feat: 添加 MediaCrawler 整合支持

- kb-zhihu-metadata: 新增 zhihu_article_crawler.py 支持爬取知乎专栏文章 - kb-zhihu-content: 添加 article-from-media 类型支持从 MediaCrawler 数据读取 - 更新 SKILL.md 文档说明新功能
2026-02-27 17:42:21 +08:00
parent 85797d0a89
commit 193d2b375d
4 changed files with 423 additions and 23 deletions
@@ -6,6 +6,7 @@

 - Video download using **yt-dlp**
 - Subtitle extraction (returns no subtitle, triggers Whisper)
+- **Read article content from MediaCrawler data** (NEW!)
 - Supports `ZHIHU_COOKIE` environment variable

 ## Environment Variables
@@ -22,20 +23,60 @@ python zhihu_content.py --id "12345678" --type video --output "/path/to/download

 # Extract subtitle (returns no subtitle, triggers Whisper)
 python zhihu_content.py --id "12345678" --type subtitle --output "/path/to/subtitles/"
+
+# 从 MediaCrawler 读取文章内容 (⚡ NEW!)
+python zhihu_content.py --type article-from-media --input "~/work/MediaCrawler/data/zhihu/json/detail_contents_2026-02-27.json" --output "~/work/knowledge-base/data/zhihu/"
 ```

-## Output
+## MediaCrawler 数据读取
+
+**新功能**：从 MediaCrawler 爬取的数据中提取知乎文章内容
+
+### 使用方法
+
+```bash
+# 从 MediaCrawler JSON 文件读取文章内容
+python zhihu_content.py --type article-from-media \
+    --input "~/work/MediaCrawler/data/zhihu/json/detail_contents_2026-02-27.json" \
+    --output "~/work/knowledge-base/data/zhihu/"
+
+# 查找最新的爬取数据
+python zhihu_content.py --type article-from-media \
+    --output "~/work/knowledge-base/data/zhihu/"
+```
+
+### 参数说明
+
+| 参数 | 说明 |
+|------|------|
+| `--type article-from-media` | 从 MediaCrawler 数据读取 |
+| `--input` | MediaCrawler 输出文件路径（可选，不指定则自动查找最新） |
+| `--output` | 输出目录 |
+
+### 输出格式

 ```json
 {
  "success": true,
-  "type": "video",
-  "filename": "video_title.mp4",
-  "filepath": "/path/to/downloads/video_title.mp4",
-  "message": "下载完成: video_title.mp4"
+  "type": "article",
+  "filename": "zhihu_article_如何高效的爬取微信公众号.md",
+  "filepath": "/home/xxx/work/knowledge-base/data/zhihu/zhihu_article_如何高效的爬取微信公众号.md",
+  "message": "文章内容已导出"
 }
 ```

+## 原有功能
+
+### Video Download
+
+Video download uses **yt-dlp**:
+1. Parses `ZHIHU_COOKIE` environment variable (optional)
+2. Creates temporary Netscape-format cookie file
+3. Runs `yt-dlp -f best -o <output> <url>`
+4. Cleans up temporary file
+
+**Note**: 知乎视频通常没有官方字幕，将自动触发 Whisper 语音识别
+
 ## Installation

