| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121 |
- import time
- import requests
- import json
- from common import Common, AliyunLogger, Feishu, Material
- from common.sql_help import sqlCollect
- from common.userAgent import get_random_user_agent
- class KsPcKeyword:
- @classmethod
- def get_key_word(cls, keyword, task_mark, mark, channel_id, name, task):
- list = []
- url = "https://www.kuaishou.com/graphql"
- payload = json.dumps({
- "operationName": "visionSearchPhoto",
- "variables": {
- "keyword": keyword,
- "pcursor": "",
- "page": "search"
- },
- "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 visionSearchPhoto($keyword: String, $pcursor: String, $searchSessionId: String, $page: String, $webPageArea: String) {\n visionSearchPhoto(keyword: $keyword, pcursor: $pcursor, searchSessionId: $searchSessionId, page: $page, webPageArea: $webPageArea) {\n result\n llsid\n webPageArea\n feeds {\n ...feedContent\n __typename\n }\n searchSessionId\n pcursor\n aladdinBanner {\n imgUrl\n link\n __typename\n }\n __typename\n }\n}\n"
- })
- cookie = Material.get_cookie_data("KsoMsyP2ghleM9tzBfmcEEXBnXg", "U1gySe", "快手搜索-cookie")
- headers = {
- 'Accept-Language': 'zh-CN,zh;q=0.9',
- 'Cache-Control': 'no-cache',
- 'Connection': 'keep-alive',
- 'Origin': 'https://www.kuaishou.com',
- 'Pragma': 'no-cache',
- 'User-Agent': get_random_user_agent("pc"),
- 'accept': '*/*',
- 'content-type': 'application/json',
- 'Cookie': cookie
- }
- try:
- time.sleep(3)
- # 代理信息
- proxy = "http://spkbt3wnzw:cx6R=v5mQuBgqsQ4o7@cn.visitxiangtan.com:30000"
- proxies = {
- "http": proxy,
- "https": proxy
- }
- response = requests.request("POST", url, headers=headers, data=payload, proxies=proxies)
- text = response.text
- if text:
- response_dict = json.loads(text)
- result = response_dict.get('result', None)
- if result:
- log_type = ['liukunyu', 'wangxueke', 'xinxin']
- mark_name = ['刘坤宇', '王雪珂', '信欣']
- Feishu.bot(log_type, '快手关键词搜索', f'快手关键词搜索cookie过期，请及时更换', mark_name)
- time.sleep(10)
- return list
- response = response.json()
- data_list = response['data']['visionSearchPhoto']['feeds']
- for data in data_list:
- data = data['photo']
- photo_id = data["id"]
- status = sqlCollect.is_used(task_mark, photo_id, mark, channel_id)
- view_count = data["viewCount"] if "viewCount" in data and data["viewCount"] else 0
- like_count = data["likeCount"] if "likeCount" in data and data["likeCount"] else 0
- like_count = cls.convert_to_number(like_count)
- video_percent = '%.4f' % (int(like_count) / int(view_count))
- special = 0.015
- old_title = data["caption"] # 标题
- duration = data["duration"]
- duration = int(duration) / 1000
- video_url = data["photoUrl"]
- image_url = data["coverUrl"]
- log_data = f"user:{keyword},,video_id:{photo_id},,video_url:{video_url},original_title:{old_title},,like_count:{like_count},,view_count:{view_count},,duration:{duration}"
- AliyunLogger.logging(channel_id, name, keyword, photo_id, "扫描到一条视频", "2001", log_data)
- if status:
- AliyunLogger.logging(channel_id, name, keyword, photo_id, "该视频已改造过", "2001", log_data)
- continue
- if int(view_count) < 1000:
- AliyunLogger.logging(channel_id, name, keyword, photo_id, f"不符合规则:浏览小于1000", "2003", log_data)
- Common.logger("ks-key-word").info(
- f"不符合规则：{task_mark},用户主页id:{keyword},视频id{photo_id} ,浏览:{view_count},浏览{view_count} ,时长:{int(duration)} ")
- continue
- if float(video_percent) < special:
- AliyunLogger.logging(channel_id, name, keyword, photo_id, f"不符合规则:点赞/浏览{special}", "2003", log_data)
- Common.logger("ks-key-word").info(
- f"不符合规则：{task_mark},用户主页id:{keyword},视频id{photo_id} ,浏览:{view_count},浏览{view_count} ,时长:{int(duration)} ")
- continue
- if int(duration) < 30 or int(duration) > 600:
- AliyunLogger.logging(channel_id, name, keyword, photo_id,
- f"不符合规则:时长不符合规则大于600秒/小于30秒", "2003",
- log_data)
- Common.logger("ks-key-word").info(
- f"不符合规则：{task_mark},用户主页id:{keyword},视频id{photo_id} ,浏览:{view_count},浏览{view_count} ,时长:{int(duration)} ")
- continue
- AliyunLogger.logging(channel_id, name, keyword, photo_id, "符合规则等待改造", "2004", log_data)
- all_data = {"video_id": photo_id, "cover": image_url, "video_url": video_url,
- "rule": '',
- "old_title": old_title}
- list.append(all_data)
- return list
- except Exception as exc:
- Common.logger("ks-key-word").info(f"快手搜索词{keyword}获取失败{exc}\n")
- return list
- @classmethod
- def convert_to_number(cls, value):
- if value.endswith("万"):
- return float(value[:-1]) * 10000 # 去掉“万”并乘以 10000
- return int(value) # 处理其他格式
- if __name__ == '__main__':
- keyword = '毛主席故居'
- task_mark = '1'
- mark = 'pl-gjc'
- channel_id = '快手搜索'
- name = '1'
- task = {'combo': ['最新发布', '近1日', '1分钟内']}
- KsPcKeyword.get_key_word(keyword, task_mark, mark, channel_id, name, task)
|
