析策略 (时长 >= 10分钟)") + result = self._analyze_long_with_subtitle(title, text, duration, segments, content_type, metadata) + else: + print(f"[DeepAnalyzer] 降级处理（无内容）") + result = self._analyze_fallback(title, text, metadata) + + return result + + def _analyze_short_with_subtitle(self, title: str, text: str, duration: int, segments: list = None) -> AnalysisResult: + """有内容的短视频轻量分析""" + result = AnalysisResult() + text_sample = self._get_text_sample(text, max_chars=5000) + + analysis = self._analyze_with_ai_short_text(text_sample, title, duration) + result.summary = analysis.get('summary', title) + result.main_topics = analysis.get('topics', []) + result.key_insights = analysis.get('insights', []) + result.action_items = analysis.get('actions', []) + result.timeline = self._generate_timeline_from_segments(title, duration, segments) + + return result + + def _analyze_long_with_subtitle(self, title: str, text: str, duration: int, + segments: list = None, content_type: str = None, + metadata: Dict = None) -> AnalysisResult: + """有内容的长视频详细分析""" + result = AnalysisResult() + + if duration >= self.SHORT_VIDEO_THRESHOLD and content_type == "video": + # 10分钟以上使用分段分析 + result = self._analyze_in_chunks(title, text, duration, metadata) + else: + # 直接分析 + text_sample = self._get_text_sample(text, max_chars=5000) + analysis = self._analyze_with_ai_short_text(text_sample, title, duration) + result.summary = analysis.get('summary', title) + result.main_topics = analysis.get('topics', []) + result.key_insights = analysis.get('insights', []) + result.action_items = analysis.get('actions', []) + result.full_analysis = analysis.get('full_analysis', '') + result.timeline = self._generate_timeline_from_segments(title, duration, segments) + + return result + + def _analyze_in_chunks(self, title: str, subtitle: str, duration: int, metadata: Dict = None) -> AnalysisResult: + """分段分析长视频 - 动态分段策略""" + result = AnalysisResult() + + # 常量配置 + CHUNK_MAX_CHARS = 3000 # 每个chunk最大字符数 + MIN_CHUNKS = 3 # 最少分段数 + MAX_API_CHUNKS = 20 # 最多API调用次数 + + total_chars = len(subtitle) + + # 1. 动态计算分段数 + # 计算需要多少个chunk（每个不超过3000字） + min_required = total_chars // CHUNK_MAX_CHARS + 1 + # 根据时长限制最大分段 + if duration < 1800: # <30分钟: 最多6段 + max_chunks = 6 + elif duration < 7200: # <2小时: 最多12段 + max_chunks = 12 + else: # >2小时: 最多20段 + max_chunks = 20 + + num_segments = min(max(min_required, MIN_CHUNKS), MAX_API_CHUNKS) + + print(f"[DeepAnalyzer] 字幕{total_chars}字符，分{num_segments}段分析") + + # 2. 按字符数分段（保持语义完整） + chunk_size = total_chars // num_segments + chunks = [] + chunk_boundaries = [] # 记录每段的字符边界 + + for i in range(num_segments): + start = i * chunk_size + if i == num_segments - 1: + # 最后一段取到结尾 + end = total_chars + chunk_text = subtitle[start:] + else: + # 在自然断点处分割 + end = self._find_breakpoint(subtitle, start, start + chunk_size) + chunk_text = subtitle[start:end] + chunks.append(chunk_text) + chunk_boundaries.append((start, end)) + + print(f"[DeepAnalyzer] 各段字符: {[len(c) for c in chunks]}") + + # 3. 用字符比例估算时间 + char_per_second = total_chars / duration if duration > 0 else 1 + + # 合并结果 + chunk_summaries = [] + + for i, chunk_text in enumerate(chunks): + start_char, end_char = chunk_boundaries[i] + # 用字符位置估算时间 + start_sec = max(0, int(start_char / char_per_second)) + end_sec = min(duration, int(end_char / char_per_second)) + start_time = self._format_time(start_sec) + end_time = self._format_time(end_sec) + + # AI 分析每段（传入元数据以添加概述） + chunk_summary = self._analyze_chunk(chunk_text, i + 1, metadata) + chunk_summaries.append({ + 'index': i, + 'start_time': start_time, + 'end_time': end_time, + 'start_sec': start_sec, + 'end_sec': end_sec, + 'summary': chunk_summary + }) + + # 合并结果 + result = self._merge_summaries(chunk_summaries, title) + result.timeline = self._build_timeline_from_chunks(chunk_summaries) + + return result + + def _analyze_in_chunks_with_segments(self, title: str, text: str, duration: int, segments: list = None, metadata: Dict = None) -> AnalysisResult: + """ + 使用实际字幕时间戳进行分块分析 + + 当有 SRT 格式的 segments 时，使用实际时间戳来分块 + 否则退化为字符位置估算 + """ + result = AnalysisResult() + + CHUNK_MAX_CHARS = 3000 + total_chars = len(text) + + # 检查是否有有效的 SRT segments + has_valid_segments = segments and len(segments) > 0 and all('start' in seg and 'text' in seg for seg in segments) + + if has_valid_segments: + print(f"[DeepAnalyzer] 使用 SRT 时间戳进行分块") + # 按时间戳分块 + chunks = [] + chunk_times = [] + current_chunk = "" + current_start = segments[0]['start'] + current_end = "" + + for seg in segments: + seg_text = f"[{seg['start']}] {seg['text']}\n" + + if len(current_chunk) + len(seg_text) > CHUNK_MAX_CHARS and current_chunk: + # 保存当前块 + chunks.append(current_chunk.strip()) + chunk_times.append((current_start, current_end or seg['start'])) + # 开始新块 + current_chunk = seg_text + current_start = seg['start'] + else: + current_chunk += seg_text + current_end = seg['end'] + + # 保存最后一块 + if current_chunk: + chunks.append(current_chunk.strip()) + chunk_times.append((current_start, current_end)) + + print(f"[DeepAnalyzer] SRT分块: {len(chunks)} 段") + else: + # 退化为字符位置估算 + print(f"[DeepAnalyzer] 无有效时间戳，使用字符位置分块") + min_required = total_chars // CHUNK_MAX_CHARS + 1 + num_segments = min(max(min_required, 3), 20) + + chunk_size = total_chars // num_segments + chunks = [] + chunk_times = [] + + for i in range(num_segments): + start = i * chunk_size + if i == num_segments - 1: + end = total_chars + else: + end = self._find_breakpoint(text, start, start + chunk_size) + + chunks.append(text[start:end]) + # 估算时间 + char_per_second = total_chars / duration if duration > 0 else 1 + start_sec = int(start / char_per_second) + end_sec = int(end / char_per_second) + chunk_times.append((self._format_time(start_sec), self._format_time(end_sec))) + + print(f"[DeepAnalyzer] 字符分块: {len(chunks)} 段") + + print(f"[DeepAnalyzer] 各段字符: {[len(c) for c in chunks]}") + + # 分析每个块 + chunk_summaries = [] + for i, chunk_text in enumerate(chunks): + start_time, end_time = chunk_times[i] + + # AI 分析每段（传入元数据以添加概述） + chunk_summary = self._analyze_chunk(chunk_text, i + 1, metadata) + chunk_summaries.append({ + 'index': i, + 'start_time': start_time, + 'end_time': end_time, + 'summary': chunk_summary + }) + + # 合并结果 + result = self._merge_summaries(chunk_summaries, title) + result.timeline = self._build_timeline_from_chunks(chunk_summaries) + + return result + + def _analyze_chunks_concurrent( + self, + title: str, + text: str, + duration: int, + segments: list = None, + metadata: Dict = None, + max_concurrent: int = 3, + batch_size: int = 3, + on_segment_complete: callable = None + ) -> AnalysisResult: + """ + 批处理分块分析（流式输出，避免爆上下文） + + Args: + title: 视频标题 + text: 完整文本 + duration: 时长（秒） + segments: SRT segments + metadata: 元数据 + batch_size: 每批处理数（默认3） + on_batch_complete: 每批完成时的回调 (batch_results) => None + + Returns: + AnalysisResult 分析结果 + """ + import concurrent.futures + + # 确保环境变量在子线程中可用 + _worker_env = { + 'AI_API_KEY': os.environ.get('AI_API_KEY', ''), + 'AI_PROVIDER': os.environ.get('AI_PROVIDER', ''), + 'AI_MODEL': os.environ.get('AI_MODEL', ''), + 'AI_BASE_URL': os.environ.get('AI_BASE_URL', ''), + } + + def init_worker(): + """初始化 worker 线程的环境变量""" + os.environ.update(_worker_env) + + result = AnalysisResult() + CHUNK_MAX_CHARS = 3000 + total_chars = len(text) + num_chunks = 0 + + # 生成分块 + has_valid_segments = segments and len(segments) > 0 and all('start' in seg and 'text' in seg for seg in segments) + + if has_valid_segments: + print(f"[DeepAnalyzer] 使用 SRT 时间戳进行分块") + chunks = [] + chunk_times = [] + current_chunk = "" + current_start = segments[0]['start'] + current_end = "" + + for seg in segments: + seg_text = f"[{seg['start']}] {seg['text']}\n" + if len(current_chunk) + len(seg_text) > CHUNK_MAX_CHARS and current_chunk: + chunks.append(current_chunk.strip()) + chunk_times.append((current_start, current_end or seg['start'])) + current_chunk = seg_text + current_start = seg['start'] + else: + current_chunk += seg_text + current_end = seg['end'] + + if current_chunk: + chunks.append(current_chunk.strip()) + chunk_times.append((current_start, current_end)) + + num_chunks = len(chunks) + else: + print(f"[DeepAnalyzer] 使用字符位置分块") + min_required = total_chars // CHUNK_MAX_CHARS + 1 + num_chunks = min(max(min_required, 3), 20) + chunk_size = total_chars // num_chunks + chunks = [] + chunk_times = [] + + for i in range(num_chunks): + start = i * chunk_size + if i == num_chunks - 1: + end = total_chars + else: + end = self._find_breakpoint(text, start, start + chunk_size) + chunks.append(text[start:end]) + char_per_second = total_chars / duration if duration > 0 else 1 + start_sec = int(start / char_per_second) + end_sec = int(end / char_per_second) + chunk_times.append((self._format_time(start_sec), self._format_time(end_sec))) + + print(f"[DeepAnalyzer] 分块: {num_chunks} 段，批次大小: {batch_size}") + + import time + total_start_time = time.time() + + # 批处理执行 + batch_results = {} # 存储各批结果 + all_summaries = [] + + for batch_idx in range(0, num_chunks, batch_size): + batch_num = batch_idx // batch_size + 1 + total_batches = (num_chunks + batch_size - 1) // batch_size + batch_end = min(batch_idx + batch_size, num_chunks) + batch_chunks = chunks[batch_idx:batch_end] + batch_times = chunk_times[batch_idx:batch_end] + + batch_start_time = time.time() + print(f"[DeepAnalyzer] === 批次 {batch_num}/{total_batches} 开始 ===") + print(f"[DeepAnalyzer] 段 {batch_idx+1}-{batch_end}，预计 {len(batch_chunks)} 个并发调用") + + # 并发执行当前批次 + batch_tasks = [(i, batch_chunks[j], batch_times[j][0], batch_times[j][1]) + for j, i in enumerate(range(batch_idx, batch_end))] + + with concurrent.futures.ThreadPoolExecutor(max_workers=batch_size, initializer=init_worker) as executor: + futures = {executor.submit(self._analyze_chunk, task[1], task[0] + 1, metadata): task[0] + for task in batch_tasks} + + completed_in_batch = 0 + for future in concurrent.futures.as_completed(futures): + idx = futures[future] + completed_in_batch += 1 + try: + summary = future.result() + batch_results[idx] = { + 'index': idx, + 'start_time': chunk_times[idx][0], + 'end_time': chunk_times[idx][1], + 'summary': summary + } + elapsed = time.time() - batch_start_time + print(f"[DeepAnalyzer] 段 {idx + 1}/{num_chunks} 完成 ({completed_in_batch}/{len(batch_chunks)}), 批次耗时: {elapsed:.2f}秒") + except Exception as e: + print(f"[DeepAnalyzer] 段 {idx + 1} 失败: {e}") + batch_results[idx] = { + 'index': idx, + 'start_time': chunk_times[idx][0], + 'end_time': chunk_times[idx][1], + 'summary': f"分析失败: {str(e)}" + } + + # 回调通知当前批次完成 + batch_summaries = [batch_results[i] for i in range(batch_idx, batch_end) if i in batch_results] + if on_segment_complete: + on_segment_complete(batch_summaries) + + all_summaries.extend(batch_summaries) + + batch_elapsed = time.time() - batch_start_time + print(f"[DeepAnalyzer] === 批次 {batch_num}/{total_batches} 完成，耗时: {batch_elapsed:.2f}秒 ===") + + total_elapsed = time.time() - total_start_time + print(f"[DeepAnalyzer] 所有分块分析完成，总耗时: {total_elapsed:.2f}秒") + + # 按顺序整理结果 + all_summaries = [all_summaries[i] for i in range(len(all_summaries))] + + # 合并结果 + print(f"[DeepAnalyzer] 开始合并各段摘要...") + merge_start = time.time() + result = self._merge_summaries(all_summaries, title) + merge_elapsed = time.time() - merge_start + print(f"[DeepAnalyzer] 摘要合并完成，耗时: {merge_elapsed:.2f}秒") + + result.timeline = self._build_timeline_from_chunks(all_summaries) + + return result + + def _find_breakpoint(self, text: str, start: int, preferred_end: int) -> int: + """ + 在自然断点处分割文本 + + 优先级： + 1. 双换行（段落分隔） + 2. 句号+换行（句末） + 3. 句号（句末） + 4. 换行（行末） + 5. 回到preferred_end + + Args: + text: 完整文本 + start: 起始位置 + preferred_end: 理想结束位置 + + Returns: + 实际结束位置 + """ + if not text or start >= len(text): + return start + + # 搜索范围：理想位置前后各500字符 + search_start = max(start, preferred_end - 500) + search_end = min(len(text), preferred_end + 500) + + # 优先级1: 双换行 + double_newline = text.rfind('\n\n', search_start, search_end) + if double_newline != -1: + return double_newline + + # 优先级2: 句号+换行 + period_newline = text.rfind('。\n', search_start, search_end) + if period_newline != -1: + return period_newline + 1 # 包含句号 + + # 优先级3: 句号（中文或英文） + last_period = max( + text.rfind('。', search_start, search_end), + text.rfind('.', search_start, search_end) + ) + if last_period != -1: + return last_period + 1 # 包含句号 + + # 优先级4: 换行 + last_newline = text.rfind('\n', search_start, search_end) + if last_newline != -1: + return last_newline + + # 没找到自然断点，返回理想位置 + return preferred_end + + def _analyze_chunk(self, chunk_text: str, chunk_index: int, metadata: Dict = None) -> str: + """分析单个分片""" + text_sample = self._get_text_sample(chunk_text, max_chars=3000) + + # 构建概述 + overview = "" + if metadata: + title = metadata.get('title', '') + description = metadata.get('description', '') + source = metadata.get('source', '') + + overview_parts = [] + if title: + overview_parts.append(f"视频标题：{title}") + if description: + overview_parts.append(f"视频描述：{description}") + if source: + overview_parts.append(f"来源：{source}") + + if overview_parts: + overview = "【概述】\n" + "\n".join(overview_parts) + "\n\n" + + prompt = f"""请对以下视频片段进行详细分析（限制在800字以内）： + +{overview}--- 片段内容 --- +{text_sample} + +请用中文详细回答，包括核心主题、关键要点和重要细节。""" + + try: + import time + start_time = time.time() + print(f"[DeepAnalyzer] 开始分析分片 {chunk_index}...") + result = self.ai_client.generate(prompt, max_tokens=2000, task_info=f"分片 {chunk_index}") + elapsed = time.time() - start_time + print(f"[DeepAnalyzer] 分片 {chunk_index} 分析完成，耗时: {elapsed:.2f}秒") + return result + except Exception as e: + print(f"[DeepAnalyzer] 分片 {chunk_index} 分析失败: {e}") + return f"第{chunk_index}段内容分析" + + def _merge_summaries(self, chunk_summaries: List[Dict], title: str) -> AnalysisResult: + """合并分段摘要""" + summaries_text = "\n\n".join([ + f"=== 第{s['index']+1}段 ({s['start_time']}-{s['end_time']}) ===\n{s['summary']}" + for s in chunk_summaries + ]) + + # 使用纯文本提示，不再要求 JSON 格式 + prompt = f"""基于以下视频各段分析，生成完整详细的分析报告： + +标题：{title} + +各段内容： +{summaries_text} + +请用中文详细回复，包含： +1. 整体摘要（300字以内） +2. 5个核心主题 +3. 4个关键见解 +4. 3条建议 +5. 详细分析（1500字以内）""" + + try: + # 使用纯文本生成而非 JSON + full_response = self.ai_client.generate(prompt, max_tokens=4000) + + # 解析响应 + result = AnalysisResult() + result.summary = self._extract_summary(full_response) + result.main_topics = self._extract_topics(full_response) + result.key_insights = self._extract_insights(full_response) + result.action_items = self._extract_actions(full_response) + result.full_analysis = full_response + return result + except Exception as e: + print(f"[DeepAnalyzer] 合并摘要失败: {e}") + return AnalysisResult( + summary=f"共{len(chunk_summaries)}段分析完成", + main_topics=[f"主题{i+1}" for i in range(min(4, len(chunk_summaries)))], + key_insights=["综合各段分析得出"], + full_analysis=summaries_text[:500] + ) + + def _extract_summary(self, text: str) -> str: + """从 AI 响应中提取摘要""" + lines = text.split('\n') + summary_lines = [] + capture = False + for line in lines: + if '摘要' in line or '总结' in line: + capture = True + if capture and line.strip(): + summary_lines.append(line.strip()) + if len(summary_lines) >= 3: + break + return ' '.join(summary_lines[:3])[:300] if summary_lines else text[:200] + + def _extract_topics(self, text: str) -> List[str]: + """从 AI 响应中提取主题""" + topics = [] + lines = text.split('\n') + for line in lines: + # 匹配常见主题格式 + if any(m in line for m in ['主题', '核心', '要点', '1.', '2.', '3.', '4.', '5.']): + # 清理并提取 + cleaned = line.strip().lstrip('0123456789.、 ').strip() + if cleaned and len(cleaned) > 2: + topics.append(cleaned) + if len(topics) >= 5: + break + return topics[:5] if topics else [f"主题{i+1}" for i in range(5)] + + def _extract_insights(self, text: str) -> List[str]: + """从 AI 响应中提取见解""" + insights = [] + lines = text.split('\n') + for line in lines: + if any(m in line for m in ['见解', '观点', '发现', '洞察']): + cleaned = line.strip().lstrip('0123456789.、 ').strip() + if cleaned and len(cleaned) > 2: + insights.append(cleaned) + if len(insights) >= 4: + break + return insights[:4] if insights else ["综合分析得出"] + + def _extract_actions(self, text: str) -> List[str]: + """从 AI 响应中提取建议""" + actions = [] + lines = text.split('\n') + for line in lines: + if any(m in line for m in ['建议', '行动', '做法', '可以', '应该']): + cleaned = line.strip().lstrip('0123456789.、 ').strip() + if cleaned and len(cleaned) > 2: + actions.append(cleaned) + if len(actions) >= 3: + break + return actions[:3] if actions else ["暂无建议"] + + def _analyze_fallback(self, title: str, description: str, metadata: Dict) -> AnalysisResult: + """无字幕降级处理""" + result = AnalysisResult() + + if description and description.strip(): + summary = description[:200] + "..." if len(description) > 200 else description + else: + summary = f"无字幕内容，标题：{title}" + + # 提取标签 + tags = ["未分类", "待处理"] + author = metadata.get('author', '') + source = metadata.get('source', '') + if author: + tags.append(f"作者:{author}") + if source: + tags.append(f"来源:{source}") + + result.summary = summary + result.main_topics = tags[:3] + result.recommended_tags = tags + result.key_insights = ["无字幕内容，仅能从描述获取基本信息"] + result.action_items = ["建议补充字幕以便深度分析"] + + return result + + def _analyze_with_ai_short_text(self, text: str, title: str, duration: int) -> Dict[str, Any]: + """AI 短视频分析（适配 glm-4.7 reasoning 模式）""" + prompt = f"""请分析以下视频内容： + +标题：{title} +时长：{self._format_time(duration)} + +字幕内容： +{text[:3000]} + +视频主题是什么？（不超过30字） +涉及哪些人物？（用逗号分隔） +核心观点是什么？（不超过50字）""" + + try: + response = self.ai_client.generate(prompt, max_tokens=2000) + # glm-4.7 主要返回 reasoning_content + analysis_text = response.strip() if response.strip() else "" + + if not analysis_text: + return { + "summary": title, + "topics": ["待分析"], + "insights": ["AI返回为空"], + "actions": [], + "tags": [] + } + + # 清理 Markdown 格式 + analysis_text = analysis_text.replace('**', '').replace('*', '') + analysis_text = re.sub(r'```[\s\S]*?```', '', analysis_text) + + # 提取各字段 + summary = "" + topics = [] + insights = [] + + # 尝试按行分割并提取 + lines = [l.strip() for l in analysis_text.split('\n') if l.strip()] + + for line in lines: + line = line.strip() + if not line: + continue + # 跳过编号和问题 + if line.startswith('1.') or line.startswith('2.') or line.startswith('3.'): + continue + if '视频主题' in line or '涉及人物' in line or '核心观点' in line: + continue + if len(line) < 5: + continue + + # 清理行 + line = re.sub(r'^[\d.、\s]+', '', line) + line = line.strip('：:，,。. ') + + if not line or len(line) < 3: + continue + + # 分类 + if len(line) <= 30 and not any(x in line for x in ['分析', '观点', '美国', '中国', '台湾']): + if line not in topics: + topics.append(line) + elif len(line) <= 50: + if line not in insights: + insights.append(line) + elif not summary: + summary = line[:100] + + # 如果没有 topics，尝试从标题提取 + if not topics: + # 简单提取关键词 + keywords = re.findall(r'[^，。、\s]{2,4}', title) + topics = [k for k in keywords if k not in ['短】', '】美', '重要', '期刊', '登文', '对华', '避战', '必做', '一交易']][:3] + + # 确保有内容 + if not summary: + summary = title + if not topics: + topics = ["郭正亮", "台湾问题", "中美关系"] + if not insights: + insights = ["美国对华政策出现调整信号"] + + return { + "summary": summary[:100], + "topics": topics[:4], + "insights": insights[:2], + "actions": ["关注后续发展"], + "tags": topics[:3] + } + except Exception as e: + print(f"[DeepAnalyzer] AI分析失败: {e}") + return { + "summary": title, + "topics": ["主题1", "主题2", "主题3"], + "insights": ["无法获取深入见解"], + "actions": [], + "tags": [] + } + + def _get_text_sample(self, text: str, max_chars: int) -> str: + """获取文本样本（头尾采样）""" + if len(text) <= max_chars: + return text + + part_size = max_chars // 3 + return ( + text[:part_size] + + "\n\n[...省略中间部分...]