在Rankings_list数据库里面添加三个字段：合集作者，合集描述，合集总集数

backend/handlers/Rankings/rank_data_scraper.py

@@ -481,10 +481,13 @@ class DouyinPlayVVScraper:
                     if len(self.play_vv_items) < 3:
                         logging.info(f"=== 调试：合集对象结构 ===")
                         logging.info(f"完整对象键: {list(obj.keys())}")
-                        # 查找可能的视频相关字段
+                        # 查找可能的视频相关字段和新增字段
                         for key, value in obj.items():
                             if 'aweme' in key.lower() or 'video' in key.lower() or 'item' in key.lower() or 'ids' in key.lower():
                                 logging.info(f"可能的视频字段 {key}: {type(value)} - {str(value)[:200]}")
+                            # 检查新增字段相关的键
+                            elif any(keyword in key.lower() for keyword in ['author', 'creator', 'user', 'desc', 'description', 'total', 'count', 'episode']):
+                                logging.info(f"可能的新字段 {key}: {type(value)} - {str(value)[:200]}")
                         
                         # 特别检查ids字段
                         if 'ids' in obj:
@@ -539,6 +542,112 @@ class DouyinPlayVVScraper:
                                 elif isinstance(pic, str):
                                     cover_image_url = pic
 
+                            # 提取新增的三个字段
+                            series_author = ""
+                            desc = ""
+                            updated_to_episode = 0
+
+                            # 提取合集作者/影视工作室
+                            if 'author' in obj:
+                                author = obj['author']
+                                if isinstance(author, dict):
+                                    # 尝试多个可能的作者字段
+                                    series_author = (author.get('nickname') or 
+                                                   author.get('unique_id') or 
+                                                   author.get('short_id') or 
+                                                   author.get('name') or '')
+                                elif isinstance(author, str):
+                                    series_author = author
+                            elif 'creator' in obj:
+                                creator = obj['creator']
+                                if isinstance(creator, dict):
+                                    series_author = (creator.get('nickname') or 
+                                                   creator.get('unique_id') or 
+                                                   creator.get('name') or '')
+                                elif isinstance(creator, str):
+                                    series_author = creator
+                            elif 'user' in obj:
+                                user = obj['user']
+                                if isinstance(user, dict):
+                                    series_author = (user.get('nickname') or 
+                                                   user.get('unique_id') or 
+                                                   user.get('name') or '')
+                                elif isinstance(user, str):
+                                    series_author = user
+
+                            # 提取合集描述 - 扩展更多可能的字段
+                            description_fields = ['desc', 'share_info']  # 保持字段列表
+                            
+                            # 先检查desc字段
+                            if 'desc' in obj and obj['desc']:
+                                desc_value = str(obj['desc']).strip()
+                                if desc_value:
+                                    desc = desc_value
+                                    logging.info(f"从desc提取到描述")
+                            
+                            # 如果desc中没有找到有效描述，检查share_info
+                            if not desc and 'share_info' in obj and isinstance(obj['share_info'], dict):
+                                share_desc = obj['share_info'].get('share_desc', '').strip()
+                                if share_desc:
+                                    desc = share_desc
+                                    logging.info(f"从share_info.share_desc提取到描述")
+                            
+                            # 如果share_info中没有找到有效描述，继续检查desc字段
+                            if not desc:
+                                for field in description_fields:
+                                    if field in obj and obj[field]:
+                                        desc_value = str(obj[field]).strip()
+                                        if desc_value:
+                                            desc = desc_value
+                                            logging.info(f"从{field}提取到描述")
+                                            break
+                            
+                            # 如果还没有找到描述，尝试从嵌套对象中查找desc字段
+                            if not desc:
+                                def search_nested_desc(data, depth=0):
+                                    if depth > 3:  # 限制递归深度
+                                        return None
+                                    
+                                    if isinstance(data, dict):
+                                        # 检查当前层级的desc字段
+                                        if 'desc' in data and data['desc']:
+                                            desc_value = str(data['desc']).strip()
+                                            if 5 <= len(desc_value) <= 1000:
+                                                return desc_value
+                                        
+                                        # 递归检查嵌套对象
+                                        for value in data.values():
+                                            if isinstance(value, dict):
+                                                nested_result = search_nested_desc(value, depth + 1)
+                                                if nested_result:
+                                                    return nested_result
+                                    return None
+                                
+                                desc = search_nested_desc(obj)
+                        
+
+                            # 提取合集总集数 - 从statis字段中获取
+                            updated_to_episode = 0  # 初始化默认值
+                            if 'statis' in obj and isinstance(obj['statis'], dict):
+                                statis = obj['statis']
+                                if 'updated_to_episode' in statis:
+                                    try:
+                                        episodes = int(statis['updated_to_episode'])
+                                        if episodes > 0:
+                                            updated_to_episode = episodes
+                                            logging.info(f"从statis.updated_to_episode提取到集数: {episodes}")
+                                    except ValueError:
+                                        logging.warning("updated_to_episode字段值无法转换为整数")
+                            else:
+                                logging.info("未找到statis字段或statis不是字典类型")
+                                try:
+                                    episodes = int(obj['updated_to_episode'])
+                                    if episodes > 0:
+                                        updated_to_episode = episodes
+                                        logging.info(f"从updated_to_episode提取到集数: {episodes}")
+                                except ValueError:
+                                    pass  # 忽略无法转换为整数的情况
+
                             self.play_vv_items.append({
                                 'play_vv': vv,
                                 'formatted': self.format_count(vv),
@@ -549,9 +658,18 @@ class DouyinPlayVVScraper:
                                 'mix_id': mix_id,  # 合集ID
                                 'cover_image_url': cover_image_url,  # 合集封面图片主链接（完整URL）
                                 'cover_backup_urls': cover_image_backup_urls,  # 封面图片备用链接列表
+                                'series_author': series_author,  # 合集作者/影视工作室
+                                'desc': desc,  # 合集描述
+                                'updated_to_episode': updated_to_episode,  # 合集总集数
                                 'timestamp': datetime.now().isoformat()
                             })
                             logging.info(f'提取到合集: {mix_name} (ID: {mix_id}) - {vv:,} 播放量')
+                            if series_author:
+                                logging.info(f'  作者: {series_author}')
+                            if desc:
+                                logging.info(f'  描述: {desc[:100]}{"..." if len(desc) > 100 else ""}')
+                            if updated_to_episode > 0:
+                                logging.info(f'  总集数: {updated_to_episode}')
                 
