123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162 |
- import random
- import time
- import requests
- import json
- import urllib3
- from requests.adapters import HTTPAdapter
- from common import Feishu, Material, AliyunLogger
- from common.sql_help import sqlCollect
- from data_channel.data_help import dataHelp
- class KS:
- @classmethod
- def get_share_count(cls, v_id):
- url = "http://8.217.192.46:8889/crawler/kuai_shou/detail"
- payload = json.dumps({
- "content_id": v_id
- })
- headers = {
- 'Content-Type': 'application/json'
- }
- try:
- time.sleep(random.uniform(1, 10))
- response = requests.request("POST", url, headers=headers, data=payload, timeout=30)
- response = response.json()
- if response["code"] == 0:
- data = response["data"]["data"]
- share_count = data.get("share_count")
- return int(share_count)
- except KeyError as e:
- return 0
- @classmethod
- def get_ks_url(cls, task_mark, url_id, number, mark, feishu_id, cookie_sheet, channel_id, name):
- list = []
- pcursor = ""
- url = "https://www.kuaishou.com/graphql"
- if not url_id:
- return
- for i in range(3):
- cookie = Material.get_cookie_data(feishu_id, cookie_sheet, channel_id)
- time.sleep(random.randint(1, 5))
- payload = json.dumps({
- "operationName": "visionProfilePhotoList",
- "variables": {
- "userId": url_id,
- "pcursor": pcursor,
- "page": "profile"
- },
- "query": "fragment photoContent on PhotoEntity {\n __typename\n id\n duration\n caption\n originCaption\n likeCount\n viewCount\n commentCount\n realLikeCount\n coverUrl\n photoUrl\n photoH265Url\n manifest\n manifestH265\n videoResource\n coverUrls {\n url\n __typename\n }\n timestamp\n expTag\n animatedCoverUrl\n distance\n videoRatio\n liked\n stereoType\n profileUserTopPhoto\n musicBlocked\n riskTagContent\n riskTagUrl\n}\n\nfragment recoPhotoFragment on recoPhotoEntity {\n __typename\n id\n duration\n caption\n originCaption\n likeCount\n viewCount\n commentCount\n realLikeCount\n coverUrl\n photoUrl\n photoH265Url\n manifest\n manifestH265\n videoResource\n coverUrls {\n url\n __typename\n }\n timestamp\n expTag\n animatedCoverUrl\n distance\n videoRatio\n liked\n stereoType\n profileUserTopPhoto\n musicBlocked\n riskTagContent\n riskTagUrl\n}\n\nfragment feedContent on Feed {\n type\n author {\n id\n name\n headerUrl\n following\n headerUrls {\n url\n __typename\n }\n __typename\n }\n photo {\n ...photoContent\n ...recoPhotoFragment\n __typename\n }\n canAddComment\n llsid\n status\n currentPcursor\n tags {\n type\n name\n __typename\n }\n __typename\n}\n\nquery visionProfilePhotoList($pcursor: String, $userId: String, $page: String, $webPageArea: String) {\n visionProfilePhotoList(pcursor: $pcursor, userId: $userId, page: $page, webPageArea: $webPageArea) {\n result\n llsid\n webPageArea\n feeds {\n ...feedContent\n __typename\n }\n hostName\n pcursor\n __typename\n }\n}\n"
- })
- headers = {
- 'accept': '*/*',
- 'content-type': 'application/json',
- 'Origin': 'https://www.kuaishou.com',
- 'Cookie': cookie,
- 'Accept-Language': 'zh-CN,zh;q=0.9',
- 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36',
- 'Referer': f'https://www.kuaishou.com/profile/{url_id}',
- 'Accept-Encoding': 'gzip, deflate, br',
- 'Connection': 'keep-alive'
- }
- urllib3.disable_warnings()
- s = requests.session()
- s.mount('http://', HTTPAdapter(max_retries=3))
- s.mount('https://', HTTPAdapter(max_retries=3))
- # response = requests.request("POST", url, headers=headers, data=payload, timeout=10)
- try:
- response = s.post(url=url, headers=headers, data=payload, verify=False, timeout=10)
- response.close()
- if response.status_code != 200:
- return list
- elif response.status_code == 200 and "error_msg" in response.text:
- Feishu.bot("wangxueke", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', 'wangxueke')
- Feishu.bot("liuzhaoheng", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', '刘兆恒')
- time.sleep(600)