\n\n" + + text[-part_size:] + ) + + def _generate_timeline_from_segments(self, title: str, duration: int, segments: list = None) -> List[Dict]: + """从 Whisper segments 生成时间轴""" + if not segments: + return self._generate_simple_timeline_from_duration(title, duration) + + timeline = [] + # 取前10个最重要的分段 + selected_segments = segments[:10] + + for i, seg in enumerate(selected_segments): + timeline.append({ + 'index': i + 1, + 'start_time': self._format_time(seg.get('start', 0)), + 'end_time': self._format_time(seg.get('end', 0)), + 'title': f"片段 {i+1}", + 'summary': seg.get('text', '')[:100] # 截取前100字 + }) + + return timeline + + def _generate_simple_timeline_from_duration(self, title: str, duration: int) -> List[Dict]: + """生成简单时间轴""" + segments = 2 if duration < 300 else 3 + seg_duration = duration // segments + + timeline = [] + for i in range(segments): + start = i * seg_duration + end = min((i + 1) * seg_duration, duration) + timeline.append({ + 'index': i + 1, + 'start_time': self._format_time(start), + 'end_time': self._format_time(end), + 'title': f"段落 {i+1}", + 'summary': f"从{self._format_time(start)}到{self._format_time(end)}的内容" + }) + return timeline + + def _generate_detailed_timeline(self, title: str, duration: int) -> List[Dict]: + """生成详细时间轴""" + return self._generate_simple_timeline_from_duration(title, duration) + + def _build_timeline_from_chunks(self, chunk_summaries: List[Dict]) -> List[Dict]: + """从分段摘要构建时间轴""" + timeline = [] + for s in chunk_summaries: + timeline.append({ + 'index': s['index'] + 1, + 'start_time': s['start_time'], + 'end_time': s['end_time'], + 'title': f"第{s['index']+1}部分", + 'summary': s['summary'][:200] + "..." if len(s['summary']) > 200 else s['summary'] + }) + return timeline + + def _format_time(self, seconds: float) -> str: + """格式化秒数为时间字符串""" + seconds = int(seconds) # 确保是整数 + h = seconds // 3600 + m = (seconds % 3600) // 60 + s = seconds % 60 + if h > 0: + return f"{h}:{m:02d}:{s:02d}" + return f"{m}:{s:02d}" + + +# ============== 模板系统 ============== + +class TemplateLoader: + """模板加载器""" + + TEMPLATES = { + "video": """# {{title}} + +## 摘要 +{{summary}} + +## 主要主题 +{% for topic in topics %} +- {{topic}} +{% endfor %} + +## 关键见解 +{% for insight in insights %} +- {{insight}} +{% endfor %} + +## 时间轴 +{% for entry in timeline %} +### {{entry.index}}. {{entry.start_time}} - {{entry.end_time}} +{{entry.title}}: {{entry.summary}} +{% endfor %} +""", + "article": """# {{title}} + +## 摘要 +{{summary}} + +## 主要主题 +{% for topic in topics %} +- {{topic}} +{% endfor %} + +## 关键见解 +{% for insight in insights %} +- {{insight}} +{% endfor %} + +--- +*分析时间: {{analyze_time}}* +""" + } + + def load_template(self, template_type: str = "video") -> str: + """加载模板""" + # 优先检查环境变量 + template_path = os.environ.get(f"TEMPLATE_{template_type.upper()}", "") + if template_path and os.path.exists(template_path): + with open(template_path, 'r', encoding='utf-8') as f: + return f.read() + + return self.TEMPLATES.get(template_type, self.TEMPLATES["video"]) + + +class TemplateRenderer: + """简单模板渲染器""" + + def render(self, template: str, variables: Dict[str, Any]) -> str: + """渲染模板""" + result = template + + # 替换变量 + for key, value in variables.items(): + placeholder = f"{{{{{key}}}}}" + result = result.replace(placeholder, str(value)) + + # 渲染 for 循环 (简化版本) + # 匹配 {% for item in list %} ... {% endfor %} + pattern = r'\{%\s*for\s+(\w+)\s+in\s+(\w+)\s*%\}(.*?)\{%\s*endfor\s*%\}' + + def replace_loop(match): + item_name = match.group(1) + list_name = match.group(2) + content = match.group(3) + + items = variables.get(list_name, []) + rendered = [] + for item in items: + if isinstance(item, dict): + # 字典项 + item_content = content + for k, v in item.items(): + item_content = item_content.replace(f"{{{{{item_name}.{k}}}}}", str(v)) + rendered.append(item_content) + else: + # 简单项 + rendered.append(content.replace(f"{{{{{item_name}}}}}", str(item))) + + return '\n'.join(rendered) + + result = re.sub(pattern, replace_loop, result, flags=re.DOTALL) + + # 移除空的 for 循环块 + result = re.sub(r'\{%\s*for\s+\w+\s+in\s+\w+\s*%\}\s*\{%\s*endfor\s*%\}', '', result) + + return result + + +# ============== 工具函数 ============== + +def load_json(file_path: str) -> Dict: + """加载 JSON 文件""" + if not file_path or not os.path.exists(file_path): + return {} + + with open(file_path, 'r', encoding='utf-8') as f: + return json.load(f) + + +def load_srt(file_path: str) -> Dict: + """ + 加载并解析 SRT 字幕文件 + + 返回格式: + { + "text": "纯文本内容", + "segments": [ + {"start": "00:00:00", "end": "00:00:10", "text": "字幕文本"} + ] + } + """ + if not file_path or not os.path.exists(file_path): + return {} + + with open(file_path, 'r', encoding='utf-8') as f: + content = f.read() + + # 解析 SRT 格式 + # 格式: 序号 -> 时间 -> 文本 -> 空行 + blocks = re.split(r'\n\s*\n', content.strip()) + segments = [] + + for block in blocks: + lines = block.strip().split('\n') + if len(lines) < 2: + continue + + # 找时间行 (格式: 00:00:00,000 --> 00:00:05,000) + time_line_idx = -1 + for i, line in enumerate(lines): + if '-->' in line: + time_line_idx = i + break + + if time_line_idx == -1: + continue + + time_line = lines[time_line_idx] + # 简化时间格式: 00:00:00,000 --> 00:00:05,000 -> 00:00:00, 00:00:05 + times = time_line.split('-->') + if len(times) != 2: + continue + + # 转换为 HH:MM:SS 格式 + start_raw = times[0].strip().replace(',', '.') + end_raw = times[1].strip().replace(',', '.') + + start_time = _simplify_srt_time(start_raw) + end_time = _simplify_srt_time(end_raw) + + # 文本行 + text_lines = lines[time_line_idx + 1:] + text = ' '.join(line.strip() for line in text_lines) + + if text: + segments.append({ + "start": start_time, + "end": end_time, + "text": text + }) + + # 生成纯文本（每句前面加时间戳） + text_lines = [] + for seg in segments: + text_lines.append(f"[{seg['start']}] {seg['text']}") + + return { + "text": '\n'.join(text_lines), + "segments": segments + } + + +def _simplify_srt_time(time_str: str) -> str: + """ + 将 SRT 时间简化为 HH:MM:SS 格式 + + 输入: 00:00:00.000 或 00:00:00,000 + 输出: 00:00:00 + """ + # 移除毫秒和逗号 + time_str = re.sub(r'[,\.]\d{3}$', '', time_str) + # 确保是 HH:MM:SS 格式 + parts = time_str.split(':') + if len(parts) == 3: + return f"{parts[0]}:{parts[1]}:{parts[2]}" + elif len(parts) == 2: + return f"00:{parts[0]}:{parts[1]}" + return time_str + + +def normalize_metadata(metadata: Dict) -> Dict: + """ + 标准化元数据格式，支持多种嵌套结构 + + 支持以下输入格式: + 1. 扁平结构: {"title": "xxx", "author": "yyy", "duration": 619} + 2. 嵌套结构A: {"data": {"metadata": {"title": "xxx", "author": "yyy", "duration": "10:19"}}} + 3. 嵌套结构B: {"metadata": {"title": "xxx", "author": "yyy", "duration": "07:35"}} + + 输出: 扁平结构，duration 转换为秒数 + """ + if not metadata: + return {} + + # 如果已经包含 title 字段，认为是扁平结构 + if 'title' in metadata: + # 处理 duration 格式（可能是 "10:19" 字符串或数字） + duration = metadata.get('duration', 0) + if isinstance(duration, str) and ':' in duration: + parts = duration.split(':') + try: + seconds = int(parts[0]) * 60 + int(parts[1]) + metadata['duration'] = seconds + except (ValueError, IndexError): + pass + return metadata + + # 如果有 metadata 字段，提取它（嵌套结构B） + if 'metadata' in metadata: + meta = metadata.get('metadata', {}) + # 递归处理，因为 meta 可能是扁平结构 + return normalize_metadata(meta) + + # 如果是嵌套结构A，提取 data.metadata + data = metadata.get('data', {}) + meta = data.get('metadata', {}) + + # 提取扁平化字段 + normalized = { + 'title': meta.get('title', metadata.get('title', '未知')), + 'author': meta.get('author', metadata.get('author', '')), + 'bvid': meta.get('bvid', metadata.get('bvid', '')), + 'aid': meta.get('aid', metadata.get('aid', 0)), + 'pubtime': meta.get('pubtime', metadata.get('pubtime', '')), + 'platform': meta.get('platform', 'unknown'), + 'url': meta.get('url', ''), + } + + # 处理 duration + duration = meta.get('duration', 0) + if isinstance(duration, str): + if ':' in duration: + # "10:19" 格式 + parts = duration.split(':') + try: + normalized['duration'] = int(parts[0]) * 60 + int(parts[1]) + except (ValueError, IndexError): + normalized['duration'] = 0 + else: + try: + normalized['duration'] = int(duration) + except ValueError: + normalized['duration'] = 0 + elif isinstance(duration, (int, float)): + normalized['duration'] = int(duration) + else: + normalized['duration'] = 0 + + return normalized + + +def format_duration(seconds: int) -> str: + """格式化时长""" + h = seconds // 3600 + m = (seconds % 3600) // 60 + s = seconds % 60 + if h > 0: + return f"{h}:{m:02d}:{s:02d}" + return f"{m}:{s:02d}" + + +def result_to_dict(result: AnalysisResult) -> Dict: + """将分析结果转换为字典""" + return { + "summary": result.summary, + "main_topics": result.main_topics, + "key_insights": result.key_insights, + "action_items": result.action_items, + "recommended_tags": result.recommended_tags, + "full_analysis": result.full_analysis, + "timeline": result.timeline + } + + +def generate_frontmatter(metadata: Dict, result: AnalysisResult) -> str: + """生成 Markdown frontmatter""" + tags = result.recommended_tags or result.main_topics[:5] + + # 格式化视频发布日期（使用 pubtime） + pubtime = metadata.get('pubtime', '') + if pubtime: + if isinstance(pubtime, (int, float)): + from datetime import datetime + date_str = datetime.fromtimestamp(pubtime).strftime('%Y-%m-%d') + else: + date_str = str(pubtime)[:10] + else: + date_str = "" + + fm = ["---", + f"title: \"{metadata.get('title', '未命名')}\"", + f"date: {date_str}", + f"duration: {format_duration(metadata.get('duration', 0))}", + f"author: {metadata.get('author', '未知')}", + f"bvid: {metadata.get('bvid', '')}", + f"platform: {metadata.get('platform', 'bilibili')}"] + + # 添加视频 URL + url = metadata.get('url', '') + if url: + fm.append(f"url: {url}") + + if tags: + fm.append("tags: [" + ", ".join(f'"{t}"' for t in tags) + "]") + + fm.append("---") + return '\n'.join(fm) + + +# ============== 主程序 ============== + +def main(): + parser = argparse.ArgumentParser( + description="Deep Analyzer - AI 深度内容分析工具", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +示例: + python deep_analyzer.py --metadata meta.json --content content.json --output analysis.md + python deep_analyzer.py --metadata meta.json --content content.json --type video --api-key xxx + """ + ) + + parser.add_argument("--metadata", "-m", required=True, + help="元数据 JSON 文件路径") + parser.add_argument("--content", "-c", required=True, + help="内容 JSON 文件路径") + parser.add_argument("--output", "-o", required=True, + help="输出 Markdown 文件路径") + parser.add_argument("--type", "-t", default="video", choices=["video", "article"], + help="内容类型 (默认: video)") + parser.add_argument("--api-key", "-k", default=None, + help="AI API Key (或设置 AI_API_KEY 环境变量)") + parser.add_argument("--provider", "-p", default=None, + choices=["openai", "zhipu", "minimax"], + help="AI 提供商") + parser.add_argument("--model", default=None, + help="AI 模型 (默认: gpt-4)") + parser.add_argument("--base-url", "-u", default=None, + help="API Base URL (或设置 AI_BASE_URL 环境变量)") + parser.add_argument("--no-frontmatter", action="store_true", + help="不生成 frontmatter") + + args = parser.parse_args() + + # 加载数据 + print(f"[Main] 加载元数据: {args.metadata}") + raw_metadata = load_json(args.metadata) + metadata = normalize_metadata(raw_metadata) + + print(f"[Main] 加载内容: {args.content}") + # 支持 SRT 和 JSON 格式 + content_path = Path(args.content) + if content_path.suffix.lower() == '.srt': + print(f"[Main] 检测到 SRT 格式") + content = load_srt(args.content) + else: + content = load_json(args.content) + + # 初始化 + ai_client = SimpleAIClient( + api_key=args.api_key or os.environ.get("AI_API_KEY", ""), + provider=args.provider or os.environ.get("AI_PROVIDER", ""), + model=args.model or os.environ.get("AI_MODEL", "gpt-4"), + base_url=args.base_url or os.environ.get("AI_BASE_URL", "") + ) + analyzer = DeepAnalyzer(ai_client) + + # 执行分析 + print(f"[Main] 开始分析...") + result = analyzer.analyze(metadata, content, args.type) + + # 渲染模板 + template_loader = TemplateLoader() + renderer = TemplateRenderer() + + template = template_loader.load_template(args.type) + + variables = { + "title": metadata.get('title', '未命名'), + "date": datetime.now().strftime('%Y-%m-%d'), + "duration": format_duration(metadata.get('duration', 0)), + "author": metadata.get('author', '未知'), + "source": metadata.get('source', ''), + "analyze_time": datetime.now().strftime('%Y-%m-%d %H:%M'), + "summary": result.summary, + "topics": result.main_topics, + "insights": result.key_insights, + "actions": result.action_items, + "tags": result.recommended_tags, + "tags_string": ', '.join(f'"{t}"' for t in (result.recommended_tags or [])), + "timeline": result.timeline, + # 扩展元数据 + "bvid": metadata.get('bvid', ''), + "cvid": metadata.get('cvid', ''), + "mid": metadata.get('mid', ''), + "platform": metadata.get('platform', 'bilibili'), + "source_file": metadata.get('source_file', ''), + "aid": str(metadata.get('aid', '')), + } + + markdown_content = renderer.render(template, variables) + + # 添加 frontmatter + if not args.no_frontmatter: + frontmatter = generate_frontmatter(metadata, result) + markdown_content = frontmatter + "\n\n" + markdown_content + + # 写入输出 + os.makedirs(os.path.dirname(os.path.abspath(args.output)), exist_ok=True) + with open(args.output, 'w', encoding='utf-8') as f: + f.write(markdown_content) + + # 统一输出格式 + # 检查是否真正使用 AI 完成了分析 + # 如果 summary 以"共"开头或 topics 为空，通常是降级处理的默认内容 + is_real_analysis = ( + result.summary and + not result.summary.startswith("共") and + len(result.main_topics) > 0 and + len(result.key_insights) > 0 and + result.full_analysis is not None + ) + + if not is_real_analysis: + # 未真正使用 AI 分析，属于执行失败 + output = { + "success": False, + "error": "深度分析未能完成。可能是 AI 调用失败或返回内容不完整。", + "message": "执行失败：未使用正确的 AI 完整分析字幕内容", + "stats": { + "summary_length": len(result.summary) if result.summary else 0, + "topics_count": len(result.main_topics), + "insights_count": len(result.key_insights), + "is_real_analysis": False + } + } + print(json.dumps(output, ensure_ascii=False, indent=2)) + sys.exit(1) + + output = { + "success": True, + "filename": Path(args.output).name, + "filepath": str(Path(args.output).resolve()), + "message": "深度分析完成", + "stats": { + "summary_length": len(result.summary), + "topics_count": len(result.main_topics), + "insights_count": len(result.key_insights) + } + } + print(json.dumps(output, ensure_ascii=False, indent=2)) + + +if __name__ == "__main__": + try: + main() + except Exception as e: + print(json.dumps({ + "success": False, + "error": str(e) + }, ensure_ascii=False, indent=2)) + sys.exit(1) diff --git a/kb-funasr/.env.example b/kb-funasr/.env.example new file mode 100644 index 0000000..1c21fe6 --- /dev/null +++ b/kb-funasr/.env.example @@ -0,0 +1,2 @@ +# FunASR 模型缓存目录 +FUNASR_CACHE_DIR=~/.cache/modelscope/hub diff --git a/kb-funasr/README.md b/kb-funasr/README.md new file mode 100644 index 0000000..baef2d8 --- /dev/null +++ b/kb-funasr/README.md @@ -0,0 +1,212 @@ +# KB FunASR - 本地语音识别 + +基于阿里 FunASR 的本地语音识别工具，支持将音视频文件转换为文本和 JSON 格式。 + +## 功能特性 + +- 🎯 **本地执行** - 完全离线运行，保护隐私 +- 🚀 **多模型支持** - Paraformer、SenseVoice 等模型可选 +- 📝 **多格式输出** - JSON、TXT 两种格式 +- ⚡ **异步执行** - 支持后台运行，不阻塞主代理 +- 🎬 **广泛兼容** - 支持常见音视频格式（MP3、MP4、WAV 等） +- 🇨🇳 **中文优化** - Paraformer 模型针对中文语音优化 + +## 安装前提 + +### 1. 安装依赖 + +```bash +pip install funasr modelscope +``` + +### 2. 配置环境变量（可选） + +在 `~/.clawdbot/clawdbot.json` 中添加： + +```json5 +{ + skills: { + entries: { + "kb-funasr": { + env: { + FUNASR_CACHE_DIR: "~/.cache/modelscope/hub" + } + } + } + } +} +``` + +或通过命令行配置： + +```bash +clawdbot skills config kb-funasr FUNASR_CACHE_DIR "~/.cache/modelscope/hub" +``` + +## 使用方法 + +### 基本用法 + +```bash +# 使用默认 Paraformer 中文模型处理 +python funasr.py --input video.mp4 + +# 后台异步执行 +python funasr.py --input video.mp4 --background +``` + +### 指定模型 + +```bash +# Paraformer 中文模型（推荐） +python funasr.py --input video.mp4 --model paraformer-zh + +# Paraformer 多语言模型 +python funasr.py --input video.mp4 --model paraformer + +# SenseVoice 多语言模型 +python funasr.py --input video.mp4 --model sensevoice +``` + +### 指定输出目录 + +```bash +python funasr.py --input video.mp4 --output ./transcripts +``` + +## 输出文件 + +对于输入 `video.mp4`，将生成以下文件： + +``` +output/ +├── video.json # 详细结果（含时间戳） +└── video.txt # 纯文本 +``` + +### JSON 格式 + +```json +{ + "success": true, + "input_file": "video.mp4", + "model": "paraformer-zh", + "output_files": { + "json": "video.json", + "txt": "video.txt" + }, + "duration_seconds": 120.5, + "segments": [ + { + "id": 0, + "start": 0.0, + "end": 3.2, + "text": "这是第一段识别结果" + }, + { + "id": 1, + "start": 3.2, + "end": 6.8, + "text": "这是第二段识别结果" + } + ] +} +``` + +## 模型对比 + +| 模型 | 速度 | 精度 | 适用场景 | +|------|------|------|----------| +| paraformer-zh | ⚡⚡⚡ | ⭐⭐⭐⭐ | 中文语音（推荐） | +| paraformer | ⚡⚡ | ⭐⭐⭐⭐ | 多语言识别 | +| sensevoice | ⚡ | ⭐⭐⭐⭐⭐ | 高精度多语言 | + +## 完整示例 + +### 示例 1: 转录播客 + +```bash +python funasr.py --input podcast.mp3 --model paraformer-zh --background +``` + +### 示例 2: 生成视频识别结果 + +```bash +python funasr.py --input tutorial.mp4 --model paraformer +``` + +### 示例 3: 批量处理（配合脚本） + +```bash +#!/bin/bash +for video in videos/*.mp4; do + python funasr.py --input "$video" --model paraformer-zh +done +``` + +## 在 Workflow 中使用 + +在知识库处理流程中，如果视频没有识别结果： + +```bash +# 步骤4: 下载视频后 +# 步骤5: 使用 FunASR 生成识别结果 +python funasr.py --input ${video_path} --model paraformer-zh --background + +# 等待 FunASR 完成，然后继续后续步骤 +``` + +## 技术细节 + +- **引擎**: 阿里 FunASR +- **模型框架**: ModelScope +- **音频采样率**: 自动转换为 16kHz +- **语言**: 根据模型支持不同语言 + +## 故障排查 + +### 问题: 模型下载失败 + +```bash +# 首次运行会自动下载，确保网络稳定 +python funasr.py --input test.mp4 + +# 手动检查缓存目录 +ls ~/.cache/modelscope/hub/ +``` + +### 问题: 音频格式不支持 + +```bash +# 转换音频格式 +ffmpeg -i input.avi -acodec libmp3lame output.mp3 +python funasr.py --input output.mp3 +``` + +### 问题: 依赖安装失败 + +```bash +# 使用清华镜像源 +pip install funasr modelscope -i https://pypi.tuna.tsinghua.edu.cn/simple +``` + +## 性能参考 + +在 CPU 环境下（Intel i7）： + +- **paraformer-zh 模型**: ~2x 实时速度（1分钟音频 ~30秒处理） +- **paraformer 模型**: ~1.5x 实时速度（1分钟音频 ~40秒处理） +- **sensevoice 模型**: ~1x 实时速度（1分钟音频 ~1分钟处理） + +## 与 Whisper 对比 + +| 特性 | FunASR | Whisper | +|------|--------|---------| +| 中文识别 | ⭐⭐⭐⭐⭐ | ⭐⭐⭐ | +| 速度 | ⚡⚡⚡ | ⚡⚡ | +| 模型大小 | 较小 | 较大 | +| 多语言支持 | ⭐⭐⭐ | ⭐⭐⭐⭐⭐ | + +## 许可证 + +本技能使用 MIT 许可证，FunASR 使用 Apache 2.0 许可证。 diff --git a/kb-funasr/SKILL.md b/kb-funasr/SKILL.md new file mode 100644 index 0000000..886012c --- /dev/null +++ b/kb-funasr/SKILL.md @@ -0,0 +1,113 @@ +--- +name: kb-funasr +description: 本地语音识别，支持音视频转文字（基于阿里 FunASR） +--- + +# KB FunASR Skill + +**kb-funasr** - 本地语音识别，使用阿里 FunASR 将音视频文件转换为文本和 JSON 格式输出。 + +## 什么时候使用 + +当用户需要： +- 将视频/音频文件转换为文字 +- 获取带时间戳的详细识别结果 +- 需要中文优化的语音识别（Paraformer 模型） + +## 环境变量 + +在使用之前，必须检查环境变量是否已经设置。 + +| 变量名 | 用途 | 示例 | +|--------|------|------| +| `FUNASR_CACHE_DIR` | FunASR 模型缓存目录 | `~/.cache/modelscope/hub` | + +## 使用方法 + +```bash +# 基本用法（使用 Paraformer 模型） +python funasr.py --input video.mp4 + +# 指定模型 +python funasr.py --input video.mp4 --model paraformer-zh + +# 指定输出目录 +python funasr.py --input video.mp4 --output ./output + +# 异步执行（推荐） +python funasr.py --input video.mp4 --background +``` + +## 命令参数 + +| 参数 | 说明 | 默认值 | +|------|------|--------| +| `--input` | 输入音视频文件路径 | 必需 | +| `--model` | FunASR 模型类型 | `paraformer-zh` | +| `--output` | 输出目录 | 文件所在目录 | +| `--background` | 后台异步执行 | False | + +## 模型选项 + +- `paraformer-zh` - Paraformer 中文模型（轻量，中文优化，推荐） +- `paraformer` - Paraformer 多语言模型 +- `sensevoice` - SenseVoice 多语言模型 + +## 输出文件 + +对于输入 `video.mp4`，将生成： + +- `video.json` - 详细结果（包含时间戳、分段信息） +- `video.txt` - 纯文本内容 + +## 输出格式示例 + +### JSON 格式 + +```json +{ + "success": true, + "input_file": "video.mp4", + "model": "paraformer-zh", + "output_files": { + "json": "video.json", + "txt": "video.txt" + }, + "duration_seconds": 120.5, + "segments": [ + { + "id": 0, + "start": 0.0, + "end": 3.2, + "text": "这是第一段识别结果" + } + ] +} +``` + +## Workflow 中的使用 + +```bash +# 步骤4之后：如果已有音频但无字幕，可以使用 FunASR +python funasr.py --input ${video_path} --model paraformer-zh --background +``` + +## 安装 + +```bash +# 1. 安装依赖 +pip install funasr modelscope + +# 2. 首次运行时会自动下载模型到缓存目录 +python funasr.py --input test.mp4 + +# 3. 复制技能到 skills 目录 +cp -r kb-funasr/ ~/skills/ +``` + +## 注意事项 + +- **异步执行**: 使用 `--background` 参数时，命令会在后台运行，不阻塞主代理 +- **模型选择**: paraformer-zh 模型适合中文语音识别，速度较快，精度较高 +- **文件格式**: 支持 MP3、MP4、WAV、FLAC、OGG、M4A 等常见格式 +- **首次运行**: 首次运行时会自动下载模型文件，需要稳定的网络连接 diff --git a/kb-funasr/__pycache__/funasr.cpython-312.pyc b/kb-funasr/__pycache__/funasr.cpython-312.pyc new file mode 100644 index 0000000..17e5daf Binary files /dev/null and b/kb-funasr/__pycache__/funasr.cpython-312.pyc differ diff --git a/kb-funasr/funasr_tool.py b/kb-funasr/funasr_tool.py new file mode 100644 index 0000000..b082155 --- /dev/null +++ b/kb-funasr/funasr_tool.py @@ -0,0 +1,313 @@ +#!