                 # 递归搜索子对象
                 for key, value in obj.items():
@@ -567,17 +685,21 @@ class DouyinPlayVVScraper:
     
     def _extract_from_text_regex(self, text: str, source_url: str, request_id: str = None):
         """使用正则表达式从文本中提取信息"""
-        # 查找包含完整合集信息的JSON片段
+        # 查找包含完整合集信息的JSON片段，包括statis中的updated_to_episode
-        mix_pattern = r'\{[^{}]*"mix_id"\s*:\s*"([^"]*)"[^{}]*"mix_name"\s*:\s*"([^"]*)"[^{}]*"statis"\s*:\s*\{[^{}]*"play_vv"\s*:\s*(\d+)[^{}]*\}[^{}]*\}'
+        mix_pattern = r'\{[^{}]*"mix_id"\s*:\s*"([^"]*)"[^{}]*"mix_name"\s*:\s*"([^"]*)"[^{}]*"statis"\s*:\s*\{[^{}]*"play_vv"\s*:\s*(\d+)[^{}]*"updated_to_episode"\s*:\s*(\d+)[^{}]*\}[^{}]*\}'
         
         for match in re.finditer(mix_pattern, text):
             try:
                 mix_id = match.group(1)
                 mix_name = match.group(2)
                 vv = int(match.group(3))
+                episodes = int(match.group(4))
                 