- return list
- elif "visionProfilePhotoList" not in response.json()["data"]:
- if name == '快手品类账号':
- Feishu.bot("wangxueke", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', 'wangxueke')
- Feishu.bot("liuzhaoheng", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', '刘兆恒')
- time.sleep(600)
- else:
- Feishu.bot(mark, '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', name)
- return list
- elif "feeds" not in response.json()["data"]["visionProfilePhotoList"]:
- if name == '快手品类账号':
- Feishu.bot("wangxueke", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', 'wangxueke')
- Feishu.bot("liuzhaoheng", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', '刘兆恒')
- time.sleep(600)
- else:
- Feishu.bot(mark, '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', name)
- return list
- elif len(response.json()["data"]["visionProfilePhotoList"]["feeds"]) == 0:
- if name == '快手品类账号':
- Feishu.bot("wangxueke", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', 'wangxueke')
- Feishu.bot("liuzhaoheng", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', '刘兆恒')
- time.sleep(600)
- else:
- Feishu.bot(mark, '机器自动改造消息通知', f'快手-{name}cookie使用频繁无法获取到数据,请及时更换', name)
- return list
- pcursor = response.json()['data']['visionProfilePhotoList']['pcursor']
- feeds = response.json()['data']['visionProfilePhotoList']['feeds']
- for i in range(len(feeds)):
- # try:
- # video_id = feeds[i].get("photo", {}).get("videoResource").get("h264", {}).get("videoId", "")
- # except KeyError:
- # video_id = feeds[i].get("photo", {}).get("videoResource").get("hevc", {}).get("videoId", "")
- # status = sqlCollect.is_used(task_mark, video_id, mark, channel_id)
- # if status:
- # continue
- video_id = feeds[i].get("photo", {}).get("id", "")
- status = sqlCollect.is_used(task_mark, video_id, mark, channel_id)
- old_title = feeds[i].get("photo", {}).get("caption")
- cover_url = feeds[i].get('photo', {}).get('coverUrl', "")
- video_url = feeds[i].get('photo', {}).get('photoUrl', "")
- view_count = int(feeds[i].get('photo', {}).get('viewCount', 0))
- realLikeCount = int(feeds[i].get('photo', {}).get('realLikeCount', 0))
- video_percent = '%.4f' % (share_count / view_count)
- duration = dataHelp.video_duration(video_url)
- log_data = f"user:{url_id},,video_id:{video_id},,video_url:{video_url},,original_title:{old_title},,share_count:{share_count},,view_count:{view_count},,duration:{duration}"
- # log_data = f"user:{url_id},,video_id:{video_id},,video_url:{video_url},,original_title:{old_title},,view_count:{view_count},,duration:{duration}"
- AliyunLogger.logging(channel_id, name, url_id, video_id, "扫描到一条视频", "2001", log_data)
- # if status:
- # AliyunLogger.logging(channel_id, name, url_id, video_id, "该视频已改造过", "2002", log_data)
- # continue
- share_count = cls.get_share_count(video_id)
- special = float(0.001)
- if float(video_percent) < special:
- AliyunLogger.logging(channel_id, name, url_id, video_id, "不符合规则:分享/浏览小于0.001", "2003", log_data)
- continue
- if share_count < 500:
- AliyunLogger.logging(channel_id, name, url_id, video_id, "不符合规则:分享小于500", "2003", log_data)
- continue
- if duration < 30 or duration > 720:
- AliyunLogger.logging(channel_id, name, url_id, video_id, "不符合规则:时长不符合规则大于720秒/小于30秒", "2003", log_data)
- continue
- all_data = {"video_id": video_id, "cover": cover_url, "video_url": video_url, "rule": video_percent, "old_title": old_title}
- list.append(all_data)
- AliyunLogger.logging(channel_id, name, url_id, video_id, "符合规则等待改造", "2004", log_data)
- if len(list) == int(number):
- return list
- except Exception as exc:
- # Feishu.bot("wangxueke", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', 'wangxueke')
- # Feishu.bot("liuzhaoheng", '机器自动改造消息通知', f'快手-{name}cookie过期,请及时更换', '刘兆恒')
- return list
- return list
- if __name__ == '__main__':
- KS.get_ks_url("1","3xzicxg2nandemc",1,"1",'WuoQsVFXChVMK4tDHqLcwLWgnjh','Sjk8p8','','')
|