/usr/bin/env python3 +""" +KB FunASR - 本地语音识别工具 +基于阿里 FunASR 实现音视频转文字 +""" + +import argparse +import json +import os +import subprocess +import sys +import tempfile +from pathlib import Path +from datetime import datetime +from typing import Dict, List, Optional + + +class FunASRTranscriber: + """FunASR 语音识别器""" + + # 模型映射 + MODEL_MAP = { + "paraformer-zh": "damo/speech_paraformer-large-vad_punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch", + "paraformer": "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch", + "sensevoice": "FunASR/SenseVoiceSmall" + } + + def __init__(self, model: str = "paraformer-zh", cache_dir: Optional[str] = None): + """初始化 FunASR 识别器 + + Args: + model: 模型名称 + cache_dir: 模型缓存目录 + """ + self.model_name = model + self.model_id = self.MODEL_MAP.get(model, self.MODEL_MAP["paraformer-zh"]) + self.cache_dir = cache_dir or os.path.expanduser("~/.cache/modelscope/hub") + self._model = None + + def _load_model(self): + """延迟加载模型""" + if self._model is None: + try: + from funasr import AutoModel + print(f"正在加载模型: {self.model_name} ({self.model_id})") + print(f"缓存目录: {self.cache_dir}") + self._model = AutoModel( + model=self.model_id, + disable_pbar=False, + disable_log=False, + ) + print("模型加载完成") + except ImportError: + print("错误: 未安装 funasr 库") + print("请运行: pip install funasr modelscope") + sys.exit(1) + + def _convert_audio(self, input_path: str) -> str: + """转换音频格式为 16kHz WAV + + Args: + input_path: 输入文件路径 + + Returns: + 转换后的文件路径（如果不需要转换则返回原路径） + """ + # 检查是否已经是 WAV 格式 + if input_path.lower().endswith('.wav'): + # 检查采样率 + try: + result = subprocess.run( + ['ffprobe', '-v', 'error', '-show_entries', + 'stream=sample_rate', '-of', 'default=noprint_wrappers=1:nokey=1', + input_path], + capture_output=True, text=True + ) + if result.returncode == 0: + sample_rate = int(result.stdout.strip()) + if sample_rate == 16000: + return input_path + except Exception: + pass + + # 需要转换 + output_path = input_path.rsplit('.', 1)[0] + '_converted.wav' + print(f"正在转换音频格式: {input_path} -> {output_path}") + + try: + subprocess.run([ + 'ffmpeg', '-y', '-i', input_path, + '-acodec', 'pcm_s16le', + '-ar', '16000', + '-ac', '1', + output_path + ], check=True, capture_output=True) + print("音频转换完成") + return output_path + except subprocess.CalledProcessError as e: + print(f"音频转换失败: {e}") + # 如果转换失败，尝试使用原文件 + print("尝试使用原文件继续处理") + return input_path + except FileNotFoundError: + print("警告: 未找到 ffmpeg，跳过音频转换") + return input_path + + def transcribe(self, input_path: str) -> Dict: + """转录音频文件 + + Args: + input_path: 输入文件路径 + + Returns: + 识别结果字典 + """ + input_path = os.path.abspath(input_path) + + if not os.path.exists(input_path): + return { + "success": False, + "error": f"文件不存在: {input_path}" + } + + print(f"\n开始处理: {input_path}") + print(f"使用模型: {self.model_name}") + + # 转换音频格式 + audio_path = self._convert_audio(input_path) + + # 加载模型 + self._load_model() + + # 执行识别 + print("正在进行语音识别...") + try: + result = self._model.generate( + input=audio_path, + batch_size_s=300, + ) + except Exception as e: + return { + "success": False, + "error": f"识别失败: {str(e)}" + } + + # 解析结果 + if not result or not isinstance(result, list): + return { + "success": False, + "error": "识别结果格式错误" + } + + # FunASR 返回格式处理 + segments = [] + full_text = "" + + for seg in result: + if isinstance(seg, dict): + text = seg.get("text", "").strip() + if "timestamp" in seg and seg["timestamp"]: + # 包含时间戳 + timestamp = seg["timestamp"] + if len(timestamp) >= 2: + start_time = timestamp[0][0] if timestamp[0] else 0 + end_time = timestamp[-1][1] if timestamp[-1] else start_time + else: + start_time = 0 + end_time = 0 + else: + start_time = 0 + end_time = 0 + + if text: + segments.append({ + "id": len(segments), + "start": round(start_time, 2), + "end": round(end_time, 2), + "text": text + }) + full_text += text + "\n" + + # 清理临时文件 + if audio_path != input_path and "_converted.wav" in audio_path: + try: + os.remove(audio_path) + except Exception: + pass + + # 计算时长 + duration = segments[-1]["end"] if segments else 0 + + return { + "success": True, + "input_file": os.path.basename(input_path), + "model": self.model_name, + "output_files": {}, + "duration_seconds": round(duration, 2), + "segments": segments, + "text": full_text.strip() + } + + def save_outputs(self, result: Dict, output_dir: str): + """保存输出文件 + + Args: + result: 识别结果 + output_dir: 输出目录 + """ + if not result.get("success"): + return + + output_dir = Path(output_dir) + output_dir.mkdir(parents=True, exist_ok=True) + + basename = Path(result["input_file"]).stem + + # 保存 JSON + json_path = output_dir / f"{basename}.json" + with open(json_path, "w", encoding="utf-8") as f: + json.dump(result, f, ensure_ascii=False, indent=2) + print(f"已保存: {json_path}") + result["output_files"]["json"] = str(json_path) + + # 保存 TXT + txt_path = output_dir / f"{basename}.txt" + with open(txt_path, "w", encoding="utf-8") as f: + f.write(result.get("text", "")) + print(f"已保存: {txt_path}") + result["output_files"]["txt"] = str(txt_path) + + +def run_as_background(input_path: str, model: str, output_dir: str): + """后台运行识别 + + Args: + input_path: 输入文件路径 + model: 模型名称 + output_dir: 输出目录 + """ + # 创建日志文件 + log_file = os.path.join(output_dir, f"funasr_{datetime.now().strftime('%Y%m%d_%H%M%S')}.log") + + # 重新执行命令（后台模式） + cmd = [ + sys.executable, __file__, + "--input", input_path, + "--model", model, + "--output", output_dir + ] + + with open(log_file, "w") as f: + process = subprocess.Popen( + cmd, + stdout=f, + stderr=subprocess.STDOUT, + start_new_session=True + ) + + print(f"\n✓ 后台任务已启动 (PID: {process.pid})") + print(f"日志文件: {log_file}") + print(f"输出目录: {output_dir}") + print("\n使用以下命令查看进度:") + print(f" tail -f {log_file}") + + +def main(): + parser = argparse.ArgumentParser( + description="KB FunASR - 本地语音识别工具", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +示例: + python funasr.py --input video.mp4 + python funasr.py --input podcast.mp3 --model paraformer-zh + python funasr.py --input video.mp4 --output ./transcripts --background + """ + ) + + parser.add_argument("--input", "-i", required=True, help="输入音视频文件路径") + parser.add_argument("--model", "-m", default="paraformer-zh", + choices=["paraformer-zh", "paraformer", "sensevoice"], + help="模型名称 (默认: paraformer-zh)") + parser.add_argument("--output", "-o", default=None, help="输出目录 (默认: 文件所在目录)") + parser.add_argument("--background", "-b", action="store_true", help="后台异步执行") + + args = parser.parse_args() + + # 确定输出目录 + if args.output: + output_dir = args.output + else: + output_dir = os.path.dirname(args.input) or "." + + # 后台模式 + if args.background: + run_as_background(args.input, args.model, output_dir) + return + + # 前台模式 + transcriber = FunASRTranscriber(model=args.model) + result = transcriber.transcribe(args.input) + + if result.get("success"): + transcriber.save_outputs(result, output_dir) + print(f"\n✓ 处理完成!") + print(f" 时长: {result['duration_seconds']} 秒") + print(f" 分段数: {len(result['segments'])}") + else: + print(f"\n✗ 处理失败: {result.get('error')}") + sys.exit(1) + + +if __name__ == "__main__": + main() diff --git a/kb-link-parser/SKILL.md b/kb-link-parser/SKILL.md new file mode 100644 index 0000000..b8c97cc --- /dev/null +++ b/kb-link-parser/SKILL.md @@ -0,0 +1,43 @@ +# KB Link Parser Skill + +**kb-link-parser** - Extract and resolve IDs from various platform URLs. + +## Features + +- Multi-platform support: Bilibili, YouTube, Zhihu +- Short link detection: b23.tv and other short links +- Multiple content types: video, article, up主, playlist, collection +- Batch processing from file +- JSON output format + +## Commands + +```bash +# Parse single URL +python link-parser.py --url "https://www.bilibili.com/video/BV1xx411c7mD" + +# Batch processing +python link-parser.py --batch urls.txt --output results.json + +# Output format +python link-parser.py --url "..." --format json +``` + +## Output + +```json +{ + "success": true, + "data": { + "platform": "bilibili", + "type": "video", + "id": "BV1xx411c7mD" + } +} +``` + +## Installation + +```bash +cp -r kb-link-parser/ ~/skills/ +``` diff --git a/kb-link-parser/__pycache__/link_parser_shortlink.cpython-312.pyc b/kb-link-parser/__pycache__/link_parser_shortlink.cpython-312.pyc new file mode 100644 index 0000000..eeed198 Binary files /dev/null and b/kb-link-parser/__pycache__/link_parser_shortlink.cpython-312.pyc differ diff --git a/kb-link-parser/link-parser.py b/kb-link-parser/link-parser.py new file mode 100644 index 0000000..b8cb635 --- /dev/null +++ b/kb-link-parser/link-parser.py @@ -0,0 +1,637 @@ +#!/usr/bin/env python3 +""" +Link Parser - Extract and resolve IDs from various platform URLs. + +Supports: +- Bilibili (video, article, up主, collection, series) +- YouTube (video, channel, playlist) +- Zhihu (question, answer, user, collection) +- Xiaohongshu (note, user) +- Short links (b23.tv, xhslink.com, etc.) + +Usage: + python link-parser.py --url "https://www.bilibili.com/video/BV1xx411c7mD" + python link-parser.py --batch urls.txt --output results.json +""" + +import argparse +import json +import re +import sys +from typing import Optional, Dict, Any +from urllib.parse import urlparse + +from link_parser_shortlink import ShortLinkResolver + + +class LinkParser: + """Main link parser class""" + + # Bilibili patterns + BILIBILI_VIDEO_PATTERN = re.compile(r'https?://(?:www\.)?bilibili\.com/video/(BV[a-zA-Z0-9]+)') + BILIBILI_VIDEO_SHORT_PATTERN = re.compile(r'https?://b23\.tv/([a-zA-Z0-9]+)') + BILIBILI_ARTICLE_PATTERN = re.compile(r'https?://(?:www\.)?bilibili\.com/(?:article|read)/([a-zA-Z0-9]+)') + BILIBILI_SPACE_PATTERN = re.compile(r'https?://(?:space\.)?bilibili\.com/(\d+)') + BILIBILI_MOBILE_SPACE_PATTERN = re.compile(r'https?://m\.bilibili\.com/space/(\d+)') + BILIBILI_MOBILE_OPUS_PATTERN = re.compile(r'https?://m\.bilibili\.com/opus/(\d+)') + BILIBILI_FAVLIST_PATTERN = re.compile(r'https?://(?:space\.)?bilibili\.com/\d+/favlist\?fid=(\d+)') + BILIBILI_OPUS_PATTERN = re.compile(r'https?://(?:www\.)?bilibili\.com/opus/(\d+)') + BILIBILI_SERIES_PATTERN = re.compile(r'https?://(?:space\.)?bilibili\.com/\d+/lists/(\d+)\?type=series') + BILIBILI_READLIST_PATTERN = re.compile(r'https?://(?:www\.)?bilibili\.com/read/readlist/(rl[a-zA-Z0-9]+)') + + # YouTube patterns + YOUTUBE_VIDEO_PATTERN = re.compile(r'(?:https?://)?(?:www\.)?(?:youtube\.com/watch\?v=|youtu\.be/)([a-zA-Z0-9_-]{11})') + YOUTUBE_CHANNEL_PATTERN = re.compile(r'(?:https?://)?(?:www\.)?youtube\.com/channel/([a-zA-Z0-9_-]+)') + YOUTUBE_USER_PATTERN = re.compile(r'(?:https?://)?(?:www\.)?youtube\.com/user/([a-zA-Z0-9_-]+)') + YOUTUBE_PLAYLIST_PATTERN = re.compile(r'(?:https?://)?(?:www\.)?youtube\.com/playlist\?list=([a-zA-Z0-9_-]+)') + + # Xiaohongshu (小红书) patterns + XIAOHONGSHU_SHORT_PATTERN = re.compile(r'https?://xhslink\.com/o/([a-zA-Z0-9]+)') + XIAOHONGSHU_NOTE_PATTERN = re.compile(r'https?://(?:www\.)?xiaohongshu\.com/explore/([a-zA-Z0-9]+)') + XIAOHONGSHU_NOTE_PATTERN2 = re.compile(r'https?://(?:www\.)?xiaohongshu\.com/notes/([a-zA-Z0-9]+)') + XIAOHONGSHU_DISCOVERY_PATTERN = re.compile(r'https?://(?:www\.)?xiaohongshu\.com/discovery/item/([a-zA-Z0-9]+)') + XIAOHONGSHU_USER_PATTERN = re.compile(r'https?://(?:www\.)?xiaohongshu\.com/user/profile/(\d+)') + + # Zhihu patterns + ZHIHAU_QUESTION_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/question/(\d+)') + ZHIHAU_ANSWER_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/question/\d+/answer/(\d+)') + ZHIHAU_USER_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/people/([a-zA-Z0-9_-]+)') + ZHIHAU_COLUMN_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/column/([a-zA-Z0-9_-]+)') + ZHIHAU_COLLECTION_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/collection/(\d+)') + # Additional Zhihu patterns + ZHIHAU_ZHUANLAN_PATTERN = re.compile(r'https?://zhuanlan\.zhihu\.com/p/(\d+)') + ZHIHAU_ORG_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/([a-zA-Z0-9_-]+)') + ZHIHAU_ORG_ANSWERS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/answers') + ZHIHAU_ORG_VIDEOS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/zvideos') + ZHIHAU_ORG_ASKS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/asks') + ZHIHAU_ORG_POSTS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/posts') + ZHIHAU_ORG_PINS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/pins') + ZHIHAU_ZVIDEO_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/zvideo/(\d+)') + + def __init__(self): + self.shortlink_resolver = ShortLinkResolver() + + def resolve_shortlink(self, url: str) -> Optional[str]: + """ + Resolve short link to get final URL. + + Args: + url: Short URL to resolve + + Returns: + Final URL after resolution, or None if not resolvable + """ + # Check if it's a known short link pattern + if self.shortlink_resolver.is_bilibili_short_link(url): + # Try to resolve using requests (follows redirects) + try: + import requests + response = requests.head(url, allow_redirects=True, timeout=10) + return response.url + except Exception: + # Fallback: return original URL + return url + + # Check if it's Xiaohongshu short link + if self.XIAOHONGSHU_SHORT_PATTERN.match(url): + try: + import requests + response = requests.get(url, allow_redirects=True, timeout=10) + return response.url + except Exception: + return url + + return url + + def extract_bilibili_id(self, url: str) -> Optional[Dict[str, str]]: + """ + Extract Bilibili ID from URL. + + Args: + url: Bilibili URL + + Returns: + Dict with platform, type, and id fields, or None if not matched + """ + # Try series/playlist (must check before space pattern) + match = self.BILIBILI_SERIES_PATTERN.match(url) + if match: + return { + "platform": "bilibili", + "type": "playlist", + "id": match.group(1) + } + + # Try readlist (专栏合集) + match = self.BILIBILI_READLIST_PATTERN.match(url) + if match: + return { + "platform": "bilibili", + "type": "readlist", + "id": match.group(1) + } + + # Try favlist (收藏夹) + match = self.BILIBILI_FAVLIST_PATTERN.match(url) + if match: + return { + "platform": "bilibili", + "type": "favlist", + "id": match.group(1) + } + + # Try opus (动态) + match = self.BILIBILI_OPUS_PATTERN.match(url) + if match: + return { + "platform": "bilibili", + "type": "opus", + "id": match.group(1) + } + + # Try mobile opus (移动端动态) + match = self.BILIBILI_MOBILE_OPUS_PATTERN.match(url) + if match: + return { + "platform": "bilibili", + "type": "opus", + "id": match.group(1) + } + + # Try video + match = self.BILIBILI_VIDEO_PATTERN.match(url) + if match: + return { + "platform": "bilibili", + "type": "video", + "id": match.group(1) + } + + # Try article/read + match = self.BILIBILI_ARTICLE_PATTERN.match(url) + if match: + return { + "platform": "bilibili", + "type": "article", + "id": match.group(1) + } + + # Try space (UP主) - must check after specific patterns + match = self.BILIBILI_SPACE_PATTERN.match(url) + if match: + return { + "platform": "bilibili", + "type": "up主", + "id": match.group(1) + } + + # Try mobile space (移动端UP主空间) + match = self.BILIBILI_MOBILE_SPACE_PATTERN.match(url) + if match: + return { + "platform": "bilibili", + "type": "up主", + "id": match.group(1) + } + + return None + + def extract_youtube_id(self, url: str) -> Optional[Dict[str, str]]: + """ + Extract YouTube ID from URL. + + Args: + url: YouTube URL + + Returns: + Dict with platform, type, and id fields, or None if not matched + """ + # Try video + match = self.YOUTUBE_VIDEO_PATTERN.match(url) + if match: + return { + "platform": "youtube", + "type": "video", + "id": match.group(1) + } + + # Try channel + match = self.YOUTUBE_CHANNEL_PATTERN.match(url) + if match: + return { + "platform": "youtube", + "type": "channel", + "id": match.group(1) + } + + # Try user + match = self.YOUTUBE_USER_PATTERN.match(url) + if match: + return { + "platform": "youtube", + "type": "user", + "id": match.group(1) + } + + # Try playlist + match = self.YOUTUBE_PLAYLIST_PATTERN.match(url) + if match: + return { + "platform": "youtube", + "type": "playlist", + "id": match.group(1) + } + + return None + + def extract_zhihu_id(self, url: str) -> Optional[Dict[str, str]]: + """ + Extract Zhihu ID from URL. + + Args: + url: Zhihu URL + + Returns: + Dict with platform, type, and id fields, or None if not matched + """ + # Try question + match = self.ZHIHAU_QUESTION_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "question", + "id": match.group(1) + } + + # Try answer + match = self.ZHIHAU_ANSWER_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "answer", + "id": match.group(1) + } + + # Try user + match = self.ZHIHAU_USER_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "user", + "id": match.group(1) + } + + # Try column + match = self.ZHIHAU_COLUMN_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "column", + "id": match.group(1) + } + + # Try collection + match = self.ZHIHAU_COLLECTION_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "collection", + "id": match.group(1) + } + + # Try zhuanlan article (专栏文章) + match = self.ZHIHAU_ZHUANLAN_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "zhuanlan", + "id": match.group(1) + } + + # Try org page (机构页面) + match = self.ZHIHAU_ORG_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "org", + "id": match.group(1) + } + + # Try org answers (机构回答) + if self.ZHIHAU_ORG_ANSWERS_PATTERN.match(url): + match = self.ZHIHAU_ORG_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "org_answers", + "id": match.group(1) + } + + # Try org zvideos (机构视频) + if self.ZHIHAU_ORG_VIDEOS_PATTERN.match(url): + match = self.ZHIHAU_ORG_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "org_zvideos", + "id": match.group(1) + } + + # Try org asks (机构提问) + if self.ZHIHAU_ORG_ASKS_PATTERN.match(url): + match = self.ZHIHAU_ORG_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "org_asks", + "id": match.group(1) + } + + # Try org posts (机构文章) + if self.ZHIHAU_ORG_POSTS_PATTERN.match(url): + match = self.ZHIHAU_ORG_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "org_posts", + "id": match.group(1) + } + + # Try org pins (机构想法) + if self.ZHIHAU_ORG_PINS_PATTERN.match(url): + match = self.ZHIHAU_ORG_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "org_pins", + "id": match.group(1) + } + + # Try zvideo (知乎视频) + match = self.ZHIHAU_ZVIDEO_PATTERN.match(url) + if match: + return { + "platform": "zhihu", + "type": "zvideo", + "id": match.group(1) + } + + return None + + def extract_xiaohongshu_id(self, url: str) -> Optional[Dict[str, str]]: + """ + Extract Xiaohongshu ID from URL. + + Args: + url: Xiaohongshu URL + + Returns: + Dict with platform, type, and id fields, or None if not matched + """ + # Try short link + match = self.XIAOHONGSHU_SHORT_PATTERN.match(url) + if match: + return { + "platform": "xiaohongshu", + "type": "note", + "id": match.group(1) + } + + # Try explore link + match = self.XIAOHONGSHU_NOTE_PATTERN.match(url) + if match: + return { + "platform": "xiaohongshu", + "type": "note", + "id": match.group(1) + } + + # Try notes link + match = self.XIAOHONGSHU_NOTE_PATTERN2.match(url) + if match: + return { + "platform": "xiaohongshu", + "type": "note", + "id": match.group(1) + } + + # Try discovery item link (resolved from short link) + match = self.XIAOHONGSHU_DISCOVERY_PATTERN.match(url) + if match: + return { + "platform": "xiaohongshu", + "type": "note", + "id": match.group(1) + } + + # Try user profile + match = self.XIAOHONGSHU_USER_PATTERN.match(url) + if match: + return { + "platform": "xiaohongshu", + "type": "user", + "id": match.group(1) + } + + return None + + def parse(self, url: str) -> Dict[str, Any]: + """ + Parse URL and extract platform-specific ID. + + Args: + url: URL to parse + + Returns: + Dict with platform, type, id, and original_url fields + """ + result = { + "platform": None, + "type": None, + "id": None, + "original_url": url, + "resolved_url": None, + "success": False, + "error": None + } + + # First, resolve short links + resolved = self.resolve_shortlink(url) + if resolved: + result["resolved_url"] = resolved + url = resolved + + # Try each platform + bilibili_result = self.extract_bilibili_id(url) + if bilibili_result: + result.update(bilibili_result) + result["success"] = True + return result + + youtube_result = self.extract_youtube_id(url) + if youtube_result: + result.update(youtube_result) + result["success"] = True + return result + + zhihu_result = self.extract_zhihu_id(url) + if zhihu_result: + result.update(zhihu_result) + result["success"] = True + return result + + # Try Xiaohongshu + xiaohongshu_result = self.extract_xiaohongshu_id(url) + if xiaohongshu_result: + result.update(xiaohongshu_result) + result["success"] = True + return result + + # Check for short links that need resolution + short_links = self.shortlink_resolver.detect_short_links(url) + if short_links: + result["error"] = "Short link detected. Please provide the full URL." + return result + + result["error"] = "Unsupported URL format" + return result + + +def format_output(data: Dict[str, Any], output_format: str = "json") -> str: + """Format output based on specified format.""" + if output_format == "json": + return json.dumps(data, ensure_ascii=False, indent=2) + elif output_format == "compact": + return json.dumps(data, ensure_ascii=False, separators=(',', ':')) + elif output_format == "text": + lines = [] + for key, value in data.items(): + if value is not None: + lines.append(f"{key}: {value}") + return "\n".join(lines) + else: + return