修复豆包关联视频

aidso_geo/models/doubao_android_data_process.py

@@ -293,6 +293,7 @@ def doubao_mobile_process_original_data(data):
             new_url_list.append(item)
 
         url_list = new_url_list
+
         spider_save_tos.process_and_save_files(file_path, search_keyword, url_list, think_content, response_content,
                                                suggestions, rich_media_block)
         return (file_path, search_keyword, url_list, think_content, response_content, suggestions)
@@ -328,7 +329,7 @@ if __name__ == '__main__':
     # file_path = 'geo/c7eb465e-f385-4aa2-89c4-a7cf11897f45/KIMI/1(1).txt'
 
     data_list = bh_utils.query_data(
-        f"select * from geo_commit_task  where taskId = '27721b42-3368-4526-b092-d3157aaa617a' and  platform  = 'DOUBA'")
+        f"select * from geo_commit_task  where taskId = '798f148f-6896-4853-b589-d968cd2d150e' and  platform  = 'DOUBA'")
 
 
 

aidso_geo/models/spider_save_tos.py

@@ -64,10 +64,19 @@ def doubao_android_process_rich_media(url_list):
 
     for item in url_list:
         video_id = item.get('item_id', '')
+        cover = item.get('cover') or {}
+        origin_cover = cover.get('origin_cover') or {}
+        image_ori = origin_cover.get('image_ori') or {}
+
+        video_first_frame_image = (
+                item.get('video_first_frame_image')
+                or image_ori.get('url')
+                or ''
+        )
         raw_data = {
             "video_id": video_id,
             "video_captions": item.get('video_captions', ''),
-            "video_first_frame_image": item.get('video_first_frame_image', '') or item.get('cover').get('origin_cover').get('image_ori').get('url') or '',
+            "video_first_frame_image": video_first_frame_image,
             "main_site_url": item.get('main_site_url', '') or f'https://www.douyin.com/video/{video_id}',
             "source_app_name": item.get('source_app_name', '') or '抖音'
         }