| 12345678910111213141516171819202122232425262728293031323334 |
- import json
- file = "/Users/zhao/Downloads/da94a214-ddbb-491f-8984-9505b30d43cb.json"
- log_json_list = []
- with open(file) as f:
- line = f.readline()
- while line:
- log_json_list.append(json.loads(line))
- line = f.readline()
- print(f"videoId,品类,视频截帧,爬取计划ID,站外视频ID,站外账号ID,结果,分享量,点赞量,分享量/点赞量,视频时长（秒）,观众年龄50+占比,观众年龄50+TGI,过滤规则表达式")
- for log in log_json_list:
- video_id = log['videoId']
- crawler_plan_id = log['crawlerPlanId']
- ext_json = json.loads(log['ext'])
- merge_cate2_map = ext_json['mergeCate2Map']
- extra_frame_image_url = ext_json['extraFrameImageUrl']
- for channel_content_id in ext_json:
- if channel_content_id in ['mergeCate2Map', 'extraFrameImageUrl']:
- continue
- channel_ext_info = ext_json[channel_content_id]
- channel_account_id = channel_ext_info.get("aweme_info", "{}").get("author", "{}").get("sec_uid", "")
- result = channel_ext_info['contentDetail'].get('result', False)
- rule_str = channel_ext_info['rule']
- rule_context = channel_ext_info['ruleContext']
- share_cnt = rule_context['shareCnt']
- video_duration_s = rule_context['videoDuration_s']
- like_cnt = rule_context['likeCnt']
- audience_age_50_rate = rule_context['audienceAge50Rate']
- audience_age_50_tgi = rule_context['audienceAge50TGI']
- share_div_link = rule_context['shareDivLink']
- print(f"{video_id},{merge_cate2_map},{extra_frame_image_url},'{crawler_plan_id},'{channel_content_id},{channel_account_id},{result},"
- f"{share_cnt},{like_cnt},{share_div_link},{video_duration_s},{audience_age_50_rate},{audience_age_50_tgi},{rule_str}")
|