 ```bash
@@ -43,16 +84,3 @@ python zhihu_content.py --id "12345678" --type subtitle --output "/path/to/subti
 # Ensure yt-dlp is installed
 pip install yt-dlp aiohttp
 ```
-
-## How It Works
-
-Video download uses **yt-dlp**:
-1. Parses `ZHIHU_COOKIE` environment variable (optional)
-2. Creates temporary Netscape-format cookie file
-3. Runs `yt-dlp -f best -o <output> <url>`
-4. Cleans up temporary file
-
-## Notes
-
- 知乎视频通常没有官方字幕，将自动触发 Whisper 语音识别
- 视频下载需要能访问知乎（可能需要代理）
@@ -5,6 +5,7 @@

 支持：
 - zvideo: 知乎视频下载
+- article-from-media: 从 MediaCrawler 数据读取知乎文章
 - 从页面提取视频播放地址
 """

@@ -13,6 +14,7 @@ import asyncio
 import json
 import os
 import re
+import shutil
 import subprocess
 import sys
 import tempfile
@@ -21,6 +23,10 @@ from pathlib import Path
 from typing import Optional, Dict, Any, List


+# MediaCrawler 目录
+MEDIACRAWLER_DIR = Path.home() / "work" / "MediaCrawler"
+
+
 class ZhihuContent:
    """知乎内容获取器"""

@@ -146,13 +152,113 @@ class ZhihuContent:

        return result

+    def read_article_from_mediacrawler(self, input_file: str = None, output_dir: str = None) -> Dict[str, Any]:
+        """
+        从 MediaCrawler 爬取的数据中读取知乎文章内容
+        
+        Args:
+            input_file: MediaCrawler 输出文件路径，不指定则自动查找最新
+            output_dir: 输出目录
+        
+        Returns:
+            处理结果字典
+        """
+        # 确定输出目录
+        if output_dir:
+            self.output_dir = Path(output_dir)
+            self.output_dir.mkdir(parents=True, exist_ok=True)
+        
+        # 查找数据文件
+        data_dir = MEDIACRAWLER_DIR / "data" / "zhihu" / "json"
+        
+        if input_file:
+            # 使用指定的文件
+            json_file = Path(input_file)
+            if not json_file.exists():
+                return {"success": False, "message": f"文件不存在: {input_file}"}
+        else:
+            # 查找最新的数据文件
+            json_files = sorted(data_dir.glob("detail_contents_*.json"), reverse=True)
+            if not json_files:
+                return {"success": False, "message": "未找到 MediaCrawler 爬取的数据，请先运行爬虫"}
+            json_file = json_files[0]
+        
+        try:
+            with open(json_file, encoding="utf-8") as f:
+                data = json.load(f)
+            
+            if not data:
+                return {"success": False, "message": "数据文件为空"}
+            
+            # 提取第一篇文章
+            item = data[0]
+            
+            # 准备数据
+            title = item.get("title", "无标题")
+            content = item.get("content_text", "")
+            url = item.get("content_url", "")
+            author = item.get("user_nickname", "未知")
+            created_ts = item.get("created_time", 0)
+            created = datetime.fromtimestamp(created_ts).strftime("%Y-%m-%d %H:%M:%S") if created_ts else ""
+            voteup = item.get("voteup_count", 0)
+            comments = item.get("comment_count", 0)
+            
+            # 生成文件名
+            safe_title = "".join(c for c in title if c.isalnum() or c in " -_")[:50]
+            filename = f"zhihu_article_{safe_title}.md"
+            output_path = self.output_dir / filename
+            
+            # 写入 Markdown 文件
+            markdown_content = f"""---
+title: "{title}"
+author: "{author}"
+url: "{url}"
+created: "{created}"
+voteup: {voteup}
+comments: {comments}
+platform: zhihu
+type: article
+---
+
+# {title}
+
+**作者**: {author}  
+**来源**: [知乎]({url})  
+**发布时间**: {created}  
+**点赞**: {voteup}  
+**评论**: {comments}
+
+---
+
+{content}
+"""
+            
+            with open(output_path, "w", encoding="utf-8") as f:
+                f.write(markdown_content)
+            
+            return {
+                "success": True,
+                "type": "article",
+                "title": title,
+                "filename": filename,
+                "filepath": str(output_path),
+                "content_length": len(content),
+                "message": f"文章内容已导出: {title}"
+            }
+            
+        except Exception as e:
+            return {"success": False, "message": f"读取失败: {str(e)}"}
+

 async def main():
    parser = argparse.ArgumentParser(description='知乎内容获取工具')
-    parser.add_argument('--id', '-i', required=True, help='知乎视频ID')
-    parser.add_argument('--type', '-t', required=True, choices=['video', 'subtitle'], help='内容类型')
+    parser.add_argument('--id', '-i', help='知乎视频ID (用于 video/subtitle 类型)')
+    parser.add_argument('--type', '-t', required=True, 
+                        choices=['video', 'subtitle', 'article-from-media'], 
+                        help='内容类型: video=视频下载, subtitle=字幕提取, article-from-media=从MediaCrawler读取文章')
    parser.add_argument('--output', '-o', default='./output', help='输出目录')
    parser.add_argument('--quality', '-q', type=int, default=720, help='视频质量')
+    parser.add_argument('--input', '-in', help='MediaCrawler 数据文件路径 (用于 article-from-media 类型)')

    args = parser.parse_args()

@@ -161,8 +267,16 @@ async def main():

    if args.type == 'video':
        result = await downloader.download_video(args.id, quality=args.quality)
-    else:
+    elif args.type == 'subtitle':
        result = await downloader.extract_subtitle(args.id)
+    elif args.type == 'article-from-media':
+        # 同步调用，不需要 asyncio
+        result = downloader.read_article_from_mediacrawler(
+            input_file=args.input, 
+            output_dir=args.output
+        )
+    else:
+        result = {"success": False, "message": f"不支持的类型: {args.type}"}

    # 统一输出格式
    if result.get("success"):
@@ -170,10 +284,14 @@ async def main():
            "success": True,
            "type": args.type,
            "has_subtitle": result.get("has_subtitle", False),
-            "filename": Path(result.get('filepath', '')).name if result.get('filepath') else None,
+            "filename": result.get('filename') or (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')
        }
+        if result.get('title'):
+            output['title'] = result['title']
+        if result.get('content_length'):
+            output['content_length'] = result['content_length']
    else:
        output = {
            "success": False,