feat(kb-bilibili-metadata): Add series/readlist/favlist metadata extraction

- Add extract_series_async() for series collection metadata - Add extract_readlist_async() for article list metadata - Add extract_favlist_async() for favorite list metadata - Add CLI support for new types: series, readlist, favlist - Update bilibili_metadata.py with new extraction functions - Add --mid parameter for series type Note: These types record basic info and subscription status only, not the full content list (which may be large).
2026-02-10 14:27:14 +08:00
parent 51347f671b
commit 4cdbc825ce
2 changed files with 225 additions and 1 deletions
@@ -431,6 +431,174 @@ class BilibiliExtractor:
        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__':
@@ -7,6 +7,7 @@ B站元数据提取 CLI 工具
 """

 import argparse
+import asyncio
 import json
 import sys
 from typing import Dict, Any
@@ -58,6 +59,39 @@ def extract_up(extractor: BilibiliExtractor, mid: str, output_file: str = None)
    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(
@@ -74,6 +108,15 @@ def main():
  # 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
        """
@@ -87,9 +130,13 @@ def main():
    parser.add_argument(
        '--type', 
        required=True,
-        choices=['video', 'article', 'up'],
+        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',
@@ -127,6 +174,15 @@ def main():
            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("错误: series类型需要提供 --mid 参数")
+                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(f"错误: 不支持的类型 {args.type}")
            sys.exit(1)