openclaw-skills/skills/kb-bilibili-content/video_downloader.py

#!/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")