zfsh_recommend.py 9.2 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155
  1. import json
  2. import time
  3. import uuid
  4. import requests
  5. from common.common import Common
  6. from common.scheduling_db import MysqlHelper
  7. from common.mq import MQ
  8. from common.public import download_rule, get_config_from_mysql
  9. proxies = {"http": None, "https": None}
  10. class ZfshRecommend:
  11. platform = ("祝福生活视频")
  12. @classmethod
  13. def repeat_video(cls, log_type, crawler, video_id, env):
  14. sql = f""" select * from crawler_video where platform in ("{crawler}","{cls.platform}") and create_time>='2023-06-26' and out_video_id="{video_id}"; """
  15. repeat_video = MysqlHelper.get_values(log_type, crawler, sql, env)
  16. return len(repeat_video)
  17. @classmethod
  18. def get_videoList(cls, log_type, crawler, our_uid, rule_dict, env):
  19. mq = MQ(topic_name="topic_crawler_etl_" + env)
  20. uuid1 = str(uuid.uuid1())
  21. for page in range(1, 100):
  22. try:
  23. Common.logger(log_type, crawler).info(f"正在抓取第{page}页")
  24. Common.logging(log_type, crawler, env, f"正在抓取第{page}页")
  25. url = "https://mini.vvuiiu.cn/article/getArticleList"
  26. payload = json.dumps({
  27. "page": page,
  28. "size": 5,
  29. "category_id": "393774", # 每日推荐id
  30. "from_type": 1,
  31. "uuid": uuid1,
  32. # "openid": "oY5tI5FgvH9Jmc8cntj81t5Ugsds",
  33. "platform": 35,
  34. "appid": "wxa903dc775e85eb5b"
  35. })
  36. headers = {
  37. 'Host': 'mini.vvuiiu.cn',
  38. 'accept': '*/*',
  39. 'content-type': 'application/json',
  40. 'accept-language': 'zh-cn',
  41. 'user-agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E217 MicroMessenger/6.8.0(0x16080000) NetType/WIFI Language/en Branch/Br_trunk MiniProgramEnv/Mac',
  42. 'referer': 'https://servicewechat.com/wxa903dc775e85eb5b/11/page-frame.html'
  43. }
  44. r = requests.post(url=url, headers=headers, data=payload, proxies=proxies, verify=False)
  45. if "data" not in r.text or r.status_code != 200:
  46. Common.logger(log_type, crawler).warning(f"get_videoList:{r.text}\n")
  47. Common.logging(log_type, crawler, env, f"get_videoList:{r.text}\n")
  48. return
  49. elif "data" not in r.json():
  50. Common.logger(log_type, crawler).info(f"get_videoList:{r.json()}\n")
  51. Common.logging(log_type, crawler, env, f"get_videoList:{r.json()}\n")
  52. return
  53. elif "list" not in r.json()["data"]:
  54. Common.logger(log_type, crawler).warning(f"get_videoList:{r.json()['data']}\n")
  55. Common.logging(log_type, crawler, env, f"get_videoList:{r.json()['data']}\n")
  56. return
  57. elif len(r.json()["data"]["list"]) == 0:
  58. Common.logger(log_type, crawler).warning(f"get_videoList:{r.json()['data']['list']}\n")
  59. Common.logging(log_type, crawler, env, f"get_videoList:{r.json()['data']['list']}\n")
  60. return
  61. else:
  62. # 视频列表
  63. feeds = r.json()["data"]["list"]
  64. for i in range(len(feeds)):
  65. try:
  66. video_title = feeds[i].get("title", "").strip().replace("\n", "") \
  67. .replace("/", "").replace("\\", "").replace("\r", "") \
  68. .replace(":", "").replace("*", "").replace("?", "") \
  69. .replace("?", "").replace('"', "").replace("<", "") \
  70. .replace(">", "").replace("|", "").replace(" ", "") \