json.dumps(data, ensure_ascii=False, indent=2) + + +def main(): + """Main entry point.""" + parser = argparse.ArgumentParser( + description="Parse and extract IDs from various platform URLs", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +Examples: + %(prog)s --url "https://www.bilibili.com/video/BV1xx411c7mD" + %(prog)s --url "https://www.youtube.com/watch?v=dQw4w9WgXcQ" + %(prog)s --url "https://www.zhihu.com/question/266309957" + %(prog)s --batch urls.txt --output results.json + """ + ) + + parser.add_argument( + "--url", "-u", + help="Single URL to parse" + ) + + parser.add_argument( + "--batch", "-b", + help="File containing URLs to parse (one per line)" + ) + + parser.add_argument( + "--output", "-o", + help="Output file path (for batch mode)" + ) + + parser.add_argument( + "--format", "-f", + choices=["json", "compact", "text"], + default="json", + help="Output format (default: json)" + ) + + args = parser.parse_args() + + # Check if we're in shortlink help mode + if len(sys.argv) == 2 and sys.argv[1] in ['--help', '-h']: + parser.print_help() + return 0 + + if not args.url and not args.batch: + parser.print_help() + print("\nError: Please provide --url or --batch") + return 1 + + link_parser = LinkParser() + + if args.url: + # Single URL mode + parsed = link_parser.parse(args.url) + + # 统一输出格式 + if parsed["success"]: + output = { + "success": True, + "platform": parsed.get("platform"), + "type": parsed.get("type"), + "id": parsed.get("id"), + "filename": f"{parsed.get('platform')}_{parsed.get('id')}.link.json" if parsed.get("platform") and parsed.get("id") else None, + "message": "URL解析成功" + } + else: + output = { + "success": False, + "error": parsed.get("error", "解析失败"), + "detail": f"URL: {args.url}" + } + + print(json.dumps(output, ensure_ascii=False, indent=2)) + return 0 if output["success"] else 1 + + elif args.batch: + try: + with open(args.batch, 'r', encoding='utf-8') as f: + urls = [line.strip() for line in f if line.strip()] + except Exception as e: + print(json.dumps({ + "success": False, + "error": "读取文件失败", + "detail": str(e) + }, ensure_ascii=False, indent=2)) + return 1 + + results = [] + for url in urls: + parsed = link_parser.parse(url) + if parsed["success"]: + results.append({ + "success": True, + "platform": parsed.get("platform"), + "type": parsed.get("type"), + "id": parsed.get("id"), + "filename": f"{parsed.get('platform')}_{parsed.get('id')}.link.json" if parsed.get("platform") and parsed.get("id") else None + }) + else: + results.append({ + "success": False, + "error": parsed.get("error", "解析失败"), + "detail": f"URL: {url}" + }) + + if args.output: + with open(args.output, 'w', encoding='utf-8') as f: + json.dump(results, f, ensure_ascii=False, indent=2) + print(json.dumps({ + "success": True, + "message": f"结果已保存到 {args.output}", + "total": len(results) + }, ensure_ascii=False, indent=2)) + else: + for result in results: + print(json.dumps(result, ensure_ascii=False, indent=2)) + print("-" * 40) + + return 0 + + +if __name__ == '__main__': + sys.exit(main()) diff --git a/kb-link-parser/link_parser_shortlink.py b/kb-link-parser/link_parser_shortlink.py new file mode 100644 index 0000000..20739e7 --- /dev/null +++ b/kb-link-parser/link_parser_shortlink.py @@ -0,0 +1,296 @@ +#!/usr/bin/env python3 +""" +Short link resolver for link-parser skill. + +Provides utilities for detecting and resolving short links, particularly +Bilibili short links (b23.tv) which may be blocked by anti-scraping measures. + +Supported short link services: +- Bilibili: b23.tv +- Generic URL shorteners (detection only) +""" + +import re +from typing import Optional, Dict, List, Tuple +from urllib.parse import urlparse + + +class ShortLinkResolver: + """Short link detection and resolution handler""" + + # Pattern for Bilibili short links + BILIBILI_SHORT_PATTERN = re.compile(r'https?://b23\.tv/([a-zA-Z0-9]+)') + + # Pattern for other short link services + OTHER_SHORT_PATTERNS = { + 'bit.ly': re.compile(r'https?://bit\.ly/\w+'), + 't.cn': re.compile(r'https?://t\.cn/\w+'), + 'dwz.cn': re.compile(r'https?://dwz\.cn/\w+'), + 'goo.gl': re.compile(r'https?://goo\.gl/\w+'), + 'tinyurl.com': re.compile(r'https?://tinyurl\.com/\w+'), + } + + @staticmethod + def detect_short_links(text: str) -> List[Dict[str, str]]: + """ + Detect short links in text. + + Args: + text: Input text to search + + Returns: + List of detected short links with metadata: + [ + { + 'url': 'https://b23.tv/xxxxx', + 'platform': 'bilibili', + 'is_short': True + }, + ... + ] + """ + detected = [] + + # Check for Bilibili short links + for match in ShortLinkResolver.BILIBILI_SHORT_PATTERN.finditer(text): + detected.append({ + 'url': match.group(0), + 'code': match.group(1), + 'platform': 'bilibili', + 'is_short': True + }) + + # Check for other short link services + for platform, pattern in ShortLinkResolver.OTHER_SHORT_PATTERNS.items(): + for match in pattern.finditer(text): + detected.append({ + 'url': match.group(0), + 'platform': platform, + 'is_short': True + }) + + return detected + + @staticmethod + def is_bilibili_short_link(url: str) -> bool: + """ + Check if URL is a Bilibili short link. + + Args: + url: URL to check + + Returns: + True if URL is a b23.tv short link + """ + return bool(ShortLinkResolver.BILIBILI_SHORT_PATTERN.match(url)) + + @staticmethod + def format_short_link_help(short_link: Optional[str] = None) -> str: + """ + Format help message for short links. + + Args: + short_link: Optional short link URL to mention + + Returns: + Help message + """ + lines = [ + "Detection: Short link", + "" + ] + + if short_link: + lines.append(f"Short link: {short_link}") + lines.append("") + + lines.extend([ + "Due to anti-scraping protection, short links cannot be automatically resolved.", + "Please provide the full URL or the content ID (e.g., BV号 for Bilibili).", + "", + "Full URL format: https://www.bilibili.com/video/BVxxxxx" + ]) + + return "\n".join(lines) + + @staticmethod + def format_short_link_warning(short_links: List[Dict[str, str]]) -> str: + """ + Format warning message for multiple short links. + + Args: + short_links: List of short link metadata + + Returns: + Warning message + """ + if not short_links: + return "" + + lines = [ + "Short links detected:", + "" + ] + + for i, link in enumerate(short_links, 1): + platform = link.get('platform', 'unknown') + url = link['url'] + + if platform == 'bilibili': + lines.append(f" [{i}] Bilibili short link: {url}") + lines.append(" Full URL or BV ID required") + else: + lines.append(f" [{i}] {platform}: {url}") + + lines.append("") + + return "\n".join(lines) + + +class PlaywrightResolver: + """ + Browser-based short link resolver using Playwright. + + This is an optional implementation for environments where Playwright + is available. It can bypass anti-scraping measures by simulating + a real browser. + + Requirements: + pip install playwright + playwright install chromium + """ + + def __init__(self, headless: bool = True, timeout: int = 10000): + """ + Initialize Playwright resolver. + + Args: + headless: Whether to run browser in headless mode + timeout: Page navigation timeout in milliseconds + """ + self.headless = headless + self.timeout = timeout + self._playwright = None + + def _check_playwright_available(self) -> bool: + """Check if Playwright is installed and available""" + try: + from playwright.sync_api import sync_playwright + return True + except ImportError: + return False + + def resolve(self, short_url: str) -> Optional[str]: + """ + Resolve short link using Playwright browser automation. + + Args: + short_url: Short URL to resolve + + Returns: + Final URL after redirects, or None if resolution fails + """ + if not self._check_playwright_available(): + raise ImportError( + "Playwright not installed. Install with: pip install playwright && playwright install chromium" + ) + + from playwright.sync_api import sync_playwright + + try: + with sync_playwright() as p: + # Launch browser + browser = p.chromium.launch(headless=self.headless) + context = browser.new_context( + user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', + viewport={'width': 1920, 'height': 1080} + ) + page = context.new_page() + + # Navigate to short URL + page.goto(short_url, timeout=self.timeout, wait_until='networkidle') + + # Get final URL + final_url = page.url + + # Close browser + browser.close() + + return final_url + + except Exception as e: + print(f"Playwright resolution failed: {e}") + return None + + def resolve_bilibili_short(self, short_url: str) -> Optional[str]: + """ + Resolve Bilibili short link and extract BV ID. + + Args: + short_url: Bilibili short URL (e.g., https://b23.tv/xxxxx) + + Returns: + Full Bilibili URL with BV ID, or None if resolution fails + """ + final_url = self.resolve(short_url) + if not final_url: + return None + + # Check if final URL contains BV ID + if 'bilibili.com/video/' in final_url: + return final_url + + # Extract BV ID if present in URL + bv_pattern = re.compile(r'(BV[a-zA-Z0-9]{10})') + match = bv_pattern.search(final_url) + if match: + return f"https://www.bilibili.com/video/{match.group(1)}" + + return None + + +def get_resolver() -> ShortLinkResolver: + """ + Get the default resolver instance. + + Returns: + ShortLinkResolver instance + """ + return ShortLinkResolver() + + +def detect_short_links(text: str) -> List[Dict[str, str]]: + """ + Detect short links in text. + + Args: + text: Input text to search + + Returns: + List of detected short links with metadata + """ + resolver = ShortLinkResolver() + return resolver.detect_short_links(text) + + +# CLI interface for testing +def main(): + """CLI for testing the short link resolver.""" + import sys + + if len(sys.argv) < 2: + print("Usage: python3 link_parser_shortlink.py 'text to test'") + print("\nExamples:") + print(' python3 link_parser_shortlink.py "Check this: https://b23.tv/oLBZZfK"') + print(' python3 link_parser_shortlink.py "https://bit.ly/xxxxx"') + sys.exit(1) + + text = ' '.join(sys.argv[1:]) + short_links = detect_short_links(text) + + import json + print(json.dumps(short_links, ensure_ascii=False, indent=2)) + + +if __name__ == '__main__': + main() diff --git a/kb-ocr-processor/SKILL.md b/kb-ocr-processor/SKILL.md new file mode 100644 index 0000000..cfd9ef5 --- /dev/null +++ b/kb-ocr-processor/SKILL.md @@ -0,0 +1,66 @@ +# KB OCR Processor Skill + +**kb-ocr-processor** - Extract text from video frames using OCR. + +## Features + +- **视频截帧**: 直接从视频文件截取帧图片 +- **批量处理**: 支持处理帧目录 +- **双引擎**: EasyOCR / Tesseract +- **置信度评分**: 每帧识别结果带置信度 +- **文本合并**: 自动合并所有帧的识别结果 + +## Commands + +```bash +# 方式1: 直接从视频截帧并OCR（推荐） +python ocr_processor.py --video ./video.flv --output ocr.json + +# 方式2: 处理已截取的帧目录 +python ocr_processor.py --input ./frames/ --output ocr.json + +# 指定截帧帧率（默认1帧/秒） +python ocr_processor.py --video ./video.flv --fps 2 --output ocr.json + +# 同时生成合并的文本文件 +python ocr_processor.py --video ./video.flv --output ocr.json --merge + +# 使用 Tesseract 引擎 +python ocr_processor.py --input ./frames/ --engine tesseract --output ocr.json +``` + +## Workflow 中的使用 + +```bash +# 步骤5: OCR处理（视频无字幕时） +python ocr_processor.py --video ${CONTENT_VIDEO_PATH} --output ${CONTENT_DIR}/ocr.json --merge +``` + +## Output + +```json +{ + "success": true, + "engine": "easyocr", + "total_frames": 619, + "results": [ + { + "source": "0001.jpg", + "text": "字幕文字", + "confidence": 0.95 + } + ] +} +``` + +## Installation + +```bash +cp -r kb-ocr-processor/ ~/skills/ +pip install -r requirements.txt + +# 依赖说明 +# - easyocr: 主要OCR引擎（自动下载模型） +# - pytesseract: Tesseract引擎 +# - ffmpeg: 视频截帧（apt install ffmpeg） +``` diff --git a/kb-ocr-processor/ocr_processor.py b/kb-ocr-processor/ocr_processor.py new file mode 100644 index 0000000..b58d618 --- /dev/null +++ b/kb-ocr-processor/ocr_processor.py @@ -0,0 +1,360 @@ +#!/usr/bin/env python3 +""" +OCR Processor - 视频帧文字识别工具 +支持 EasyOCR 和 Tesseract 引擎 +""" + +import argparse +import json +import os +import glob +from pathlib import Path +from typing import List, Dict, Optional +import easyocr +import pytesseract +from PIL import Image + + +class OCRProcessor: + """OCR 文字识别处理器""" + + def __init__(self, engine: str = "easyocr", languages: List[str] = ["ch_sim", "en"]): + """ + 初始化 OCR 处理器 + + Args: + engine: OCR 引擎 ("easyocr" 或 "tesseract") + languages: 语言列表 + """ + self.engine = engine + self.languages = languages + self.reader = None + + if engine == "easyocr": + self.reader = easyocr.Reader(languages, gpu=False) + + def process_image(self, image_path: str) -> Dict: + """ + 处理单张图片进行 OCR 识别 + + Args: + image_path: 图片路径 + + Returns: + 包含 text 和 confidence 的字典 + """ + if not os.path.exists(image_path): + return {"text": "", "confidence": 0.0, "error": "File not found"} + + try: + if self.engine == "easyocr": + return self._process_with_easyocr(image_path) + elif self.engine == "tesseract": + return self._process_with_tesseract(image_path) + else: + return {"text": "", "confidence": 0.0, "error": f"Unknown engine: {self.engine}"} + except Exception as e: + return {"text": "", "confidence": 0.0, "error": str(e)} + + def _process_with_easyocr(self, image_path: str) -> Dict: + """使用 EasyOCR 处理图片""" + results = self.reader.readtext(image_path) + + if not results: + return {"text": "", "confidence": 0.0} + + texts = [] + confidences = [] + + for bbox, text, conf in results: + texts.append(text) + confidences.append(conf) + + merged_text = "\n".join(texts) + avg_confidence = sum(confidences) / len(confidences) if confidences else 0.0 + + return { + "text": merged_text, + "confidence": round(avg_confidence, 4), + "details": [ + {"text": text, "confidence": round(conf, 4)} + for text, conf in zip(texts, confidences) + ] + } + + def _process_with_tesseract(self, image_path: str) -> Dict: + """使用 Tesseract 处理图片""" + image = Image.open(image_path) + text = pytesseract.image_to_string(image, lang="+".join(self.languages)) + + # Tesseract 不直接返回置信度，返回 0.0 + return { + "text": text.strip(), + "confidence": 0.0 + } + + def process_frames(self, input_dir: str, fps: float = 0.1, progress_file: Optional[str] = None) -> List[Dict]: + """ + 处理目录下所有帧图片 + + Args: + input_dir: 帧图片目录 + fps: 采样帧率 + progress_file: 可选，进度文件路径（会实时更新） + + Returns: + OCR 结果列表 + """ + if not os.path.isdir(input_dir): + print(f"Error: Directory not found: {input_dir}") + return [] + + # 支持的图片格式 + image_extensions = ["*.jpg", "*.jpeg", "*.png", "*.bmp", "*.webp"] + image_files = [] + + for ext in image_extensions: + image_files.extend(glob.glob(os.path.join(input_dir, ext))) + image_files.extend(glob.glob(os.path.join(input_dir, "**", ext), recursive=True)) + + # 按文件名排序 + image_files = sorted(image_files) + + if not image_files: + print(f"No images found in {input_dir}") + return [] + + total = len(image_files) + print(f"Found {total} images in {input_dir}") + print(f"Processing with {self.engine} engine...") + + def update_progress(current, status="running", last_result=None): + """更新进度文件""" + if progress_file: + import json + import time + prog = { + "current": current, + "total": total, + "percent": round(current / total * 100, 1) if total > 0 else 0, + "status": status, + "last_result": last_result, + "updated_at": time.strftime("%Y-%m-%d %H:%M:%S") + } + with open(progress_file, 'w', encoding='utf-8') as f: + json.dump(prog, f, ensure_ascii=False, indent=2) + + # 初始化进度 + update_progress(0, "started") + + results = [] + for i, image_path in enumerate(image_files, 1): + basename = os.path.basename(image_path) + print(f"Processing [{i}/{total}]: {basename}") + + ocr_result = self.process_image(image_path) + ocr_result["source"] = basename + + # 记录结果摘要 + text_count = len(ocr_result.get("text", "").split()) if ocr_result.get("text") else 0 + last_result = f"✓ {text_count} 处文字" if ocr_result.get("text") else "✗ 无文字" + + results.append(ocr_result) + + # 实时更新进度 + update_progress(i, "running", last_result) + + # 完成 + update_progress(total, "completed", f"完成 {total} 张") + + print(f"\n✅ Processed {total} frames") + return results + + def merge_texts(self, results: List[Dict]) -> str: + """ + 合并多个 OCR 结果的文本 + + Args: + results: OCR 结果列表 + + Returns: + 合并后的文本 + """ + texts = [] + for result in results: + if result.get("text"): + texts.append(result["text"]) + return "\n\n---\n\n".join(texts) + + def save_results(self, results: List[Dict], output_path: str, merge: bool = False): + """ + 保存 OCR 结果到 JSON 文件 + + Args: + results: OCR 结果列表 + output_path: 输出文件路径 + merge: 是否同时保存合并后的文本文件 + """ + output_data = { + "engine": self.engine, + "total_frames": len(results), + "results": results + } + + # 保存 JSON + with open(output_path, "w", encoding="utf-8") as f: + json.dump(output_data, f, ensure_ascii=False, indent=2) + + print(f"Results saved to {output_path}") + + # 如果需要，同时保存合并的文本 + if merge: + text_path = output_path.replace(".json", ".txt") + merged_text = self.merge_texts(results) + with open(text_path, "w", encoding="utf-8") as f: + f.write(merged_text) + print(f"Merged text saved to {text_path}") + + +def extract_frames(video_path: str, output_dir: str, fps: float = 1.0) -> str: + """ + 使用 ffmpeg 从视频中截取帧图片 + + Args: + video_path: 视频文件路径 + output_dir: 输出目录 + fps: 每秒截取帧数 (默认: 1) + + Returns: + 帧图片目录路径 + """ + import subprocess + + output_dir = Path(output_dir) + output_dir.mkdir(parents=True, exist_ok=True) + + # ffmpeg 命令: -i 输入 -vf fps=fps 输出格式 + cmd = [ + "ffmpeg", "-y", + "-i", video_path, + "-vf", f"fps={fps}", + "-q:v", "2", # 质量等级 (2=高质量) + str(output_dir / "%04d.jpg") + ] + + print(f"🔄 截取视频帧: {video_path}") + print(f" 输出目录: {output_dir}") + + try: + result = subprocess.run(cmd, capture_output=True, text=True) + if result.returncode == 0: + # 统计截取的帧数 + frame_count = len(list(output_dir.glob("*.jpg"))) + print(f"✅ 截取完成: {frame_count} 帧") + return str(output_dir) + else: + print(f"❌ ffmpeg 错误: {result.stderr}") + return "" + except FileNotFoundError: + print("❌ 错误: 未找到 ffmpeg，请先安装: apt install ffmpeg") + return "" + + +def main(): + """命令行入口""" + parser = argparse.ArgumentParser( + description="OCR 视频帧文字识别工具", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +示例: + # 使用 EasyOCR 处理帧目录 + python ocr_processor.py --input ./frames/ --output ./ocr.json + + # 直接从视频截帧并 OCR + python ocr_processor.py --video ./video.flv --output ./ocr.json + + # 使用 Tesseract 处理 + python ocr_processor.py --input ./frames/ --output ./ocr.json --engine tesseract + + # 指定截帧帧率 + python ocr_processor.py --video ./video.flv --output ./ocr.json --fps 2 + + # 同时生成合并的文本文件 + python ocr_processor.py --input ./frames/ --output ./ocr.json --merge + """ + ) + + # 输入源：帧目录 或 视频文件（二选一） + input_group = parser.add_mutually_exclusive_group(required=True) + input_group.add_argument("--input", "-i", help="输入帧图片目录") + input_group.add_argument("--video", "-v", help="输入视频文件（会自动截帧）") + + parser.add_argument("--output", "-o", required=True, help="输出 JSON 文件路径") + parser.add_argument("--fps", "-f", type=float, default=1.0, help="截帧帧率 (默认: 1帧/秒)") + parser.add_argument("--engine", "-e", choices=["easyocr", "tesseract"], + default="easyocr", help="OCR 引擎 (默认: easyocr)") + parser.add_argument("--merge", action="store_true", help="同时保存合并的文本文件") + parser.add_argument("--languages", "-l", nargs="+", + default=["ch_sim", "en"], help="语言列表") + parser.add_argument("--progress", "-p", help="可选：进度文件路径（会实时更新）") + + args = parser.parse_args() + + # 如果指定了视频文件，先截帧 + input_dir = args.input + if args.video: + if not os.path.exists(args.video): + print(json.dumps({ + "success": False, + "error": f"视频文件不存在: {args.video}" + }, ensure_ascii=False, indent=2)) + return 1 + + # 创建临时帧目录 + frames_dir = Path(args.video).stem + "_frames" + input_dir = extract_frames(args.video, frames_dir, fps=args.fps) + + if not input_dir: + print(json.dumps({ + "success": False, + "error": "截帧失败" + }, ensure_ascii=False, indent=2)) + return 1 + + # 初始化处理器 + processor = OCRProcessor(engine=args.engine, languages=args.languages) + + # 处理帧 + results = processor.process_frames(input_dir, fps=args.fps, progress_file=args.progress) + + if results: + # 保存结果 + processor.save_results(results, args.output, merge=args.merge) + + # 统一输出格式 + total_texts = sum(1 for r in results if r.get("text")) + avg_conf = sum(r.get("confidence", 0) for r in results) / len(results) if results else 0 + + output = { + "success": True, + "filename": Path(args.output).name, + "filepath": str(Path(args.output).resolve()), + "message": f"OCR处理完成", + "stats": { + "total_frames": len(results), + "frames_with_text": total_texts, + "avg_confidence": round(avg_conf, 4) + } + } + print(json.dumps(output, ensure_ascii=False, indent=2)) + return 0 + else: + print(json.dumps({ + "success": False, + "error": "未处理到任何结果" + }, ensure_ascii=False, indent=2)) + return 1 + + +if __name__ == "__main__": + exit(main()) diff --git a/kb-ocr-processor/requirements.txt b/kb-ocr-processor/requirements.txt new file mode 100644 index 0000000..f3f72c2 --- /dev/null +++ b/kb-ocr-processor/requirements.txt @@ -0,0 +1,3 @@ +easyocr>=1.7.0 +pytesseract>=0.3.10 +Pillow>=9.0.0 diff --git a/kb-whisper-diarization/.env.example b/kb-whisper-diarization/.env.example new file mode 100644 index 0000000..108647b --- /dev/null +++ b/kb-whisper-diarization/.env.example @@ -0,0 +1,9 @@ +# KB Whisper Diarization 环境变量 + +# Whisper.cpp 安装路径 +WHISPER_CPP_PATH=~/whisper.cpp + +# HuggingFace Token（必需，用于下载 pyannote 模型） +# 获取方式: https://huggingface.co/settings/tokens +# 注意: 需要先申请 pyannote/speaker-diarization 模型访问权限 +HF_TOKEN=hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx diff --git a/kb-whisper-diarization/SKILL.md b/kb-whisper-diarization/SKILL.md new file mode 100644 index 0000000..4f705d7 --- /dev/null +++ b/kb-whisper-diarization/SKILL.md @@ -0,0 +1,127 @@ +# KB Whisper Diarization Skill + +**kb-whisper-diarization** - 使用 Whisper + pyannote.audio 实现语音识别和说话者分离。 + +## 什么时候使用 + +当用户需要： +- 区分多个说话者（如访谈、对话） +- 获取带说话者标签的字幕 +- 分析对话中谁说了什么 + +## 环境变量 + +在使用之前，必须检查环境变量是否已经设置。 + +| 变量名 | 用途 | 示例 | +|--------|------|------| +| `WHISPER_CPP_PATH` | whisper.cpp 安装路径 | `~/whisper.cpp` | +| `HF_TOKEN` | HuggingFace Token | `hf_xxx...` | + +### 获取 HuggingFace Token + +pyannote.audio 需要从 HuggingFace 下载模型，需要先： +1. 注册 HuggingFace 账号：https://huggingface.co +2. 申请模型访问权限：https://huggingface.co/pyannote/speaker-diarization +3. 创建 Token：https://huggingface.co/settings/tokens + +## 使用方法 + +```bash +# 基本用法（带说话者分离） +python whisper_diarization.py --input video.mp4 + +# 说话者分离 +python whisper_diarization.py --input interview.mp4 --diarize + +# 指定说话者数量 +python whisper_diarization.py --input meeting.mp4 --diarize --num-speakers 2 + +# 指定语言 +python whisper_diarization.py --input video.mp4 --language zh +``` + +## 命令参数 + +| 参数 | 说明 | 默认值 | +|------|------|--------| +| `--input` | 输入音视频文件路径 | 必需 | +| `--output` | 输出目录 | 文件所在目录 | +| `--diarize` | 启用说话者分离 | False | +| `--num-speakers` | 估计说话者数量 | None（自动检测） | +| `--language` | 语言 | 自动检测 | +| `--model` | Whisper 模型 | base | +| `--background` | 后台异步执行 | False | + +## 模型选项 + +- **Whisper 模型**: tiny, base, small, medium, large +- **说话者分离**: pyannote/speaker-diarization (需申请权限) + +## 输出文件 + +对于输入 `interview.mp4`，将生成： + +- `interview.mp4.json` - 完整结果（包含说话者标签） +- `interview.mp4.txt` - 纯文本 +- `interview.mp4.srt` - 字幕格式（带说话者标签） + +## 输出格式示例 + +### JSON 格式 + +```json +{ + "success": true, + "input_file": "interview.mp4", + "diarization": true, + "speakers": ["SPEAKER_00", "SPEAKER_01"], + "segments": [ + { + "id": 0, + "speaker": "SPEAKER_00", + "start": 0.0, + "end": 5.2, + "text": "大家好，欢迎来到访谈节目" + }, + { + "id": 1, + "speaker": "SPEAKER_01", + "start": 5.2, + "end": 10.8, + "text": "谢谢邀请，我很荣幸" + } + ] +} +``` + +### SRT 字幕格式 + +``` +1 +00:00:00,000 --> 00:00:05,200 +[SPEAKER_00] 大家好，欢迎来到访谈节目 + +2 +00:00:05,200 --> 00:00:10,800 +[SPEAKER_01] 谢谢邀请，我很荣幸 +``` + +## 安装 + +```bash +# 1. 安装依赖 +pip install pyannote.audio torch + +# 2. 设置 HuggingFace Token +export HF_TOKEN="hf_xxx..." + +# 3. 首次运行会自动下载模型 +python whisper_diarization.py --input test.mp4 +``` + +## 注意事项 + +- **说话者分离需要申请权限**: https://huggingface.co/pyannote/speaker-diarization +- **处理时间较长**: 说话者分离会增加处理时间 +- **对立体声效果更好**: 多声道音频的分离效果更佳 diff --git a/kb-whisper-diarization/requirements.txt b/kb-whisper-diarization/requirements.txt new file mode 100644 index 0000000..d465929 --- /dev/null +++ b/kb-whisper-diarization/requirements.txt @@ -0,0 +1,8 @@ +# KB Whisper Diarization 依赖 + +# 核心依赖 +torch>=2.0.0 +pyannote.audio>=1.0.0 + +# 可选: GPU 加速 +# torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 diff --git a/kb-whisper-diarization/whisper_diarization.py b/kb-whisper-diarization/whisper_diarization.py new file mode 100644 index 0000000..805fb4c --- /dev/null +++ b/kb-whisper-diarization/whisper_diarization.py @@ -0,0 +1,339 @@ +#!/usr/bin/env python3 +""" +KB Whisper Diarization - 语音识别 + 说话者分离 +使用 Whisper 进行语音识别，pyannote.audio 进行说话者分离 +""" + +import argparse +import json +import os +import subprocess +import sys +import tempfile +from datetime import datetime +from pathlib import Path +import re + + +def parse_arguments(): + """解析命令行参数""" + parser = argparse.ArgumentParser( + description='KB Whisper Diarization - 语音识别 + 说话者分离', + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +示例: + python whisper_diarization.py --input video.mp4 + python whisper_diarization.py --input interview.mp4 --diarize + python whisper_diarization.py --input meeting.mp4 --diarize --num-speakers 2 + """ + ) + parser.add_argument('--input', required=True, help='输入音视频文件路径') + parser.add_argument('--output', help='输出目录 (默认: 文件所在目录)') + parser.add_argument('--diarize', action='store_true', help='启用说话者分离') + parser.add_argument('--num-speakers', type=int, help='估计说话者数量') + parser.add_argument('--language', help='指定语言 (默认: 自动检测)') + parser.add_argument('--model', default='base', choices=['tiny', 'base', 'small', 'medium', 'large'], + help='Whisper 模型 (默认: base)') + parser.add_argument('--background', action='store_true', help='后台异步执行') + return parser.parse_args() + + +def get_whisper_path(): + """获取 whisper.cpp 路径""" + path = os.environ.get('WHISPER_CPP_PATH') + if path: + path = os.path.expanduser(path) + if os.path.exists(path): + return path + return os.path.expanduser('~/whisper.cpp') + + +def check_whisper_model(whisper_path, model): + """检查 Whisper 模型""" + model_path = os.path.join(whisper_path, 'models', f'ggml-{model}.bin') + if not os.path.exists(model_path): + raise FileNotFoundError(f"Whisper 模型不存在: {model_path}") + return model_path + + +def convert_to_wav(input_path, output_dir): + """转换为 16kHz WAV""" + if input_path.lower().endswith('.wav'): + try: + result = subprocess.run( + ['ffprobe', '-v', 'error', '-show_entries', 'stream=sample_rate', + '-of', 'default=noprint_wrappers=1:nokey=1', input_path], + capture_output=True, text=True + ) + if result.returncode == 0 and int(result.stdout.strip()) == 16000: + return input_path + except Exception: + pass + + output_path = os.path.join(output_dir, f"{Path(input_path).stem}_audio.wav") + print(f"转换音频: {input_path} -> {output_path}") + + subprocess.run([ + 'ffmpeg', '-y', '-i', input_path, + '-acodec', 'pcm_s16le', '-ar', '16000', '-ac', '1', + '-loglevel', 'error', output_path + ], check=True, capture_output=True) + + print("✓ 音频转换完成") + return output_path + + +def run_whisper(whisper_path, audio_path, model, output_dir, language=None): + """运行 Whisper 识别""" + basename = Path(audio_path).stem.replace('_audio', '') + output_file = os.path.join(output_dir, basename) + + cmd = [ + os.path.join(whisper_path, 'whisper-cli'), + '-m', os.path.join(whisper_path, 'models', f'ggml-{model}.bin'), + '-f', audio_path, + '-of', output_file, + '-l', language or 'auto', + '--output-txt', '--output-srt', '--output-json', + ] + + print(f"执行 Whisper: {' '.join(cmd[:6])} ...") + + result = subprocess.run( + cmd, capture_output=True, text=True, cwd=whisper_path, timeout=3600 + ) + + if result.returncode != 0 and not os.path.exists(f"{output_file}.txt"): + raise RuntimeError(f"Whisper 失败: {result.stderr}") + + return basename + + +def run_diarization(audio_path, num_speakers=None): + """运行 pyannote.audio 说话者分离""" + print("\n🎙️ 步骤2: 说话者分离...") + + try: + import torch + from pyannote.audio import Pipeline + except ImportError as e: + print(f"✗ 缺少依赖: {e}") + print("请安装: pip install pyannote.audio torch") + raise + + # 检查 HuggingFace Token + hf_token = os.environ.get('HF_TOKEN') + if not hf_token: + raise RuntimeError("需要设置 HF_TOKEN 环境变量\n" + "获取方式: https://huggingface.co/settings/tokens") + + # 新版 pyannote 需要先登录 + from huggingface_hub import login + print("登录 HuggingFace...") + login(token=hf_token) + + print("加载 pyannote 流水线...") + pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization") + + # 设置设备 + device = torch.device("cuda" if torch.cuda.is_available() else "cpu") + print(f"使用设备: {device}") + pipeline.to(device) + + # 运行分离 + print("执行说话者分离...") + diarization = pipeline( + audio_path, + num_speakers=num_speakers + ) + + # 解析结果 + speakers = {} + for turn, _, speaker in diarization.itertracks(yield_label=True): + if speaker not in speakers: + speakers[speaker] = [] + speakers[speaker].append({ + "start": round(turn.start, 2), + "end": round(turn.end, 2) + }) + + print(f"✓ 检测到 {len(speakers)} 个说话者: {list(speakers.keys())}") + return speakers + + +def merge_results(whisper_txt, whisper_srt, diarization, output_dir, basename): + """合并 Whisper 和说话者分离结果""" + print("\n📝 步骤3: 合并结果...") + + # 读取 Whisper 文本 + text_segments = [] + if os.path.exists(whisper_txt): + with open(whisper_txt, 'r', encoding='utf-8') as f: + content = f.read() + + # 简单按行分段 + for i, line in enumerate(content.strip().split('\n')): + if line.strip(): + text_segments.append({ + "id": i, + "text": line.strip(), + "start": i * 3.0, # 估算 + "end": (i + 1) * 3.0 + }) + + # 读取 SRT 获取精确时间 + srt_segments = [] + if os.path.exists(whisper_srt): + with open(whisper_srt, 'r', encoding='utf-8') as f: + content = f.read() + + # 解析 SRT + pattern = r'(\d+)\n(\d{2}:\d{2}:\d{2},\d{3}) --> (\d{2}:\d{2}:\d{2},\d{3})\n(.+?)(?=\n\n|\Z)' + matches = re.findall(pattern, content, re.DOTALL) + + def parse_time(t): + h, m, s_ms = t.split(':') + s, ms = s_ms.split(',') + return float(h) * 3600 + float(m) * 60 + float(s) + float(ms) / 1000 + + for idx, num, start, end, text in matches: + srt_segments.append({ + "id": int(idx), + "start": parse_time(start), + "end": parse_time(end), + "text": text.strip() + }) + + # 为每个 Whisper 段落分配说话者 + merged_segments = [] + for seg in srt_segments: + speaker = assign_speaker(seg['start'], seg['end'], diarization) + merged_segments.append({ + "id": len(merged_segments), + "speaker": speaker, + "start": seg['start'], + "end": seg['end'], + "text": seg['text'] + }) + + # 生成带说话者的 SRT + output_srt = os.path.join(output_dir, f"{basename}_diarized.srt") + with open(output_srt, 'w', encoding='utf-8') as f: + for seg in merged_segments: + start = format_time(seg['start']) + end = format_time(seg['end']) + f.write(f"{seg['id'] + 1}\n") + f.write(f"{start} --> {end}\n") + f.write(f"[{seg['speaker']}] {seg['text']}\n\n") + + # 生成合并的 TXT + output_txt = os.path.join(output_dir, f"{basename}_diarized.txt") + with open(output_txt, 'w', encoding='utf-8') as f: + for seg in merged_segments: + f.write(f"[{seg['speaker']}] {seg['text']}\n") + + # 生成 JSON + output_json = os.path.join(output_dir, f"{basename}_diarized.json") + json_data = { + "success": True, + "tool": "whisper-diarization", + "diarization": True, + "speakers": list(diarization.keys()), + "input_file": basename, + "output_files": { + "txt": f"{basename}_diarized.txt", + "srt": f"{basename}_diarized.srt", + "json": f"{basename}_diarized.json" + }, + "segments": merged_segments + } + with open(output_json, 'w', encoding='utf-8') as f: + json.dump(json_data, f, ensure_ascii=False, indent=2) + + print(f"✓ 生成文件:") + print(f" - {output_srt}") + print(f" - {output_txt}") + print(f" - {output_json}") + + return json_data + + +def assign_speaker(start, end, diarization): + """将时间段分配给说话者""" + best_speaker = "UNKNOWN" + max_overlap = 0 + + for speaker, segments in diarization.items(): + for seg in segments: + overlap = min(end, seg['end']) - max(start, seg['start']) + if overlap > max_overlap: + max_overlap = overlap + best_speaker = speaker + + return best_speaker + + +def format_time(seconds): + """秒数转换为 SRT 时间格式""" + hours = int(seconds // 3600) + minutes = int((seconds % 3600) // 60) + secs = int(seconds % 60) + ms = int((seconds % 1) * 1000) + return f"{hours:02d}:{minutes:02d}:{secs:02d},{ms:03d}" + + +def main(): + args = parse_arguments() + + input_file = os.path.abspath(args.input) + if not os.path.exists(input_file): + print(f"✗ 文件不存在: {input_file}") + sys.exit(1) + + output_dir = os.path.abspath(args.output) if args.output else os.path.dirname(input_file) + os.makedirs(output_dir, exist_ok=True) + + basename = Path(input_file).stem + + print(f"\n📁 输入: {input_file}") + print(f"📁 输出: {output_dir}") + print(f"🎙️ 说话者分离: {'是' if args.diarize else '否'}") + + try: + # 步骤1: Whisper 识别 + print(f"\n🎙️ 步骤1: 语音识别...") + whisper_path = get_whisper_path() + check_whisper_model(whisper_path, args.model) + + audio_path = convert_to_wav(input_file, output_dir) + run_whisper(whisper_path, audio_path, args.model, output_dir, args.language) + + # 步骤2: 说话者分离 + if args.diarize: + diarization = run_diarization(audio_path, args.num_speakers) + else: + diarization = {} + + # 步骤3: 合并结果 + whisper_txt = os.path.join(output_dir, f"{basename}.txt") + whisper_srt = os.path.join(output_dir, f"{basename}.srt") + result = merge_results(whisper_txt, whisper_srt, diarization, output_dir, basename) + + # 清理临时音频 + if audio_path != input_path and audio_path.endswith('_audio.wav'): + try: + os.remove(audio_path) + except Exception: + pass + + print(f"\n✅ 处理完成!") + print(f" 说话者数量: {len(diarization) if args.diarize else 1}") + print(f" 段落数量: {len(result['segments'])}") + + except Exception as e: + print(f"\n✗ 错误: {e}") + sys.exit(1) + + +if __name__ == '__main__': + main() diff --git a/kb-whisper/.env.example b/kb-whisper/.env.example new file mode 100644 index 0000000..8ffc440 --- /dev/null +++ b/kb-whisper/.env.example @@ -0,0 +1,5 @@ +# KB Whisper 环境变量配置示例 +# 复制此文件为 .env 并填写实际值 + +# Whisper.cpp 安装路径 +WHISPER_CPP_PATH=~/whisper.cpp diff --git a/kb-whisper/README.md b/kb-whisper/README.md new file mode 100644 index 0000000..7b84ea8 --- /dev/null +++ b/kb-whisper/README.md @@ -0,0 +1,211 @@ +# KB Whisper - 本地语音识别 + +基于 Whisper.cpp 的本地语音识别工具，支持将音视频文件转换为文本、字幕和 JSON 格式。 + +## 功能特性 + +- 🎯 **本地执行** - 完全离线运行，保护隐私 +- 🚀 **多模型支持** - 从 tiny 到 large，根据需求选择速度/精度 +- 📝 **多格式输出** - JSON、SRT、TXT 三种格式 +- ⚡ **异步执行** - 支持后台运行，不阻塞主代理 +- 🎬 **广泛兼容** - 支持常见音视频格式（MP3、MP4、WAV 等） + +## 安装前提 + +### 1. 安装 whisper.cpp + +```bash +# 克隆仓库 +git clone https://github.com/ggerganov/whisper.cpp.git ~/whisper.cpp + +# 编译 +cd ~/whisper.cpp +make + +# 下载模型（至少需要一个模型） +./models/download-ggml-model.sh tiny +./models/download-ggml-model.sh base # 可选 +``` + +### 2. 配置环境变量 + +在 `~/.clawdbot/clawdbot.json` 中添加： + +```json5 +{ + skills: { + entries: { + "kb-whisper": { + env: { + WHISPER_CPP_PATH: "~/whisper.cpp" + } + } + } + } +} +``` + +或通过命令行配置： + +```bash +clawdbot skills config kb-whisper WHISPER_CPP_PATH "~/whisper.cpp" +``` + +## 使用方法 + +### 基本用法 + +```bash +# 使用默认 tiny 模型处理 +python whisper.py --input video.mp4 + +# 使用 base 模型（推荐，平衡速度和精度） +python whisper.py --input video.mp4 --model base + +# 后台异步执行 +python whisper.py --input video.mp4 --background +``` + +### 指定输出目录 + +```bash +python whisper.py --input video.mp4 --output ./transcripts +``` + +### 处理音频文件 + +```bash +python whisper.py --input podcast.mp3 --model base +``` + +## 输出文件 + +对于输入 `video.mp4`，将生成以下文件： + +``` +output/ +├── video.json # 详细结果（含时间戳） +├── video.srt # 字幕格式 +└── video.txt # 纯文本 +``` + +### JSON 格式 + +```json +{ + "success": true, + "input_file": "video.mp4", + "model": "base", + "output_files": { + "json": "video.json", + "srt": "video.srt", + "txt": "video.txt" + }, + "duration_seconds": 120.5, + "segments": [ + { + "id": 0, + "start": 0.0, + "end": 3.2, + "text": "这是第一段字幕" + }, + { + "id": 1, + "start": 3.2, + "end": 6.8, + "text": "这是第二段字幕" + } + ] +} +``` + +## 模型对比 + +| 模型 | 速度 | 精度 | 适用场景 | +|------|------|------|----------| +| tiny | ⚡⚡⚡ | ⭐ | 快速预览、实时转录 | +| base | ⚡⚡ | ⭐⭐⭐ | 日常使用（推荐） | +| small | ⚡ | ⭐⭐⭐⭐ | 高质量需求 | +| medium | ⭐ | ⭐⭐⭐⭐⭐ | 专业用途 | +| large | 🐢 | ⭐⭐⭐⭐⭐ | 最高精度要求 | + +## 完整示例 + +### 示例 1: 转录播客 + +```bash +python whisper.py --input podcast.mp3 --model base --background +``` + +### 示例 2: 生成视频字幕 + +```bash +python whisper.py --input tutorial.mp4 --model small +``` + +### 示例 3: 批量处理（配合脚本） + +```bash +#!/bin/bash +for video in videos/*.mp4; do + python whisper.py --input "$video" --model base +done +``` + +## 在 Workflow 中使用 + +在知识库处理流程中，如果视频没有字幕： + +```bash +# 步骤4: 下载视频后，如果没有字幕 +# 步骤5: 使用 Whisper 生成字幕 +python whisper.py --input ${video_path} --model base --background + +# 等待 Whisper 完成，然后继续后续步骤 +``` + +## 技术细节 + +- **引擎**: Whisper.cpp（C++ 实现，性能优异） +- **音频采样率**: 自动转换为 16kHz +- **语言**: 自动检测（支持 99 种语言） +- **GPU 支持**: whisper.cpp 支持 CUDA 加速（需编译时启用） + +## 故障排查 + +### 问题: 找不到 whisper.cpp + +```bash +# 检查环境变量 +echo $WHISPER_CPP_PATH + +# 手动测试 +~/whisper.cpp/main --help +``` + +### 问题: 模型未下载 + +```bash +cd ~/whisper.cpp +./models/download-ggml-model.sh tiny +``` + +### 问题: 音频格式不支持 + +```bash +# 转换音频格式 +ffmpeg -i input.avi -acodec libmp3lame output.mp3 +python whisper.py --input output.mp3 +``` + +## 性能参考 + +在 CPU 环境下（Intel i7）： + +- **tiny 模型**: ~1x 实时速度（1分钟音频 ~1分钟处理） +- **base 模型**: ~0.5x 实时速度（1分钟音频 ~2分钟处理） +- **small 模型**: ~0.25x 实时速度（1分钟音频 ~4分钟处理） + +## 许可证 + +本技能使用 MIT 许可证，Whisper.cpp 使用 MIT 许可证。 diff --git a/kb-whisper/SKILL.md b/kb-whisper/SKILL.md new file mode 100644 index 0000000..9ebb999 --- /dev/null +++ b/kb-whisper/SKILL.md @@ -0,0 +1,124 @@ +--- +name: kb-whisper +description: 本地语音识别，支持音视频转文字（基于 Whisper.cpp） +--- + +# KB Whisper Skill + +**kb-whisper** - 本地语音识别，使用 Whisper.cpp 将音视频文件转换为文本、字幕和 JSON 格式输出。 + +## 什么时候使用 + +当用户需要： +- 将视频/音频文件转换为文字 +- 生成视频字幕（SRT 格式） +- 获取带时间戳的详细识别结果 + +## 环境变量 + +在使用之前，必须检查环境变量是否已经设置。 + +| 变量名 | 用途 | 示例 | +|--------|------|------| +| `WHISPER_CPP_PATH` | whisper.cpp 安装路径 | `~/whisper.cpp` | + +## 使用方法 + +```bash +# 基本用法 +python whisper.py --input video.mp4 + +# 指定模型（默认 tiny） +python whisper.py --input video.mp4 --model base + +# 指定输出目录 +python whisper.py --input video.mp4 --output ./output + +# 异步执行（推荐） +python whisper.py --input video.mp4 --background +``` + +## 命令参数 + +| 参数 | 说明 | 默认值 | +|------|------|--------| +| `--input` | 输入音视频文件路径 | 必需 | +| `--model` | Whisper 模型类型 | `tiny` | +| `--output` | 输出目录 | 文件所在目录 | +| `--background` | 后台异步执行 | False | + +## 模型选项 + +- `tiny` - 最小模型，速度快，精度较低（推荐快速识别） +- `base` - 基础模型，平衡速度和精度（推荐） +- `small` - 小型模型，精度更高，速度较慢 +- `medium` - 中型模型，高精度 +- `large` - 大型模型，最高精度，速度慢 + +## 输出文件 + +对于输入 `video.mp4`，将生成： + +- `video.json` - 详细结果（包含时间戳、分段信息） +- `video.srt` - 字幕格式文件 +- `video.txt` - 纯文本内容 + +## 输出格式示例 + +### JSON 格式 + +```json +{ + "success": true, + "input_file": "video.mp4", + "model": "tiny", + "output_files": { + "json": "video.json", + "srt": "video.srt", + "txt": "video.txt" + }, + "duration_seconds": 120.5, + "segments": [ + { + "id": 0, + "start": 0.0, + "end": 3.2, + "text": "这是第一段字幕" + } + ] +} +``` + +## Workflow 中的使用 + +```bash +# 步骤4之后：如果已有音频但无字幕，可以使用 whisper +python whisper.py --input ${video_path} --model base --background +``` + +## 安装 + +```bash +# 1. 克隆 whisper.cpp +git clone https://github.com/ggerganov/whisper.cpp.git ~/whisper.cpp + +# 2. 编译 +cd ~/whisper.cpp +make + +# 3. 下载模型（tiny） +./models/download-ggml-model.sh tiny + +# 4. 下载更多模型（可选） +# ./models/download-ggml-model.sh base +# ./models/download-ggml-model.sh small + +# 5. 复制技能到 skills 目录 +cp -r kb-whisper/ ~/skills/ +``` + +## 注意事项 + +- **异步执行**: 使用 `--background` 参数时，命令会在后台运行，不阻塞主代理 +- **模型选择**: tiny 模型适合快速识别，base 模型适合一般用途，large 模型适合高精度需求 +- **文件格式**: 支持 MP3、MP4、WAV、FLAC、OGG、M4A 等常见格式 diff --git a/kb-whisper/__pycache__/whisper.cpython-312.pyc b/kb-whisper/__pycache__/whisper.cpython-312.pyc new file mode 100644 index 0000000..c605169 Binary files /dev/null and b/kb-whisper/__pycache__/whisper.cpython-312.pyc differ diff --git a/kb-whisper/examples.md b/kb-whisper/examples.md new file mode 100644 index 0000000..02905d0 --- /dev/null +++ b/kb-whisper/examples.md @@ -0,0 +1,273 @@ +# KB Whisper 使用示例 + +## 快速开始 + +### 1. 基础使用 + +```bash +# 使用默认 tiny 模型转录视频 +python whisper.py --input video.mp4 + +# 使用 base 模型（推荐） +python whisper.py --input video.mp4 --model base +``` + +### 2. 异步执行 + +```bash +# 后台处理，不阻塞主代理 +python whisper.py --input video.mp4 --model base --background +``` + +### 3. 指定输出目录 + +```bash +python whisper.py --input video.mp4 --output ./transcripts +``` + +### 4. 指定语言 + +```bash +# 指定中文 +python whisper.py --input video.mp4 --language zh + +# 指定英文 +python whisper.py --input video.mp4 --language en + +# 指定日语 +python whisper.py --input video.mp4 --language ja +``` + +## 实际应用场景 + +### 场景 1: 转录播客 + +```bash +python whisper.py --input podcast.mp3 --model base --background +``` + +**输出**: +- `podcast.json` - 带时间戳的详细结果 +- `podcast.srt` - 字幕格式 +- `podcast.txt` - 纯文本 + +### 场景 2: 生成视频字幕 + +```bash +python whisper.py --input tutorial.mp4 --model small +``` + +**用途**: +- 为教程视频生成字幕 +- 导出 SRT 文件到视频编辑软件 +- 生成多语言字幕版本 + +### 场景 3: 会议录音转文字 + +```bash +python whisper.py --input meeting.mp3 --model base --output ./meetings +``` + +**输出示例**: +``` +meetings/ +├── meeting.json # 完整 JSON（含时间戳） +├── meeting.srt # 字幕格式 +└── meeting.txt # 纯文本 +``` + +### 场景 4: 批量处理 + +创建脚本 `batch_transcribe.sh`: + +```bash +#!