快手优化

kuaishou/kuaishou_author/kuaishou_author_scheduling_new.py

@@ -1,5 +1,6 @@
 # -*- coding: utf-8 -*-
 # @Time: 2023/11/07
+import datetime
 import os
 import random
 import sys
@@ -8,7 +9,6 @@ from datetime import date, timedelta
 import requests
 import json
 import urllib3
-from pandas import datetime
 
 from common.feishu import Feishu
 
@@ -124,12 +124,12 @@ class KuaishouauthorScheduling:
                 },
                 "query": "fragment photoContent on PhotoEntity {\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  __typename\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    __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"
             })
-            cookie = cls.get_cookie(log_type, crawler, env)["cookie"]
+            # cookie = cls.get_cookie(log_type, crawler, env)["cookie"]
             headers = {
                 'Accept': '*/*',
                 'Content-Type': 'application/json',
                 'Origin': 'https://www.kuaishou.com',
-                'Cookie': cookie,
+                'Cookie': "kpf=PC_WEB; clientid=3; did=web_9c6a04a4004fdb7c95a658a56ed275b6; userId=1299331643; kpn=KUAISHOU_VISION; kuaishou.server.web_st=ChZrdWFpc2hvdS5zZXJ2ZXIud2ViLnN0EqABCqafvOnP6y7cYgtjIf1e768WcRUF6GRpDnLIc4pmS75OjS3bmBA0dsvXr2gI-erIpf6QtiDmG9gJt8uCf6iphyIa71jOWlOucSzyJHjaqh1Mk6F_iJM3U1LERQ1SepV-7zggDAEkSkyx4e8IGw3Q4AFzt6CqODASMchfKZa504WyJQbsvW8fyCWQsAgkATxG26K7EAnVGjN2nH_eF2r1IRoSoJCKbxHIWXjzVWap_gGna5KjIiB5WaM9v01O0CeINbL0Mz0lGQlktiBTUUX26W5q-9Dc6igFMAE; kuaishou.server.web_ph=472bf55506210d228e60cb1489e8a127bb51",
                 'Content-Length': '1260',
                 'Accept-Language': 'zh-CN,zh-Hans;q=0.9',
                 'Host': 'www.kuaishou.com',
@@ -143,7 +143,7 @@ class KuaishouauthorScheduling:
             # max_retries=3 重试3次
             s.mount('http://', HTTPAdapter(max_retries=3))
             s.mount('https://', HTTPAdapter(max_retries=3))
-            response = s.post(url=url, headers=headers, data=payload, proxies=Common.tunnel_proxies(), verify=False, timeout=10)
+            response = s.post(url=url, headers=headers, data=payload, verify=False, timeout=10)
             response.close()
             # Common.logger(log_type, crawler).info(f"response:{response.text}\n")
             if response.status_code != 200:
@@ -219,6 +219,7 @@ class KuaishouauthorScheduling:
                             message=f"已下载视频数:{cls.download_cnt}\n"
                         )
                         return
+                    user_name = feeds[i].get("author").get("name")
                     video_title = feeds[i].get("photo", {}).get("caption", random_title(log_type, crawler, env, text='title'))
                     video_title = cls.video_title(log_type, crawler, env, video_title)
                     try:
@@ -335,10 +336,10 @@ class KuaishouauthorScheduling:
                         video_dict["publish_time"] = video_dict["publish_time_str"]
                         video_dict["strategy_type"] = log_type
                         mq.send_msg(video_dict)
-                        current_time = datetime.now()
+                        current_time = datetime.datetime.now()
                         timestamp = current_time.strftime("%Y-%m-%d %H:%M:%S")
                         values = [[
-                            link,
+                            user_name,
                             video_id,
                             video_title,
                             publish_time_str,