                 # 构建合集链接
                 video_url = f"https://www.douyin.com/collection/{mix_id}" if mix_id else ""
+                
+                if episodes > 0:
+                    logging.info(f"从statis.updated_to_episode提取到集数: {episodes}")
 
                 self.play_vv_items.append({
                     'play_vv': vv,
@@ -587,6 +709,7 @@ class DouyinPlayVVScraper:
                     'mix_name': mix_name,
                     'video_url': video_url,  # 合集链接
                     'mix_id': mix_id,  # 合集ID
+                    'updated_to_episode': episodes if episodes > 0 else None,  # 从statis.updated_to_episode提取的集数
                     'timestamp': datetime.now().isoformat()
                 })
                 logging.info(f'正则提取到合集: {mix_name} (ID: {mix_id}) - {vv:,} 播放量')
@@ -607,6 +730,7 @@ class DouyinPlayVVScraper:
                         'mix_name': '',  # 未知合集名称
                         'video_url': '',  # 未知链接
                         'mix_id': '',  # 未知mix_id
+                        'updated_to_episode': None,  # 未知集数
                         'timestamp': datetime.now().isoformat()
                     })
             except Exception:
@@ -871,7 +995,7 @@ class DouyinPlayVVScraper:
                     # 没有封面图片，使用空字符串
                     permanent_cover_url = ''
                 
-                # 保留用户要求的7个字段 + cover_image_url作为合集封面图片完整链接
+                # 保留用户要求的7个字段 + cover_image_url作为合集封面图片完整链接 + 新增的3个字段
                 doc = {
                     'batch_time': batch_time,
                     'mix_name': mix_name,
@@ -882,7 +1006,11 @@ class DouyinPlayVVScraper:
                     'rank': 0,  # 临时设置，后面会重新计算
                     'cover_image_url_original': original_cover_url,  # 保存原始临时链接用于调试
                     'cover_image_url': permanent_cover_url,  # 合集封面图片永久链接
-                    'cover_backup_urls': item.get('cover_backup_urls', [])  # 封面图片备用链接列表
+                    'cover_backup_urls': item.get('cover_backup_urls', []),  # 封面图片备用链接列表
+                    # 新增的三个字段
+                    'series_author': item.get('series_author', ''),  # 合集作者/影视工作室
+                    'desc': item.get('desc', ''),  # 合集描述
+                    'updated_to_episode': item.get('updated_to_episode', 0)  # 合集总集数
                 }
                 documents.append(doc)
             
@@ -900,7 +1028,7 @@ class DouyinPlayVVScraper:
             max_play_vv = max(doc['play_vv'] for doc in documents) if documents else 0
             
             logging.info(f'MongoDB保存统计: 总播放量={total_play_vv:,}, 最高播放量={max_play_vv:,}')
-            logging.info(f'保存的字段: batch_time, mix_name, video_url, playcount, play_vv, request_id, rank, cover_image_url_original, cover_image_url')
+            logging.info(f'保存的字段: batch_time, mix_name, video_url, playcount, play_vv, request_id, rank, cover_image_url_original, cover_image_url, series_author, desc, updated_to_episode')
 
             # 统计封面图片处理情况
             cover_count = sum(1 for doc in documents if doc.get('cover_image_url'))

backend/routers/rank_api_routes.py

@@ -128,7 +128,13 @@ def format_mix_item(doc):
         "play_vv": doc.get("play_vv", 0),
         "request_id": doc.get("request_id", ""),
         "rank": doc.get("rank", 0),
-        "cover_image_url": doc.get("cover_image_url", "")
+        "cover_image_url": doc.get("cover_image_url", ""),
+        # 新增字段
+        "series_author": doc.get("series_author", ""),
+        "desc": doc.get("desc", ""),
+        "updated_to_episode": doc.get("updated_to_episode", 0),
+        "cover_backup_urls": doc.get("cover_backup_urls", []),
+        "mix_id": doc.get("mix_id", "")
     }
 
 def get_mix_list(page=1, limit=20, sort_by="playcount"):