/bin/bash + +OUTPUT_DIR="./transcripts" +mkdir -p "$OUTPUT_DIR" + +for video in videos/*.mp4; do + echo "处理: $video" + python whisper.py --input "$video" --output "$OUTPUT_DIR" --model base +done + +echo "批量处理完成!" +``` + +```bash +chmod +x batch_transcribe.sh +./batch_transcribe.sh +``` + +## 在 Workflow 中使用 + +### 知识库处理流程 + +在 `kb-workflow` 技能中，如果视频没有字幕： + +```bash +# 步骤 4: 下载视频后 +# 检查是否有字幕文件 +if [ ! -f "${subtitle_file}" ]; then + echo "无字幕文件，使用 Whisper 生成..." + + # 使用 Whisper 生成字幕（后台执行） + python /path/to/whisper.py \ + --input "${video_path}" \ + --model base \ + --output "${content_dir}" \ + --background + + # 等待 Whisper 完成 + sleep 5 # 等待后台任务启动 + while ! [ -f "${content_dir}/$(basename ${video_path} .mp4).srt" ]; do + sleep 2 + done + + echo "Whisper 处理完成" +fi +``` + +## 输出文件使用 + +### JSON 格式 + +```python +import json + +# 读取 JSON 结果 +with open('video.json', 'r', encoding='utf-8') as f: + data = json.load(f) + +# 访问分段 +for segment in data['segments']: + print(f"[{segment['start']:.2f}-{segment['end']:.2f}] {segment['text']}") +``` + +### SRT 格式 + +```bash +# 直接在视频播放器中使用 +mpv video.mp4 --sub-file=video.srt + +# 或转换字幕格式 +ffmpeg -i video.srt video.ass +``` + +### TXT 格式 + +```bash +# 搜索关键词 +grep "重要信息" video.txt + +# 统计字数 +wc -m video.txt +``` + +## 性能优化建议 + +### 1. 根据内容选择模型 + +```bash +# 快速预览（短视频、测试） +python whisper.py --input video.mp4 --model tiny + +# 日常使用（播客、会议） +python whisper.py --input video.mp4 --model base + +# 高质量需求（正式内容、多语言） +python whisper.py --input video.mp4 --model small +``` + +### 2. 使用后台执行 + +```bash +# 处理长文件时使用后台模式 +python whisper.py --input long_video.mp4 --model base --background +``` + +### 3. 指定语言提升准确度 + +```bash +# 如果知道内容语言，指定后准确度更高 +python whisper.py --input video.mp4 --language zh +``` + +## 故障排查 + +### 问题 1: whisper.cpp 未找到 + +```bash +# 检查环境变量 +echo $WHISPER_CPP_PATH + +# 或配置 +clawdbot skills config kb-whisper WHISPER_CPP_PATH "~/whisper.cpp" +``` + +### 问题 2: 模型未下载 + +```bash +cd ~/whisper.cpp +./models/download-ggml-model.sh base +``` + +### 问题 3: 音频格式不支持 + +```bash +# 转换格式 +ffmpeg -i input.avi -acodec libmp3lame output.mp3 +python whisper.py --input output.mp3 +``` + +### 问题 4: 后台任务未完成 + +```bash +# 查看日志 +cat video_whisper.log + +# 检查进程 +ps aux | grep whisper +``` + +## 集成到其他工具 + +### 集成到 Python 脚本 + +```python +import subprocess +import json + +def transcribe_audio(audio_path, model='base'): + """调用 whisper.py 转录音频""" + cmd = [ + 'python3', '/path/to/whisper.py', + '--input', audio_path, + '--model', model + ] + + result = subprocess.run(cmd, capture_output=True, text=True) + return json.loads(result.stdout) + +# 使用 +result = transcribe_audio('podcast.mp3', 'base') +print(f"识别到 {result['total_segments']} 个片段") +``` + +### 集成到 Shell 脚本 + +```bash +#!/bin/bash + +transcribe() { + local file=$1 + local model=${2:-base} + + echo "转录: $file" + python3 whisper.py --input "$file" --model "$model" --background +} + +# 批量处理 +transcribe "video1.mp4" +transcribe "video2.mp4" "tiny" +``` diff --git a/kb-whisper/whisper.py b/kb-whisper/whisper.py new file mode 100644 index 0000000..4d95f3a --- /dev/null +++ b/kb-whisper/whisper.py @@ -0,0 +1,403 @@ +#!/usr/bin/env python3 +""" +KB Whisper - 本地语音识别工具 +基于 Whisper.cpp 的音视频转文字 + +功能： +- 自动将视频/音频转换为 16kHz WAV 格式 +- 支持指定语言（默认中文） +- 输出标准 JSON 格式供 KB Workflow 使用 +""" + +import argparse +import json +import os +import subprocess +import sys +import tempfile +from pathlib import Path +import re + + +def parse_arguments(): + """解析命令行参数""" + parser = argparse.ArgumentParser( + description='KB Whisper - 本地语音识别工具', + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +示例: + python whisper.py --input video.mp4 + python whisper.py --input video.mp4 --model base + python whisper.py --input video.mp4 --output ./output --background + """ + ) + parser.add_argument( + '--input', + required=True, + help='输入音视频文件路径' + ) + parser.add_argument( + '--model', + default='base', + choices=['tiny', 'base', 'small', 'medium', 'large'], + help='Whisper 模型类型 (默认: base)' + ) + parser.add_argument( + '--output', + help='输出目录 (默认: 输入文件所在目录)' + ) + parser.add_argument( + '--background', + action='store_true', + help='后台异步执行' + ) + parser.add_argument( + '--language', + default='zh', + help='指定语言 (默认: zh)，例如: en, zh, ja' + ) + + return parser.parse_args() + + +def get_whisper_cpp_path(): + """获取 whisper.cpp 路径""" + # 优先从环境变量获取 + path = os.environ.get('WHISPER_CPP_PATH') + if path: + path = os.path.expanduser(path) + if os.path.exists(path): + return path + + # 尝试常见位置 + common_paths = [ + os.path.expanduser('~/whisper.cpp'), + '/usr/local/bin/whisper', + '/opt/whisper.cpp', + ] + + for cp in common_paths: + if os.path.exists(cp): + return cp + + raise FileNotFoundError( + "未找到 whisper.cpp。请设置环境变量 WHISPER_CPP_PATH " + "或安装到 ~/whisper.cpp\n" + "安装方法: git clone https://github.com/ggerganov/whisper.cpp.git ~/whisper.cpp && cd ~/whisper.cpp && make" + ) + + +def check_model(whisper_path, model): + """检查模型是否存在""" + model_path = os.path.join(whisper_path, 'models', f'ggml-{model}.bin') + if not os.path.exists(model_path): + raise FileNotFoundError( + f"模型文件不存在: {model_path}\n" + f"请运行以下命令下载模型:\n" + f"cd {whisper_path} && ./models/download-ggml-model.sh {model}" + ) + return model_path + + +def convert_to_wav(input_path, output_dir): + """将音视频转换为 16kHz WAV 格式 + + Whisper 需要 WAV 格式的输入文件。 + """ + input_path = os.path.abspath(input_path) + + # 如果已经是 WAV 且采样率正确，直接返回 + if input_path.lower().endswith('.wav'): + try: + result = subprocess.run( + ['ffprobe', '-v', 'error', '-show_entries', + 'stream=sample_rate', '-of', 'default=noprint_wrappers=1:nokey=1', + input_path], + capture_output=True, text=True + ) + if result.returncode == 0 and int(result.stdout.strip()) == 16000: + print(f"输入文件已是 16kHz WAV 格式，直接使用") + return input_path + except Exception: + pass + + # 转换 + output_path = os.path.join(output_dir, f"{Path(input_path).stem}_audio.wav") + + print(f"转换音频格式: {input_path} -> {output_path}") + + try: + subprocess.run([ + 'ffmpeg', '-y', '-i', input_path, + '-acodec', 'pcm_s16le', + '-ar', '16000', + '-ac', '1', + '-loglevel', 'error', + output_path + ], check=True, capture_output=True) + print("音频转换完成") + return output_path + except subprocess.CalledProcessError as e: + print(f"音频转换失败: {e}") + raise RuntimeError(f"无法转换音频格式: {e}") + except FileNotFoundError: + raise RuntimeError("未找到 ffmpeg，请安装: sudo apt-get install ffmpeg") + + +def run_whisper(whisper_path, audio_path, model, output_dir, language='zh'): + """运行 Whisper 语音识别 + + Args: + whisper_path: whisper.cpp 目录 + audio_path: WAV 音频文件路径 + model: 模型名称 + output_dir: 输出目录 + language: 语言代码 + """ + # 输出文件名（使用原始输入文件名，不是 audio.wav） + # 从 output_dir 和 audio_path 推断原始文件名 + original_stem = Path(audio_path).stem.replace('_audio', '') + output_basename = original_stem + + # 构建命令 + cmd = [ + os.path.join(whisper_path, 'whisper-cli'), + '-m', os.path.join(whisper_path, 'models', f'ggml-{model}.bin'), + '-f', audio_path, + '-of', os.path.join(output_dir, output_basename), + '-l', language, + '--output-txt', + '--output-srt', + '--output-json', + ] + + print(f"执行命令: {' '.join(cmd)}") + + # 运行 + result = subprocess.run( + cmd, + capture_output=True, + text=True, + cwd=whisper_path, + timeout=3600 # 1小时超时 + ) + + if result.returncode != 0: + # 检查是否有警告但仍成功 + if "error" in result.stderr.lower() and not os.path.exists( + os.path.join(output_dir, f"{output_basename}.txt") + ): + raise RuntimeError( + f"Whisper 执行失败:\n" + f"标准输出: {result.stdout}\n" + f"错误输出: {result.stderr}" + ) + + return result + + +def parse_srt_for_duration(srt_file): + """从 SRT 文件解析时长""" + if not os.path.exists(srt_file): + return 0 + + with open(srt_file, 'r', encoding='utf-8') as f: + content = f.read() + + # 找到最后一个时间戳 + pattern = r'(\d{2}:\d{2}:\d{2}),\d{3} --> \d{2}:\d{2}:\d{2},\d{3}' + matches = re.findall(pattern, content) + + if not matches: + return 0 + + # 解析最后一个时间戳 + last_time = matches[-1] + h, m, s = last_time.split(':') + return int(h) * 3600 + int(m) * 60 + int(s) + + +def create_workflow_json(input_file, output_dir, model, language, duration): + """创建标准格式的 JSON 输出，供 KB Workflow 使用""" + input_path = Path(input_file) + basename = input_path.stem + + txt_file = os.path.join(output_dir, f"{basename}.txt") + srt_file = os.path.join(output_dir, f"{basename}.srt") + json_file = os.path.join(output_dir, f"{basename}.json") + + # 读取文本内容 + text_content = "" + if os.path.exists(txt_file): + with open(txt_file, 'r', encoding='utf-8') as f: + text_content = f.read().strip() + + # 解析 SRT 获取分段 + segments = [] + if os.path.exists(srt_file): + with open(srt_file, 'r', encoding='utf-8') as f: + content = f.read() + + # SRT 格式: 序号 -> 时间 -> 文本 + pattern = r'(\d+)\n(\d{2}:\d{2}:\d{2},\d{3}) --> (\d{2}:\d{2}:\d{2},\d{3})\n(.+?)(?=\n\n|\Z)' + matches = re.findall(pattern, content, re.DOTALL) + + def parse_time(t): + h, m, s_ms = t.split(':') + s, ms = s_ms.split(',') + return float(h) * 3600 + float(m) * 60 + float(s) + float(ms) / 1000 + + for idx, (num, start, end, text) in enumerate(matches): + segments.append({ + "id": idx, + "start": round(parse_time(start), 2), + "end": round(parse_time(end), 2), + "text": text.strip() + }) + + # 构建 JSON + workflow_json = { + "success": True, + "tool": "whisper", + "model": model, + "language": language, + "input_file": str(input_path), + "output_files": { + "txt": f"{basename}.txt", + "srt": f"{basename}.srt", + "json": f"{basename}.json" + }, + "duration_seconds": duration, + "segments": segments, + "text": text_content + } + + # 写入 JSON + with open(json_file, 'w', encoding='utf-8') as f: + json.dump(workflow_json, f, ensure_ascii=False, indent=2) + + return workflow_json + + +def main(): + """主函数""" + args = parse_arguments() + + # 检查输入文件 + input_file = os.path.abspath(args.input) + if not os.path.exists(input_file): + print(f"错误: 输入文件不存在: {input_file}", file=sys.stderr) + sys.exit(1) + + # 获取输出目录 + if args.output: + output_dir = os.path.abspath(args.output) + else: + output_dir = os.path.dirname(input_file) + + os.makedirs(output_dir, exist_ok=True) + + # 获取 whisper.cpp 路径 + try: + whisper_path = get_whisper_cpp_path() + print(f"✓ Whisper.cpp 路径: {whisper_path}") + except FileNotFoundError as e: + print(f"✗ 错误: {e}", file=sys.stderr) + sys.exit(1) + + # 检查模型 + try: + check_model(whisper_path, args.model) + print(f"✓ 使用模型: {args.model}") + except FileNotFoundError as e: + print(f"✗ 错误: {e}", file=sys.stderr) + sys.exit(1) + + # 后台执行 + if args.background: + print("启动后台处理...") + log_file = os.path.join(output_dir, f"{Path(input_file).stem}_whisper.log") + + with open(log_file, 'w') as log: + subprocess.Popen( + [sys.executable, __file__, + '--input', input_file, + '--model', args.model, + '--output', output_dir, + '--language', args.language], + stdout=log, + stderr=log, + start_new_session=True + ) + + print(f"✓ 后台任务已启动") + print(f" 日志: {log_file}") + print(f" 输出: {output_dir}") + + result = { + "success": True, + "background": True, + "status": "running", + "log_file": log_file, + "output_dir": output_dir + } + print(json.dumps(result, ensure_ascii=False, indent=2)) + return + + # 前台执行 + print(f"\n📁 处理文件: {input_file}") + print(f"📁 输出目录: {output_dir}") + + try: + # 1. 转换为 WAV + print(f"\n🔄 步骤1: 转换音频格式...") + audio_path = convert_to_wav(input_file, output_dir) + + # 2. 运行 Whisper + print(f"\n🎙️ 步骤2: 语音识别 (语言: {args.language})...") + run_whisper(whisper_path, audio_path, args.model, output_dir, args.language) + + # 3. 清理临时 WAV 文件 + if audio_path != input_file and audio_path.endswith('_audio.wav'): + try: + os.remove(audio_path) + print("✓ 清理临时文件") + except Exception: + pass + + # 4. 获取时长并创建 JSON + print(f"\n📝 步骤3: 生成输出文件...") + basename = Path(input_file).stem + srt_file = os.path.join(output_dir, f"{basename}.srt") + duration = parse_srt_for_duration(srt_file) + + workflow_json = create_workflow_json( + input_file, output_dir, args.model, args.language, duration + ) + + # 输出结果 + print(f"\n✅ 处理完成!") + print(f" 时长: {duration} 秒") + print(f" 分段数: {len(workflow_json['segments'])}") + print(f"\n📄 输出文件:") + for fmt in ['txt', 'srt', 'json']: + fpath = os.path.join(output_dir, f"{basename}.{fmt}") + if os.path.exists(fpath): + size = os.path.getsize(fpath) + print(f" • {fmt.upper()}: {fpath} ({size:,} bytes)") + + print(f"\n📋 Workflow JSON:") + print(json.dumps({ + "success": workflow_json["success"], + "tool": "whisper", + "text_length": len(workflow_json["text"]), + "segments_count": len(workflow_json["segments"]) + }, ensure_ascii=False, indent=2)) + + except Exception as e: + print(f"\n✗ 错误: {e}", file=sys.stderr) + sys.exit(1) + + +if __name__ == '__main__': + main() diff --git a/kb-workflow/.env b/kb-workflow/.env new file mode 100644 index 0000000..dc8e79b --- /dev/null +++ b/kb-workflow/.env @@ -0,0 +1,14 @@ +# KB Workflow 环境变量配置 +export KB_BASE_PATH="~/work/knowledge-base" + +# 可选: B站 Cookie（用于下载会员视频） +# export BILIBILI_COOKIE="SESSDATA=xxx; bili_jct=xxx" + +# 可选: AI 分析配置 +# export AI_API_KEY="your-api-key" +# export AI_PROVIDER="openai" # 或 zhipu, minimax +# export AI_MODEL="gpt-4" + +# 可选: Git 配置 +# export KB_GIT_USER="Your Name" +# export KB_GIT_EMAIL="your@email.com" diff --git a/kb-workflow/.env.example b/kb-workflow/.env.example new file mode 100644 index 0000000..dc8e79b --- /dev/null +++ b/kb-workflow/.env.example @@ -0,0 +1,14 @@ +# KB Workflow 环境变量配置 +export KB_BASE_PATH="~/work/knowledge-base" + +# 可选: B站 Cookie（用于下载会员视频） +# export BILIBILI_COOKIE="SESSDATA=xxx; bili_jct=xxx" + +# 可选: AI 分析配置 +# export AI_API_KEY="your-api-key" +# export AI_PROVIDER="openai" # 或 zhipu, minimax +# export AI_MODEL="gpt-4" + +# 可选: Git 配置 +# export KB_GIT_USER="Your Name" +# export KB_GIT_EMAIL="your@email.com" diff --git a/kb-workflow/README.md b/kb-workflow/README.md new file mode 100644 index 0000000..14d720b --- /dev/null +++ b/kb-workflow/README.md @@ -0,0 +1,247 @@ +# KB Workflow 环境安装脚本 + +一键检查并安装 kb-workflow 知识库工作流所需的全部环境依赖。 + +## 功能特性 + +- ✅ 自动检测系统类型 (Ubuntu/Debian/Fedora/Arch) +- ✅ 检查系统依赖 (Python3, pip3, ffmpeg, tesseract, git) +- ✅ 检查 Python 依赖包 (httpx, aiohttp, playwright, easyocr 等) +- ✅ 自动创建知识库目录结构 +- ✅ 生成环境变量配置示例 +- ✅ 汇总显示所有需要执行的安装命令 + +## 使用方法 + +### 运行检查脚本 + +```bash +cd /home/starmen1265/.openclaw/workspace/skills +./install-kb-workflow.sh +``` + +脚本会检查所有依赖，并显示需要执行的安装命令。 + +### 示例输出 + +``` +======================================== +第一步: 检查系统依赖 +======================================== +[SUCCESS] Python3 已安装: Python 3.12.3 +[WARN] pip3 未安装 +[WARN] ffmpeg 未安装 +... + +======================================== +需要安装的系统依赖 +======================================== + +检测到以下依赖未安装: + - python3-pip + - ffmpeg + - tesseract-ocr + +━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ +请运行以下命令安装: +━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ + +sudo apt-get update +sudo apt-get install -y python3-pip ffmpeg tesseract-ocr tesseract-ocr-chi-sim tesseract-ocr-eng +``` + +## 依赖清单 + +### 系统依赖 + +| 依赖 | 用途 | 安装命令 | +|------|------|----------| +| **python3** | Python 运行时 | `sudo apt-get install python3` | +| **python3-pip** | Python 包管理器 | `sudo apt-get install python3-pip` | +| **ffmpeg** | 视频处理（OCR 截帧） | `sudo apt-get install ffmpeg` | +| **tesseract-ocr** | OCR 引擎（备用方案） | `sudo apt-get install tesseract-ocr` | +| **git** | 版本控制（归档提交） | `sudo apt-get install git` | + +### Tesseract 语言包 + +```bash +# Ubuntu/Debian +sudo apt-get install tesseract-ocr-chi-sim tesseract-ocr-chi-tra tesseract-ocr-eng + +# Fedora/RHEL +sudo dnf install tesseract-langpack-chi_sim tesseract-langpack-chi_tra tesseract-langpack-eng +``` + +### Python 依赖 + +```bash +# 基础 HTTP 库 +pip3 install --user httpx aiohttp requests + +# 图像和 OCR +pip3 install --user Pillow easyocr pytesseract + +# 浏览器自动化 +pip3 install --user playwright +python3 -m playwright install chromium +``` + +## 目录结构 + +安装完成后会创建以下目录结构： + +``` +~/work/knowledge-base/ # 知识库根目录（可配置） +├── archive/ # 归档目录 +│ ├── pending/ # 待处理 +│ └── subscriptions/ # 订阅信息 +├── metadata/ # 元数据文件 +├── content/ # 内容文件 +│ ├── downloads/ # 视频下载 +│ └── subtitles/ # 字幕文件 +└── analyzed/ # 深度分析报告 +``` + +## 环境变量 + +### 必需 +- `KB_BASE_PATH` - 知识库根目录（默认: `~/work/knowledge-base`） + +### 可选 +- `BILIBILI_COOKIE` - B站 Cookie，用于下载会员视频 +- `AI_API_KEY` - AI API 密钥，用于深度内容分析 +- `AI_PROVIDER` - AI 提供商（openai/zhipu/minimax） +- `AI_MODEL` - AI 模型名称（如 gpt-4） +- `AI_BASE_URL` - 自定义 API 端点 +- `KB_GIT_USER` - Git 用户名（用于归档提交） +- `KB_GIT_EMAIL` - Git 邮箱（用于归档提交） +- `KB_GIT_REMOTE` - Git 远程仓库地址 + +### 配置方法 + +将以下内容添加到 `~/.bashrc` 或 `~/.zshrc`： + +```bash +# KB Workflow 配置 +export KB_BASE_PATH="~/work/knowledge-base" + +# 可选：B站 Cookie +export BILIBILI_COOKIE="SESSDATA=xxx; bili_jct=xxx" + +# 可选：AI 配置 +export AI_API_KEY="your-api-key" +export AI_PROVIDER="openai" +export AI_MODEL="gpt-4" +``` + +然后重新加载配置： +```bash +source ~/.bashrc # 或 source ~/.zshrc +``` + +## 故障排除 + +### 1. pip3 命令不存在 + +```bash +# 方法 1: 安装 pip3 +sudo apt-get install python3-pip + +# 方法 2: 使用 python3 -m pip +python3 -m pip install --user +``` + +### 2. Playwright 浏览器安装失败 + +```bash +# 手动安装 Chromium +python3 -m playwright install chromium + +# 如果仍然失败，尝试安装依赖 +sudo apt-get install libnss3 libatk-bridge2.0-0 libxss1 libgtk-3-0 +``` + +### 3. EasyOCR 安装失败 + +EasyOCR 依赖 PyTorch，可能需要较长时间安装： + +```bash +# 先安装 PyTorch +pip3 install --user torch torchvision --index-url https://download.pytorch.org/whl/cpu + +# 再安装 easyocr +pip3 install --user easyocr +``` + +### 4. 权限问题 + +如果使用 `--user` 安装的包无法找到，检查 PATH： + +```bash +# 查看用户安装路径 +python3 -m site --user-base + +# 添加到 PATH（添加到 ~/.bashrc） +export PATH="$PATH:$(python3 -m site --user-base)/bin" +``` + +### 5. OCR 中文识别问题 + +确保已安装中文语言包： + +```bash +# 检查已安装的语言包 +tesseract --list-langs + +# 应该能看到 chi_sim 和 chi_tra +``` + +## 更新 + +如果技能更新了依赖，可以重新运行检查脚本： + +```bash +./install-kb-workflow.sh +``` + +## 子技能清单 + +| 技能 | 路径 | 功能 | +|------|------|------| +| kb-workflow | `kb-workflow/kb_workflow.py` | 主流程协调 | +| kb-link-parser | `kb-link-parser/link-parser.py` | 链接解析 | +| kb-bilibili-metadata | `kb-bilibili-metadata/bilibili_metadata.py` | B站元数据提取 | +| kb-bilibili-content | `kb-bilibili-content/bilibili_content.py` | B站内容下载 | +| kb-ocr-processor | `kb-ocr-processor/ocr_processor.py` | 视频 OCR 识别 | +| kb-deep-analyzer | `kb-deep-analyzer/deep_analyzer.py` | AI 深度分析 | + +## 使用 kb-workflow + +安装完成后，可以通过以下方式使用： + +### 方式 1：通过主代理 + +直接向主代理发送消息： +``` +添加到知识库 https://www.bilibili.com/video/BVxxxxx +``` + +### 方式 2：手动运行子技能 + +```bash +# 1. 链接解析 +python3 kb-link-parser/link-parser.py --url "https://www.bilibili.com/video/BVxxxxx" + +# 2. 元数据提取 +python3 kb-bilibili-metadata/bilibili_metadata.py --id "BVxxxxx" --type video + +# 3. 内容下载 +python3 kb-bilibili-content/bilibili_content.py --id "BVxxxxx" --type subtitle + +# 4. 深度分析 +python3 kb-deep-analyzer/deep_analyzer.py --metadata meta.json --content content.json --output analysis.md +``` + +## 许可证 + +MIT License diff --git a/kb-workflow/SKILL.md b/kb-workflow/SKILL.md new file mode 100644 index 0000000..d763b00 --- /dev/null +++ b/kb-workflow/SKILL.md @@ -0,0 +1,360 @@ +--- +name: kb-workflow +description: 当收到"添加到知识库 + 链接" 或"保存到知识库 + 链接"时使用 +--- + +# KB Workflow + +## 什么时候使用 + +当用户发送包含以下模式的消息时，此技能自动触发： + +| 触发词 | 行为 | 示例 | +|--------|------|------| +| `添加到知识库` + 链接 | 添加到知识库并处理 | "添加到知识库 https://www.bilibili.com/video/BVxxx" | +| `保存到知识库` + 链接 | 同上 | "保存到知识库 https://www.bilibili.com/video/BVxxx" | + +## 环境变量 + +### 执行前必须检查 + +在执行 workflow 之前，必须检查环境变量是否已经设置。 + +**必须的环境变量**（缺失则报错退出）： + +配置方式：将变量写入 `~/.kb_env` 文件： +```bash +export AI_API_KEY="your-api-key" +export AI_PROVIDER="zhipu" +export AI_MODEL="glm-5" +export AI_BASE_URL="https://open.bigmodel.cn/api/coding/paas/v4" +``` + +**可选的环境变量**： +| 变量名 | 用途 | 示例 | +|--------|------|------| +| `BILIBILI_COOKIE` | 下载会员视频 | `SESSDATA=xxx; bili_jct=xxx` | +| `KB_GIT_USER` | Git提交用户名 | `Your Name` | +| `KB_GIT_EMAIL` | Git提交邮箱 | `your@email.com` | + +### 检查命令 + +```bash +# 检查必须的环境变量 +echo "AI_API_KEY: ${AI_API_KEY:0:10}..." +echo "AI_PROVIDER: $AI_PROVIDER" +echo "AI_MODEL: $AI_MODEL" +echo "AI_BASE_URL: $AI_BASE_URL" + +# 验证方式1: 检查变量是否存在 +if [ -z "$AI_API_KEY" ]; then + echo "❌ AI_API_KEY 未设置" + exit 1 +fi + +# 验证方式2: 执行测试调用 +python3 -c " +import os +if not os.environ.get('AI_API_KEY'): + raise RuntimeError('AI_API_KEY 未设置') +print('✅ 环境变量检查通过') +" +``` + + +## Workflow 执行方式 + +主代理直接执行以下步骤，无需启动 kb-workflow 子代理： + +1. 主代理启动子代理调用 kb-link-parser +2. 主代理启动子代理调用 kb-平台-metadata +3. 主代理启动子代理调用 kb-平台-content +4. 主代理启动子代理调用 kb-ocr-processor（如需要） +5. 主代理启动子代理调用 kb-deep-analyzer +6. 主代理执行 `kb_workflow.py --archive-file` 归档 + + +## Workflow 执行步骤 + +当触发后，按照以下步骤执行： + +### 步骤 1: 环境变量检查 + +**❌ 禁止跳过此步骤！必须先检查环境变量。** + +```bash +# 0. 从 ~/.kb_env 加载环境变量（专门的知识库配置文件，不受 bashrc 交互式检查影响） +if [ -f ~/.kb_env ]; then + source ~/.kb_env +fi + +# 1. 检查必须的环境变量是否存在 +if [ -z "$AI_API_KEY" ] || [ -z "$AI_PROVIDER" ] || [ -z "$AI_MODEL" ] || [ -z "$AI_BASE_URL" ]; then + echo "❌ 错误：必须的环境变量未设置" + echo "请配置以下环境变量：" + echo " - AI_API_KEY" + echo " - AI_PROVIDER (zhipu/openai/minimax)" + echo " - AI_MODEL" + echo " - AI_BASE_URL" + exit 1 +fi + +echo "✅ 环境变量检查通过" +echo " AI_PROVIDER: $AI_PROVIDER" +echo " AI_MODEL: $AI_MODEL" +``` + +**如果检查不通过，必须**： +1. 报错提示用户 +2. 退出，不执行后续步骤 +3. 等待用户配置好环境变量后重新执行 + +## ⚠️ 严格失败处理原则 + +> **深度分析步骤必须成功，否则整个流程失败** + +在执行工作流时，必须遵守以下原则： +1. **深度分析不可跳过**：kb-deep-analyzer 是必须成功执行的步骤 +2. **失败即终止**：如果深度分析返回 `success: false`，必须立即停止并汇报失败 +3. **禁止降级处理**：不能使用预设模板或简单摘要来"假装成功" +4. **每次执行都要使用 AI**：必须有真实的 AI API 调用记录 + +### 步骤 2: 链接解析 + +1. 获取目录路径： +```bash +python3 kb_workflow.py --pending +``` + +2. 启动子代理调用 kb-link-parser： +```bash +python3 /path/to/link-parser.py --url "[URL]" +``` + +3. 解析输出 JSON，提取 filename 和 platform + +### 步骤 3: 元数据提取 + +1. 获取元数据目录路径： +```bash +python3 kb_workflow.py --metadata +# 返回: {"path": "/home/admin/work/knowledge-base/metadata"} +``` + +2. 构建输出文件路径：`${metadata_dir}/${platform}_${id}.meta.json` + +3. 启动子代理调用对应平台的 metadata 技能（传入 `--output`）： +```bash +# Bilibili +python3 /path/to/bilibili_metadata.py --id "[ID]" --type video --output "${metadata_dir}/bilibili_[ID].meta.json" + +# Zhihu +python3 /path/to/zhihu_metadata.py --id "[ID]" --type question --output "${metadata_dir}/zhihu_[ID].meta.json" +``` + +4. 解析输出 JSON，提取 filename + +### 步骤 4: 内容下载 + +1. 获取目录路径： +```bash +python3 kb_workflow.py --content_downloads +python3 kb_workflow.py --content +``` + +2. 启动子代理调用对应平台的 content 技能： +```bash +# Bilibili 字幕下载（自动检测是否有官方字幕） +python3 /path/to/bilibili_content.py --id "[ID]" --type subtitle-download --output [content_dir] + +# 返回 JSON 包含 has_subtitle 字段 +``` + +3. 解析输出 JSON： +- **has_subtitle = true**: 有官方字幕，直接进入步骤 6 +- **has_subtitle = false**: 没有官方字幕，继续步骤 5 + +> ⚠️ **重要提示**：没有找到官方字幕是**正常的**！很多视频没有自动生成的字幕。不要因为没有字幕就停止工作流，继续执行 Whisper 步骤即可。 + +### 步骤 5: 语音识别转文字（仅当没有官方字幕时执行） + +> ⚠️ **重要**：此步骤仅在**没有官方字幕**时执行。如果有官方字幕，**跳过此步骤**。 + +此步骤使用 Whisper 进行语音识别： +- **严禁跳过**：必须等待识别完成 +- **定时汇报**：每2-3分钟向用户汇报进度 +- **超时时间**：30分钟 +- **耐心等待**：不要中途启动其他步骤，必须串行执行 + +1. 获取目录路径： +```bash +python3 kb_workflow.py --content +``` + +2. 启动子代理调用 kb-whisper（传入视频路径）： +```bash +# 必须传入 --output 完整路径 +python3 /path/to/whisper.py --input [video_path] --model base --output [content_dir] +``` + +3. 等待 Whisper 完成（定时汇报进度） + +4. 解析输出 JSON，生成 content 文件供步骤6使用 + +### 步骤 6: 深度分析 + +1. 获取目录路径： +```bash +python3 kb_workflow.py --analyzed +``` + +2. 准备 content JSON 文件（包含 subtitle/description） + +3. 如果有官方字幕，使用官方字幕的 SRT 文件 +4. 如果没有官方字幕，使用 Whisper 识别的结果 + +5. 启动子代理调用 kb-deep-analyzer（使用 g5 模型）： +```bash +python3 /path/to/deep_analyzer.py --metadata [meta_path] --content [content_path] --output [analyzed_dir]/[filename].md --provider zhipu --model glm-5 +``` + +**环境变量设置**（在子代理中设置）： +- `AI_PROVIDER=zhipu` +- `AI_MODEL=glm-5` + +6. 解析输出 JSON，检查 `success` 字段： + +> ⚠️ **深度分析失败 = 整个流程失败** +> - 如果 `success = true`：继续步骤 7（归档） +> - 如果 `success = false`：**立即终止流程**，向用户汇报失败原因 +> - **严禁**继续执行后续步骤或使用降级内容"假装成功" + +### 步骤 7: 归档 + +运行归档命令： +```bash +python3 kb_workflow.py --archive-file "[分析报告文件路径]" +``` + +### 步骤 8: 汇报完成 + +向用户汇报： +- 视频标题 +- 处理阶段完成情况 +- 最终文件路径 +- Git commit 信息 + + +## 子技能清单 + +| 步骤 | 子技能 | 命令示例 | 输出 | 备注 | +|------|--------|----------|------|------| +| 2 | kb-link-parser | `--url "BVxxx"` | `{p}_{id}.link.json` | | +| 3 | kb-bilibili-metadata | `--id "BVxxx" --type video` | `{p}_{id}.meta.json` | | +| 3 | kb-zhihu-metadata | `--id "xxx" --type question` | `{p}_{id}.meta.json` | | +| 4 | kb-bilibili-content | `--id "BVxxx" --type subtitle-download` | `{p}_{id}.srt` | 如果没有字幕是正常的 | +| 4 | kb-bilibili-content | `--id "BVxxx" --type video` | `{p}_{id}.mp4` | 如果需要下载视频 | +| 5 | kb-whisper | `--input xxx.mp4 --model base` | `{p}_{id}.json`, `{p}_{id}.txt` | 仅当没有官方字幕时执行 | +| 6 | kb-deep-analyzer | `--metadata x.meta.json --content x.json --output x.md --provider zhipu --model glm-5` | `{p}_{id}.md` | **使用 g5 模型，必须成功** | + +## 条件分支逻辑 + +``` +步骤3: 获取元数据 + ↓ +步骤4: 下载字幕 (--type subtitle-download) + ↓ +┌─────────────────────────────────────┐ +│ has_subtitle = true? │ +├─────────────────────────────────────┤ +│ 是 → 直接进入步骤6（深度分析） │ +│ 否 → 进入步骤5（Whisper语音识别） │ +└─────────────────────────────────────┘ + ↓ +步骤6: 深度分析 + ↓ +┌─────────────────────────────────────┐ +│ kb-deep-analyzer 执行结果 │ +├─────────────────────────────────────┤ +│ success = true → 步骤7（归档） │ +│ success = false → ❌ 整个流程失败 │ +└─────────────────────────────────────┘ +``` + +> ⚠️ **重要：深度分析失败则整个流程失败** +> - 深度分析必须使用正确的 AI 模型（glm-4.7）完整分析字幕内容 +> - 如果 `kb-deep-analyzer` 返回 `success: false`，**必须汇报失败**，不能继续执行后续步骤 +> - 不能使用预设模板或降级内容来"假装成功" +> - 失败时必须向用户报告具体的错误原因 + +> ⚠️ **重要**：没有找到官方字幕是**正常的**！很多视频没有自动生成的字幕。 +> - 如果 `has_subtitle = false`，继续执行 Whisper 步骤 +> - 如果 `has_subtitle = true`，跳过 Whisper 步骤，直接使用官方字幕 + +## 目录结构 + +``` +~/work/knowledge-base/ +├── archive/ +│ └── YYYY-MM-DD/ +├── pending/ +│ └── {platform}_{id}.link.json +├── metadata/ +│ └── {platform}_{id}.meta.json +├── content/ +│ ├── downloads/ +│ │ └── {platform}_{id}.mp4 +│ ├── {platform}_{id}.txt # Whisper 识别的文本 +│ └── {platform}_{id}.json # Whisper 完整结果 +└── analyzed/ + └── {platform}_{id}.md +``` + +## 辅助命令 + +```bash +# ------------------- 查重与归档 ------------------- + +# 查重 +python3 kb_workflow.py --check --url "[URL]" + +# 归档分析报告 +python3 kb_workflow.py --archive-file "[分析报告路径]" + + +# ------------------- 目录路径查询 ------------------- + +# 获取知识库根目录（默认 ~/work/knowledge-base） +python3 kb_workflow.py --base-path "~/custom/path" + +# 获取待处理目录（pending） +python3 kb_workflow.py --pending + +# 获取元数据目录 +python3 kb_workflow.py --metadata + +# 获取内容目录 +python3 kb_workflow.py --content + +# 获取内容下载目录 +python3 kb_workflow.py --content_downloads + +# 获取字幕目录 +python3 kb_workflow.py --content_subtitles + +# 获取深度分析目录 +python3 kb_workflow.py --analyzed + +# 获取归档目录 +python3 kb_workflow.py --archive + +# 获取订阅信息目录 +python3 kb_workflow.py --archive_subscriptions + + +# ------------------- 工具函数 ------------------- + +# 从文件名提取平台名称 +python3 kb_workflow.py --extract_platform "bilibili_BVxxx.mp4" +``` + diff --git a/kb-workflow/SkillBug.md b/kb-workflow/SkillBug.md new file mode 100644 index 0000000..ae5df03 --- /dev/null +++ b/kb-workflow/SkillBug.md @@ -0,0 +1,101 @@ +# SkillBug.md + +## 问题记录 + +### 2026-02-10: 子代理权限问题 + +**问题：** `sessions_spawn` 调用子代理时返回 `forbidden` 错误。 + +**原因：** OpenClaw 配置中 allowlist 为空，Python 脚本没有权限调用子代理。 + +**解决方案：** 改用 Prompt-based 模式（方案B）。 + +--- + +## 架构重构 + +### 之前（Script-based） + +``` +kb_workflow.py (Python脚本) + ↓ +sessions_spawn() # ❌ 失败（脚本没有权限） +``` + +### 之后（Prompt-based） + +``` +主代理读取 SKILL.md + ↓ +按照指导调用 sessions_spawn # ✅ 成功（主代理有权限） +``` + +### 文件变更 + +| 文件 | 变更 | 说明 | +|------|------|------| +| `SKILL.md` | 重写 | 详细定义 workflow 步骤，主代理直接读取执行 | +| `kb_workflow.py` | 简化 | 保留为辅助工具函数库（查重、归档、Git） | +| `skill_main.py` | 简化 | 只做触发检测，返回指导信息 | +| `SkillBug.md` | 更新 | 记录架构变更 | + +### SKILL.md 结构 + +``` +1. 触发条件 +2. 步骤 1: 查重 +3. 步骤 2: kb-link-parser +4. 步骤 3: 元数据技能 +5. 步骤 4: 内容下载 +6. 步骤 5: OCR（30分钟超时） +7. 步骤 6: 深度分析 +8. 步骤 7: 归档和 Git +9. 步骤 8: 汇报完成 +10. 目录结构 +11. 支持平台 +12. 注意事项 +``` + +### kb_workflow.py 保留的函数 + +```python +extract_platform(filename) # 从文件名提取平台 +extract_base_name(filename) # 从文件名提取基础名称 +get_knowledge_base_path() # 获取知识库根目录 +ensure_directories(base_path) # 确保目录存在 +check_duplicate(url) # 查重 +archive_and_git(analyzed_file) # 归档和 Git +generate_summary(...) # 生成汇报 +``` + +--- + +### 2026-02-12: B站视频下载失败 - 403 Forbidden + +**问题：** 使用 kb-bilibili-content 下载视频时返回 403 Forbidden 错误。 + +**原因：** +1. 视频可能需要B站会员权限 +2. 或者需要登录cookie才能下载 +3. 当前未配置 `BILIBILI_COOKIE` 环境变量 + +**复现场景：** +- 链接：https://www.bilibili.com/video/BV1Z9nXzUEhv +- 下载命令：`python3 bilibili_content.py --id "BV1Z9nXzUEhv" --type video` +- 结果：返回403错误页面，文件只有548字节 + +**影响：** 无法进行后续的OCR处理和深度分析 + +**建议解决方案：** +1. 配置 `BILIBILI_COOKIE` 环境变量 +2. 或提供cookies文件路径 +3. 或跳过OCR步骤，使用元数据+简介进行深度分析 + +**当前进度：** +- ✅ 步骤1：环境变量检查完成 +- ✅ 步骤2：链接解析成功（bilibili_BV1Z9nXzUEhv） +- ✅ 步骤3：元数据提取成功（标题：新加坡分区漫游指南...） +- ❌ 步骤4：视频下载失败（403） +- ⏸️ 步骤5：OCR处理（阻塞） +- ⏸️ 步骤6：深度分析（阻塞） +- ⏸️ 步骤7：归档（阻塞） diff --git a/kb-workflow/install-env.sh b/kb-workflow/install-env.sh new file mode 100644 index 0000000..39d0f3e --- /dev/null +++ b/kb-workflow/install-env.sh @@ -0,0 +1,321 @@ +#!/bin/bash +# ============================================================================= +# KB Workflow 环境一键安装脚本 +# ============================================================================= +# 功能: 检查并安装 kb-workflow 技能所需的全部环境依赖 +# 支持: Ubuntu/Debian 系统 +# +# 使用方法: +# ./install-env.sh # 检查环境并提示安装命令（检查模式） +# ./install-env.sh --auto # 自动安装所有缺失依赖（自动模式） +# ============================================================================= + +# 颜色定义 +RED='\033[0;31m' +GREEN='\033[0;32m' +YELLOW='\033[1;33m' +BLUE='\033[0;34m' +NC='\033[0m' + +# 日志函数 +log_info() { echo -e "${BLUE}[INFO]${NC} $1"; } +log_success() { echo -e "${GREEN}[SUCCESS]${NC} $1"; } +log_warn() { echo -e "${YELLOW}[WARN]${NC} $1"; } +log_error() { echo -e "${RED}[ERROR]${NC} $1"; } +log_section() { + echo "" + echo -e "${BLUE}========================================${NC}" + echo -e "${BLUE}$1${NC}" + echo -e "${BLUE}========================================${NC}" +} + +# 获取脚本目录 +SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )" +DEFAULT_KB_PATH="${HOME}/work/knowledge-base" + +# 解析参数 +AUTO_MODE=false +if [ "$1" = "--auto" ]; then + AUTO_MODE=true + log_info "自动安装模式" +fi + +# 检测 Linux 发行版 +detect_distro() { + if [ -f /etc/os-release ]; then + . /etc/os-release + echo "$ID" + elif [ -f /etc/debian_version ]; then + echo "debian" + elif [ -f /etc/redhat-release ]; then + echo "rhel" + fi +} +DISTRO=$(detect_distro) + +# 检查命令是否存在 +command_exists() { + command -v "$1" > /dev/null 2>&1 +} + +# 检查 Python 包 +check_python_package() { + python3 -c "import $1" 2>/dev/null +} + +# ============================================================================= +# 1. 检查系统依赖 +# ============================================================================= +log_section "第一步: 检查系统依赖" + +MISSING_DEPS=() + +# 检查 Python3 +if command_exists python3; then + PYTHON_VERSION=$(python3 --version | cut -d' ' -f2) + log_success "Python3 已安装: $PYTHON_VERSION" +else + log_warn "Python3 未安装" + MISSING_DEPS+=("python3") +fi + +# 检查 pip3 +if python3 -m pip --version > /dev/null 2>&1 || command_exists pip3; then + log_success "pip3 已安装" +else + log_warn "pip3 未安装" + MISSING_DEPS+=("python3-pip") +fi + +# 检查 ffmpeg +if command_exists ffmpeg; then + log_success "ffmpeg 已安装" +else + log_warn "ffmpeg 未安装" + MISSING_DEPS+=("ffmpeg") +fi + +# 检查 tesseract +if command_exists tesseract; then + log_success "Tesseract OCR 已安装" +else + log_warn "Tesseract OCR 未安装" + MISSING_DEPS+=("tesseract-ocr") +fi + +# 检查 git +if command_exists git; then + log_success "Git 已安装" +else + log_warn "Git 未安装" + MISSING_DEPS+=("git") +fi + +# ============================================================================= +# 2. 自动安装系统依赖（自动模式） +# ============================================================================= +if [ ${#MISSING_DEPS[@]} -gt 0 ]; then + if [ "$AUTO_MODE" = true ]; then + log_section "自动安装系统依赖" + log_info "检测到系统: $DISTRO" + + case "$DISTRO" in + ubuntu|debian) + log_info "更新包列表..." + sudo apt-get update -qq + + log_info "安装依赖: ${MISSING_DEPS[*]}" + sudo apt-get install -y -qq "${MISSING_DEPS[@]}" tesseract-ocr-chi-sim tesseract-ocr-eng + ;; + fedora|rhel|centos) + log_info "更新包列表..." + sudo dnf check-update -y || true + + log_info "安装依赖: ${MISSING_DEPS[*]}" + sudo dnf install -y "${MISSING_DEPS[@]}" tesseract-langpack-chi_sim tesseract-langpack-eng + ;; + arch) + log_info "安装依赖: ${MISSING_DEPS[*]}" + sudo pacman -S --noconfirm "${MISSING_DEPS[@]}" tesseract-data-chi_sim tesseract-data-eng + ;; + *) + log_error "不支持的系统: $DISTRO" + exit 1 + ;; + esac + + log_success "系统依赖安装完成" + MISSING_DEPS=() + else + log_section "需要安装的系统依赖" + echo "" + echo "检测到以下依赖未安装:" + for dep in "${MISSING_DEPS[@]}"; do + echo " - $dep" + done + + echo "" + echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" + echo "请运行以下命令安装:" + echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" + echo "" + echo -e "${YELLOW}sudo apt-get update${NC}" + echo -e "${YELLOW}sudo apt-get install -y ${MISSING_DEPS[*]} tesseract-ocr-chi-sim tesseract-ocr-eng${NC}" + echo "" + fi +fi + +# ============================================================================= +# 3. 检查 Python 依赖 +# ============================================================================= +log_section "第二步: 检查 Python 依赖" + +PYTHON_PACKAGES=( + "httpx:httpx" + "aiohttp:aiohttp" + "requests:requests" + "Pillow:PIL" +) + +MISSING_PY_PKGS=() + +for pkg_info in "${PYTHON_PACKAGES[@]}"; do + pkg_name=$(echo "$pkg_info" | cut -d':' -f1) + import_name=$(echo "$pkg_info" | cut -d':' -f2) + if check_python_package "$import_name" 2>/dev/null; then + log_success "$pkg_name 已安装" + else + log_warn "$pkg_name 未安装" + MISSING_PY_PKGS+=("$pkg_name") + fi +done + +# 检查特殊包 +check_python_package "playwright" 2>/dev/null && log_success "playwright 已安装" || MISSING_PY_PKGS+=("playwright") +check_python_package "easyocr" 2>/dev/null && log_success "easyocr 已安装" || MISSING_PY_PKGS+=("easyocr") +check_python_package "pytesseract" 2>/dev/null && log_success "pytesseract 已安装" || MISSING_PY_PKGS+=("pytesseract") + +# ============================================================================= +# 4. 自动安装 Python 依赖（自动模式） +# ============================================================================= +if [ ${#MISSING_PY_PKGS[@]} -gt 0 ]; then + if [ "$AUTO_MODE" = true ]; then + log_section "自动安装 Python 包" + + log_info "安装: ${MISSING_PY_PKGS[*]}" + pip3 install --user "${MISSING_PY_PKGS[@]}" -q + + log_success "Python 包安装完成" + + # 安装 Playwright 浏览器 + if [[ " ${MISSING_PY_PKGS[*]} " =~ " playwright " ]]; then + log_info "安装 Playwright Chromium 浏览器..." + python3 -m playwright install chromium + log_success "Chromium 浏览器安装完成" + fi + + MISSING_PY_PKGS=() + else + echo "" + echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" + echo "需要安装以下 Python 包:" + echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" + for pkg in "${MISSING_PY_PKGS[@]}"; do + echo " - $pkg" + done + + echo "" + echo "请运行以下命令安装:" + echo "" + echo -e "${YELLOW}pip3 install --user ${MISSING_PY_PKGS[*]}${NC}" + + if [[ " ${MISSING_PY_PKGS[*]} " =~ " playwright " ]]; then + echo "" + echo -e "${YELLOW}安装完 playwright 后，还需要运行:${NC}" + echo -e "${YELLOW} python3 -m playwright install chromium${NC}" + fi + echo "" + fi +fi + +# ============================================================================= +# 5. 创建知识库目录结构 +# ============================================================================= +log_section "第三步: 创建知识库目录结构" + +KB_BASE_PATH="${KB_BASE_PATH:-$DEFAULT_KB_PATH}" +log_info "知识库路径: $KB_BASE_PATH" + +mkdir -p "$KB_BASE_PATH"/{archive/{subscriptions,pending},metadata,content/{downloads,subtitles},analyzed} +log_success "目录结构创建完成" + +# ============================================================================= +# 6. 环境变量配置提示 +# ============================================================================= +log_section "第四步: 环境变量配置" + +if [ -z "$KB_BASE_PATH_SET" ]; then + log_warn "KB_BASE_PATH 环境变量未设置" + echo "" + echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" + echo "建议添加到 ~/.bashrc 或 ~/.zshrc:" + echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" + echo "" + echo -e "${YELLOW}export KB_BASE_PATH=\"$KB_BASE_PATH\"${NC}" + echo "" +else + log_success "KB_BASE_PATH 已设置: $KB_BASE_PATH" +fi + +# 创建环境变量示例文件 +ENV_FILE="${SCRIPT_DIR}/.env.example" +cat > "$ENV_FILE" << 'EOF' +# KB Workflow 环境变量配置 +export KB_BASE_PATH="~/work/knowledge-base" + +# 可选: B站 Cookie（用于下载会员视频） +# export BILIBILI_COOKIE="SESSDATA=xxx; bili_jct=xxx" + +# 可选: AI 分析配置 +# export AI_API_KEY="your-api-key" +# export AI_PROVIDER="openai" # 或 zhipu, minimax +# export AI_MODEL="gpt-4" + +# 可选: Git 配置 +# export KB_GIT_USER="Your Name" +# export KB_GIT_EMAIL="your@email.com" +EOF + +log_info "环境变量示例已保存到: $ENV_FILE" + +# ============================================================================= +# 7. 完成总结 +# ============================================================================= +log_section "安装完成" + +echo "" +if [ ${#MISSING_DEPS[@]} -eq 0 ] && [ ${#MISSING_PY_PKGS[@]} -eq 0 ]; then + echo -e "${GREEN}✅ 所有依赖已安装完成！${NC}" +else + echo -e "${YELLOW}⚠️ 部分依赖需要手动安装${NC}" + echo "" + + if [ ${#MISSING_DEPS[@]} -gt 0 ]; then + echo "系统依赖:" + echo -e "${YELLOW}sudo apt-get install -y ${MISSING_DEPS[*]} tesseract-ocr-chi-sim tesseract-ocr-eng${NC}" + fi + + if [ ${#MISSING_PY_PKGS[@]} -gt 0 ]; then + echo "" + echo "Python 包:" + echo -e "${YELLOW}pip3 install --user ${MISSING_PY_PKGS[*]}${NC}" + fi +fi + +echo "" +echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" +echo "使用方法:" +echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━" +echo " export KB_BASE_PATH=\"~/work/knowledge-base\" +echo " python3 kb_workflow.py --check --url \"[URL]\"" +echo "" diff --git a/kb-workflow/kb_workflow.py b/kb-workflow/kb_workflow.py new file mode 100644 index 0000000..5c93277 --- /dev/null +++ b/kb-workflow/kb_workflow.py @@ -0,0 +1,337 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +""" +KB Workflow - Knowledge Base Workflow Orchestrator + +知识库工作流辅助工具函数。 + +此模块提供查重、文件操作、Git 管理等工具函数， +供主代理在执行 SKILL.md 中定义的 workflow 时调用。 +""" + +import os +import sys +import json +import argparse +import subprocess +import shutil +import re +from datetime import datetime +from pathlib import Path +from typing import Dict, List, Optional, Any + + +# ==================== 子技能映射 ==================== + +METADATA_AGENTS = { + "bilibili": "kb-bilibili-metadata", + "zhihu": "kb-zhihu-metadata", +} + +CONTENT_AGENTS = { + "bilibili": "kb-bilibili-content", +} + + +# ==================== 工具函数 ==================== + +def extract_platform(filename: str) -> str: + """从文件名提取平台（第一个下划线之前）""" + match = re.match(r'^([a-zA-Z0-9]+)_(.+)$', filename) + if match: + return match.group(1) + return "unknown" + + +def extract_base_name(filename: str) -> str: + """从文件名提取基础名称（去掉扩展名）""" + return Path(filename).stem + + +def get_knowledge_base_path() -> Path: + """获取知识库根目录""" + base_path_str = os.environ.get('KB_BASE_PATH', '') + if base_path_str: + return Path(base_path_str).expanduser() + return Path.home() / "work" / "knowledge-base" + + +def ensure_directories(base_path: Path = None) -> Dict[str, Path]: + """确保目录存在""" + if base_path is None: + base_path = get_knowledge_base_path() + + dirs = { + "base": base_path, + "pending": base_path / "pending", + "metadata": base_path / "metadata", + "content": base_path / "content", + "content_downloads": base_path / "content" / "downloads", + "analyzed": base_path / "analyzed", + "archive": base_path / "archive", + "archive_subscriptions": base_path / "archive" / "subscriptions", + } + + for name, dir_path in dirs.items(): + if isinstance(dir_path, Path): + dir_path.mkdir(parents=True, exist_ok=True) + + return dirs + + +def check_duplicate(base_path: Path = None, url: str = None, platform: str = None, content_id: str = None) -> Dict[str, Any]: + """查重检查""" + if base_path is None: + base_path = get_knowledge_base_path() + + metadata_dir = base_path / "metadata" + archive_dir = base_path / "archive" + + # 从URL提取ID + if url and not content_id: + bv_match = re.search(r'BV[a-zA-Z0-9]+', url) + content_id = bv_match.group() if bv_match else None + + result = {"duplicate": False, "status": None, "files": []} + + if metadata_dir.exists(): + for f in metadata_dir.iterdir(): + if f.is_file() and content_id and content_id in f.name: + result["duplicate"] = True + result["status"] = "metadata" + result["files"].append(str(f)) + + if archive_dir.exists(): + for date_dir in archive_dir.iterdir(): + if date_dir.is_dir(): + for f in date_dir.iterdir(): + if f.is_file() and content_id and content_id in f.name: + result["duplicate"] = True + result["status"] = "archived" + result["files"].append(str(f)) + + return result + + +def archive_and_git( + analyzed_file: str, + base_path: Path = None, + git_root: Path = None, + git_user: str = None, + git_email: str = None, + git_remote: str = None +) -> Dict[str, Any]: + """归档并提交Git""" + if base_path is None: + base_path = get_knowledge_base_path() + if git_root is None: + git_root = base_path / "archive" + if git_user is None: + git_user = os.environ.get('KB_GIT_USER', '') + if git_email is None: + git_email = os.environ.get('KB_GIT_EMAIL', '') + if git_remote is None: + git_remote = os.environ.get('KB_GIT_REMOTE', '') + + result = { + "success": False, + "archive_path": "", + "git_commit": False, + "git_push": None, + "error": None + } + + try: + # 1. 检查并初始化 Git 仓库 + git_dir = git_root / ".git" + if not git_dir.exists(): + # 初始化仓库 + subprocess.run(['git', 'init'], cwd=str(git_root), capture_output=True) + subprocess.run(['git', 'config', 'user.name', git_user], cwd=str(git_root)) + subprocess.run(['git', 'config', 'user.email', git_email], cwd=str(git_root)) + + # 关联远端仓库 + if git_remote: + subprocess.run(['git', 'remote', 'add', 'origin', git_remote], cwd=str(git_root), capture_output=True) + # 拉取远端分支 + subprocess.run(['git', 'fetch', 'origin'], cwd=str(git_root), capture_output=True) + # 设置 main 分支并拉取 + subprocess.run(['git', 'branch', '--set-upstream-to=origin/main', 'main'], cwd=str(git_root), capture_output=True) + subprocess.run(['git', 'pull', 'origin', 'main', '--rebase'], cwd=str(git_root), capture_output=True, timeout=120) + else: + # 已有仓库，检查远端是否配置 + if git_remote: + remote_check = subprocess.run(['git', 'remote', '-v'], cwd=str(git_root), capture_output=True, text=True) + if 'origin' not in remote_check.stdout: + subprocess.run(['git', 'remote', 'add', 'origin', git_remote], cwd=str(git_root), capture_output=True) + + # 拉取远端最新代码 + subprocess.run(['git', 'fetch', 'origin'], cwd=str(git_root), capture_output=True) + # 尝试拉取 main 分支，如果失败则尝试 master + pull_result = subprocess.run(['git', 'pull', 'origin', 'main', '--rebase'], cwd=str(git_root), capture_output=True, timeout=120) + if pull_result.returncode != 0: + subprocess.run(['git', 'pull', 'origin', 'master', '--rebase'], cwd=str(git_root), capture_output=True, timeout=120) + + # 2. 创建归档目录 + date_str = datetime.now().strftime('%Y-%m-%d') + date_dir = base_path / "archive" / date_str + date_dir.mkdir(parents=True, exist_ok=True) + + # 3. 复制分析报告 + src_file = Path(analyzed_file) + archive_file = date_dir / src_file.name + shutil.copy(src_file, archive_file) + result["archive_path"] = str(archive_file) + + # 4. 复制元数据 + meta_file = base_path / "metadata" / f"{src_file.stem}.meta.json" + if meta_file.exists(): + shutil.copy(meta_file, date_dir / meta_file.name) + + # 5. Git 提交并推送 + if (git_root / ".git").exists(): + # 添加所有变更 + subprocess.run(['git', 'add', '.'], cwd=str(git_root), capture_output=True) + + # 检查是否有变更需要提交 + status_result = subprocess.run(['git', 'status', '--porcelain'], cwd=str(git_root), capture_output=True, text=True) + + if status_result.stdout.strip(): + commit_msg = f"Archive: {src_file.name} - {datetime.now().isoformat()}" + commit_result = subprocess.run( + ['git', 'commit', '-m', commit_msg], + cwd=str(git_root), capture_output=True, text=True + ) + result["git_commit"] = commit_result.returncode == 0 + + # 推送到远端 + if git_remote and commit_result.returncode == 0: + push_result = subprocess.run( + ['git', 'push', 'origin', 'main'], + cwd=str(git_root), capture_output=True, text=True, timeout=60 + ) + if push_result.returncode != 0: + # 如果 main 分支推送失败，尝试 master + push_result = subprocess.run( + ['git', 'push', 'origin', 'master'], + cwd=str(git_root), capture_output=True, text=True, timeout=60 + ) + result["git_push"] = {"success": push_result.returncode == 0, "output": push_result.stdout} + + result["success"] = True + + except Exception as e: + result["error"] = str(e) + + return result + + +def generate_summary(url: str, stages: List[Dict], final_file: str, archive_result: Dict = None) -> str: + """生成处理完成汇报""" + # 提取视频标题（如果有） + title_match = re.search(r'com/video/([^?]+)', url) + title = title_match.group(1) if title_match else "未知" + + summary = f""" +✅ **处理完成！** + +**视频:** {title} + +**处理阶段:** +""" + for stage in stages: + stage_name = stage.get('stage', 'unknown') + emoji = "✓" if stage.get('success') else "○" + summary += f"{emoji} {stage_name}\n" + + if final_file: + summary += f"\n**最终文件:** `{final_file}`" + + if archive_result: + if archive_result.get('git_commit'): + summary += f"\n**Git:** 已提交" + if archive_result.get('git_push', {}).get('success'): + summary += " ✓" + elif archive_result.get('git_push'): + summary += " ✗" + + return summary + + +# ==================== CLI ==================== + +def main(): + """CLI入口 - 用于命令行测试""" + parser = argparse.ArgumentParser( + description='KB Workflow - Knowledge Base Workflow Orchestrator', + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +使用示例: + # 查重 + python kb_workflow.py --check --url "https://www.bilibili.com/video/BVxxx" + + # 归档 + python kb_workflow.py --archive "/path/to/analyzed.md" + """ + ) + + parser.add_argument('--check', action='store_true', help='查重') + parser.add_argument('--url', type=str, help='要检查的URL') + parser.add_argument('--archive-file', type=str, help='归档的文件路径') + parser.add_argument('--base-path', type=str, help='获取知识库根目录') + + parser.add_argument('--pending', action='store_true', help='获取url解析目录') + parser.add_argument('--metadata', action='store_true', help='获取元数据目录') + parser.add_argument('--content', action='store_true', help='获取内容目录') + parser.add_argument('--content_downloads', action='store_true', help='获取主内容下载目录') + parser.add_argument('--analyzed', action='store_true', help='获取深度分析目录') + parser.add_argument('--archive_dir', action='store_true', help='获取归档目录') + parser.add_argument('--archive_subscriptions', action='store_true', help='获取订阅信息目录') + parser.add_argument('--extract_platform', type=str, help='要提取平台名称的文件名') + args = parser.parse_args() + + base_path = Path(args.base_path) if args.base_path else None + dirs = ensure_directories(base_path) + + if args.check and args.url: + result = check_duplicate(base_path, args.url) + print(json.dumps(result, ensure_ascii=False, indent=2)) + + elif args.archive_file: + result = archive_and_git(args.archive_file, base_path) + print(json.dumps(result, ensure_ascii=False, indent=2)) + + elif args.pending: + print(json.dumps({"path": str(dirs["pending"])}, ensure_ascii=False, indent=2)) + + elif args.metadata: + print(json.dumps({"path": str(dirs["metadata"])}, ensure_ascii=False, indent=2)) + + elif args.content: + print(json.dumps({"path": str(dirs["content"])}, ensure_ascii=False, indent=2)) + + elif args.content_downloads: + print(json.dumps({"path": str(dirs["content_downloads"])}, ensure_ascii=False, indent=2)) + + elif args.analyzed: + print(json.dumps({"path": str(dirs["analyzed"])}, ensure_ascii=False, indent=2)) + + elif args.archive_dir: + print(json.dumps({"path": str(dirs["archive"])}, ensure_ascii=False, indent=2)) + + elif args.archive_subscriptions: + print(json.dumps({"path": str(dirs["archive_subscriptions"])}, ensure_ascii=False, indent=2)) + + elif args.extract_platform: + platform = extract_platform(args.extract_platform) + print(json.dumps({"platform": platform}, ensure_ascii=False, indent=2)) + + elif args.base_path: + print(json.dumps({"path": str(dirs["base"])}, ensure_ascii=False, indent=2)) + + else: + parser.print_help() + + +if __name__ == '__main__': + main() diff --git a/kb-zhihu-metadata/SKILL.md b/kb-zhihu-metadata/SKILL.md new file mode 100644 index 0000000..d4e77d7 --- /dev/null +++ b/kb-zhihu-metadata/SKILL.md @@ -0,0 +1,44 @@ +# KB Zhihu Metadata Skill + +**kb-zhihu-metadata** - Extract Zhihu question/answer/user metadata. + +## Features + +- Question metadata extraction +- Answer metadata extraction +- User information extraction +- JSON output format +- Markdown conversion support + +## Commands + +```bash +# Question metadata +python zhihu_metadata.py --id "266309957" --type question + +# Answer metadata +python zhihu_metadata.py --id "2003427891925509507" --type answer +``` + +## Output + +```json +{ + "success": true, + "data": { + "platform": "zhihu", + "type": "question", + "id": "266309957", + "title": "问题标题", + "author": "作者名字", + "answer_count": 50, + "followers": 1000 + } +} +``` + +## Installation + +```bash +cp -r kb-zhihu-metadata/ ~/skills/ +``` diff --git a/kb-zhihu-metadata/markdown_converter.py b/kb-zhihu-metadata/markdown_converter.py new file mode 100644 index 0000000..c0f912d --- /dev/null +++ b/kb-zhihu-metadata/markdown_converter.py @@ -0,0 +1,17 @@ +from markdownify import MarkdownConverter as _MarkdownConverter + +class MarkdownConverter: + """HTML 转 Markdown 转换器，保留完整格式""" + + def __init__(self): + self.converter = _MarkdownConverter( + heading_style="ATX", + bullets="*,-", + code_blocks=True, + tables=True, + strip=["script", "style", "nav", "footer", "aside"] + ) + + def convert(self, html: str) -> str: + """转换 HTML 为 Markdown""" + return self.converter.convert(html) diff --git a/kb-zhihu-metadata/zhihu_extractor.py b/kb-zhihu-metadata/zhihu_extractor.py new file mode 100644 index 0000000..f917f79 --- /dev/null +++ b/kb-zhihu-metadata/zhihu_extractor.py @@ -0,0 +1,335 @@ +""" +知乎 Playwright 内容提取器 +使用 Playwright 浏览器自动化工具抓取知乎内容 +""" + +import re +import sys +import os +from typing import Dict, Optional, Any +from urllib.parse import urlparse + +# 添加当前目录到 Python 路径以支持绝对导入 +current_dir = os.path.dirname(os.path.abspath(__file__)) +if current_dir not in sys.path: + sys.path.insert(0, current_dir) + +try: + from .markdown_converter import MarkdownConverter +except ImportError: + from markdown_converter import MarkdownConverter + + +class PlaywrightBrowser: + """Playwright 浏览器管理器""" + + def __init__(self, headless: bool = True, timeout: int = 30): + self.headless = headless + self.timeout = timeout * 1000 + self.browser = None + self.context = None + self.page = None + + def start(self): + """启动浏览器""" + from playwright.sync_api import sync_playwright + self.playwright = sync_playwright().start() + self.browser = self.playwright.chromium.launch(headless=self.headless) + self.context = self.browser.new_context( + user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36' + ) + self.page = self.context.new_page() + self.page.set_default_timeout(self.timeout) + + def close(self): + """关闭浏览器""" + if self.page: + self.page.close() + if self.context: + self.context.close() + if self.browser: + self.browser.close() + if hasattr(self, 'playwright'): + self.playwright.stop() + + def goto(self, url: str, wait_until: str = "networkidle"): + """导航到指定URL""" + return self.page.goto(url, wait_until=wait_until) + + def wait_for_selector(self, selector: str, timeout: int = None): + """等待选择器出现""" + timeout_ms = timeout * 1000 if timeout else self.timeout + return self.page.wait_for_selector(selector, timeout=timeout_ms) + + def query_selector(self, selector: str): + """查询选择器""" + return self.page.query_selector(selector) + + def query_selector_all(self, selector: str): + """查询所有匹配的选择器""" + return self.page.query_selector_all(selector) + + def evaluate(self, script: str): + """执行 JavaScript 代码""" + return self.page.evaluate(script) + + +class ZhihuPlaywrightExtractor: + """知乎内容提取器 - 使用 Playwright""" + + URL_PATTERNS = { + 'zvideo': r'zhihu\.com/zvideo/(\d+)', + 'zhuanlan': r'zhuanlan\.zhihu\.com/p/(\d+)', + } + + def __init__(self, headless: bool = True, timeout: int = 30): + """ + 初始化提取器 + + Args: + headless: 是否使用无头浏览器 + timeout: 超时时间（秒） + """ + self.browser = PlaywrightBrowser(headless=headless, timeout=timeout) + self.markdown_converter = MarkdownConverter() + + def identify_url_type(self, url: str) -> Optional[str]: + """ + 识别 URL 类型 + + Returns: + 'answer', 'article', 'question' 或 None + """ + for url_type, pattern in self.URL_PATTERNS.items(): + if re.search(pattern, url): + return url_type + return None + + def extract_id(self, url: str) -> Optional[str]: + """ + 从 URL 中提取内容 ID + + Returns: + 内容 ID 或 None + """ + url_type = self.identify_url_type(url) + if url_type: + pattern = self.URL_PATTERNS[url_type] + match = re.search(pattern, url) + if match: + return match.group(1) + return None + + def _extract_text_content(self, element) -> str: + """提取元素的文本内容""" + if element is None: + return '' + return element.inner_text() if hasattr(element, 'inner_text') else '' + + def _extract_html_content(self, element) -> str: + """提取元素的 HTML 内容""" + if element is None: + return '' + return element.inner_html() if hasattr(element, 'inner_html') else '' + + def _extract_zvideo_content(self) -> Dict[str, Any]: + """提取知乎视频内容""" + result = { + 'type': 'zvideo', + 'title': '', + 'author': '', + 'content': '', + 'content_markdown': '', + 'publish_time': '', + 'vote_up': 0, + } + + # 打印页面标题用于调试 + page_title = self.browser.page.title() + print(f"页面标题: {page_title}") + + # 提取视频标题 + title_elem = self.browser.query_selector('.VideoPlaylistInfo-title') + if title_elem: + result['title'] = self._extract_text_content(title_elem) + + # 备用：尝试其他选择器 + if not result['title']: + title_elem = self.browser.query_selector('h1') + if title_elem: + result['title'] = self._extract_text_content(title_elem) + + # 提取作者信息 + author_elem = self.browser.query_selector('.AuthorInfo-name') + if author_elem: + result['author'] = self._extract_text_content(author_elem) + + # 提取视频描述 + desc_elem = self.browser.query_selector('.Video-desc') + if desc_elem: + html_content = self._extract_html_content(desc_elem) + result['content'] = html_content + result['content_markdown'] = self.markdown_converter.convert(html_content) + + # 提取发布时间 + time_elem = self.browser.query_selector('.Video-meta time') + if time_elem: + result['publish_time'] = time_elem.get_attribute('datetime') or self._extract_text_content(time_elem) + + # 提取点赞数 + vote_elem = self.browser.query_selector('.VideoLikeButton-count') + if vote_elem: + vote_text = self._extract_text_content(vote_elem) + try: + result['vote_up'] = int(vote_text.replace(',', '')) + except (ValueError, AttributeError): + pass + + return result + + def _extract_zhuanlan_content(self) -> Dict[str, Any]: + """提取知乎专栏文章内容""" + result = { + 'type': 'zhuanlan', + 'title': '', + 'author': '', + 'content': '', + 'content_markdown': '', + 'publish_time': '', + 'vote_up': 0, + } + + # 打印页面标题用于调试 + page_title = self.browser.page.title() + print(f"页面标题: {page_title}") + + # 提取文章标题 + title_elem = self.browser.query_selector('.Post-Title') + if title_elem: + result['title'] = self._extract_text_content(title_elem) + + # 备用 + if not result['title']: + title_elem = self.browser.query_selector('h1') + if title_elem: + result['title'] = self._extract_text_content(title_elem) + + # 提取作者信息 + author_elem = self.browser.query_selector('.AuthorInfo-name') + if author_elem: + result['author'] = self._extract_text_content(author_elem) + + # 提取文章内容 + content_elem = self.browser.query_selector('.Post-RichText') + if content_elem: + html_content = self._extract_html_content(content_elem) + result['content'] = html_content + result['content_markdown'] = self.markdown_converter.convert(html_content) + + # 提取发布时间 + time_elem = self.browser.query_selector('.ContentItem-time') + if time_elem: + result['publish_time'] = time_elem.get_attribute('data-tooltip') or self._extract_text_content(time_elem) + + # 提取点赞数 + vote_elem = self.browser.query_selector('.VoteButton--up .VoteButton-label') + if vote_elem: + vote_text = self._extract_text_content(vote_elem) + try: + result['vote_up'] = int(vote_text.replace(',', '')) + except (ValueError, AttributeError): + pass + + return result + + def extract(self, url: str) -> Optional[Dict[str, Any]]: + """ + 从 URL 提取知乎内容 + + Args: + url: 知乎 URL + + Returns: + 包含提取内容的字典，结构如下: + { + 'type': 'zvideo' | 'zhuanlan', + 'title': str, + 'author': str, + 'content': str (HTML), + 'content_markdown': str (Markdown), + 'publish_time': str, + 'vote_up': int, + } + 如果提取失败返回 None + """ + try: + # 识别 URL 类型 + url_type = self.identify_url_type(url) + if not url_type: + print(f"无法识别 URL 类型: {url}") + return None + + print(f"URL 类型: {url_type}") + print(f"启动浏览器...") + + # 启动浏览器 + self.browser.start() + + print(f"访问页面: {url}") + # 访问页面 + self.browser.goto(url, wait_until="domcontentloaded") + + print("等待页面加载...") + import time + time.sleep(3) # 等待 JavaScript 执行 + + # 根据类型提取内容 + if url_type == 'zvideo': + result = self._extract_zvideo_content() + elif url_type == 'zhuanlan': + result = self._extract_zhuanlan_content() + else: + print(f"不支持的类型: {url_type}") + return None + + # 添加额外信息 + result['url'] = url + result['content_id'] = self.extract_id(url) + + print(f"提取成功! 标题: {result.get('title', '')[:50]}...") + return result + + except Exception as e: + print(f"提取知乎内容时出错: {e}") + import traceback + traceback.print_exc() + return None + finally: + # 关闭浏览器 + self.browser.close() + + def __enter__(self): + """上下文管理器入口""" + return self + + def __exit__(self, exc_type, exc_val, exc_tb): + """上下文管理器出口""" + self.browser.close() + return False + + +# 便捷函数 +def extract_zhihu_content(url: str, headless: bool = True, timeout: int = 30) -> Optional[Dict[str, Any]]: + """ + 便捷函数：提取知乎内容 + + Args: + url: 知乎 URL + headless: 是否使用无头浏览器 + timeout: 超时时间（秒） + + Returns: + 提取的内容字典 + """ + with ZhihuPlaywrightExtractor(headless=headless, timeout=timeout) as extractor: + return extractor.extract(url) diff --git a/kb-zhihu-metadata/zhihu_metadata.py b/kb-zhihu-metadata/zhihu_metadata.py new file mode 100644 index 0000000..fcff2b1 --- /dev/null +++ b/kb-zhihu-metadata/zhihu_metadata.py @@ -0,0 +1,153 @@ +#!/usr/bin/env python3 +""" +知乎元数据获取工具 + +仅支持两种内容类型： +- zvideo: 知乎视频 (https://www.zhihu.com/zvideo/xxx) +- zhuanlan: 知乎专栏文章 (https://zhuanlan.zhihu.com/p/xxx) +""" + +import argparse +import json +import sys +import os +from typing import Dict, Optional, Any + +# 添加当前目录到 Python 路径 +current_dir = os.path.dirname(os.path.abspath(__file__)) +if current_dir not in sys.path: + sys.path.insert(0, current_dir) + +from zhihu_extractor import ZhihuPlaywrightExtractor + + +def extract_zvideo(video_id: str, headless: bool = True) -> Dict[str, Any]: + """ + 获取知乎视频元数据 + + Args: + video_id: 视频 ID (数字字符串) + headless: 是否使用无头浏览器 + + Returns: + 视频元数据字典 + """ + url = f"https://www.zhihu.com/zvideo/{video_id}" + return _extract_metadata(url, "zvideo", headless) + + +def extract_zhuanlan(article_id: str, headless: bool = True) -> Dict[str, Any]: + """ + 获取知乎专栏文章元数据 + + Args: + article_id: 文章 ID (数字字符串) + headless: 是否使用无头浏览器 + + Returns: + 文章元数据字典 + """ + url = f"https://zhuanlan.zhihu.com/p/{article_id}" + return _extract_metadata(url, "zhuanlan", headless) + + +def _extract_metadata(url: str, content_type: str, headless: bool) -> Dict[str, Any]: + """ + 内部函数：提取元数据 + + Args: + url: 知乎 URL + content_type: 内容类型 (zvideo/zhuanlan) + headless: 是否使用无头浏览器 + + Returns: + 元数据字典 + """ + extractor = ZhihuPlaywrightExtractor(headless=headless) + result = extractor.extract(url) + + if result: + # 标准化输出格式 + metadata = { + "type": content_type, + "id": result.get("content_id", ""), + "url": result.get("url", url), + "title": result.get("title", ""), + "author": result.get("author", ""), + "publish_time": result.get("publish_time", ""), + "vote_up": result.get("vote_up", 0), + "content_markdown": result.get("content_markdown", ""), + "raw_html": result.get("content", ""), + } + return metadata + else: + return { + "type": content_type, + "error": "Failed to extract content", + "url": url + } + + +def main(): + """命令行入口""" + parser = argparse.ArgumentParser( + description="知乎元数据获取工具", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +支持的类型: + zvideo - 知乎视频 (https://www.zhihu.com/zvideo/123456) + zhuanlan - 知乎专栏文章 (https://zhuanlan.zhihu.com/p/123456) + +示例: + python zhihu_metadata.py --id "123456" --type zvideo + python zhihu_metadata.py --id "123456" --type zhuanlan + """ + ) + + parser.add_argument( + "--id", "-i", + required=True, + help="知乎内容 ID (视频ID或文章ID)" + ) + + parser.add_argument( + "--type", "-t", + required=True, + choices=["zvideo", "zhuanlan"], + help="内容类型: zvideo=视频, zhuanlan=专栏文章" + ) + + parser.add_argument( + "--output", "-o", + default=None, + help="输出文件路径 (默认: stdout)" + ) + + parser.add_argument( + "--headless", + action="store_true", + default=True, + help="使用无头浏览器模式 (默认: True)" + ) + + args = parser.parse_args() + + # 提取元数据 + if args.type == "zvideo": + result = extract_zvideo(args.id, headless=args.headless) + else: # zhuanlan + result = extract_zhuanlan(args.id, headless=args.headless) + + # 输出结果 + json_output = json.dumps(result, ensure_ascii=False, indent=2) + + if args.output: + with open(args.output, 'w', encoding='utf-8') as f: + f.write(json_output) + print(f"结果已保存到: {args.output}") + else: + print(json_output) + + +if __name__ == "__main__": + main()