  71. .replace("&NBSP", "").replace(".", "。").replace(" ", "") \
  72. .replace("'", "").replace("#", "").replace("Merge", "")
  73. publish_time_stamp = int(feeds[i].get("article_id", 0))
  74. publish_time_str = time.strftime("%Y/%m/%d %H:%M:%S", time.localtime(publish_time_stamp))
  75. video_dict = {
  76. "video_title": video_title,
  77. "video_id": feeds[i]["id"], # 视频id
  78. "publish_time_stamp": publish_time_stamp,
  79. "publish_time_str": publish_time_str,
  80. "is_video": int(feeds[i].get("is_video", 0)), # 类型
  81. "category_id": int(feeds[i].get("category_id", 0)), # 视频来源(精彩推荐)
  82. "image_path": feeds[i].get("image_path", ""), # 视频封面
  83. "video_url": feeds[i].get("video_url", ""), # 视频链接
  84. "click": int(feeds[i].get("click", 0)), # 点击数
  85. "video_width": int(feeds[i].get("vw", 0)),
  86. "video_height": int(feeds[i].get("vh", 0)),
  87. "user_name": feeds[i].get("source", "").strip().replace("\n", ""),
  88. "user_id": feeds[i].get("openid", ""),
  89. "play_cnt": 0,
  90. "like_cnt": 0,
  91. "comment_cnt": 0,
  92. "share_cnt": 0,
  93. # "duration": feeds[i].get("mediaDuration", 0),
  94. "session": ""
  95. }
  96. for k, v in video_dict.items():
  97. Common.logger(log_type, crawler).info(f"{k}:{v}")
  98. Common.logging(log_type, crawler, env, f"video_dict:{video_dict}")
  99. if video_dict["video_id"] == "" or video_dict["video_title"] == "" or video_dict[
  100. "video_url"] == "":
  101. Common.logger(log_type, crawler).info("无效视频\n")
  102. Common.logging(log_type, crawler, env, "无效视频\n")
  103. elif download_rule(log_type=log_type, crawler=crawler, video_dict=video_dict,
  104. rule_dict=rule_dict) is False:
  105. Common.logger(log_type, crawler).info("不满足抓取规则\n")
  106. Common.logging(log_type, crawler, env, "不满足抓取规则\n")
  107. elif any(str(word) if str(word) in video_dict["video_title"] else False
  108. for word in get_config_from_mysql(log_type=log_type,
  109. source=crawler,
  110. env=env,
  111. text="filter",
  112. action="")) is True:
  113. Common.logger(log_type, crawler).info('已中过滤词\n')
  114. Common.logging(log_type, crawler, env, '已中过滤词\n')
  115. elif cls.repeat_video(log_type, crawler, video_dict["video_id"], env) != 0:
  116. Common.logger(log_type, crawler).info('视频已下载\n')
  117. Common.logging(log_type, crawler, env, '视频已下载\n')
  118. else:
  119. video_dict["out_user_id"] = video_dict["user_id"]
  120. video_dict["platform"] = crawler
  121. video_dict["strategy"] = log_type
  122. video_dict["out_video_id"] = video_dict["video_id"]
  123. video_dict["width"] = video_dict["video_width"]
  124. video_dict["height"] = video_dict["video_height"]
  125. video_dict["crawler_rule"] = json.dumps(rule_dict)
  126. video_dict["user_id"] = our_uid
  127. video_dict["publish_time"] = video_dict["publish_time_str"]
  128. mq.send_msg(video_dict)
  129. except Exception as e:
  130. Common.logger(log_type, crawler).error(f"抓取单条视频异常:{e}\n")
  131. Common.logging(log_type, crawler, env, f"抓取单条视频异常:{e}\n")
  132. except Exception as e:
  133. Common.logger(log_type, crawler).error(f"抓取第{page}页时异常:{e}\n")
  134. Common.logging(log_type, crawler, env, f"抓取第{page}页时异常:{e}\n")
  135. if __name__ == "__main__":
  136. rule_dict1 = {"period": {"min": 365, "max": 365},
  137. "duration": {"min": 30, "max": 1800},
  138. "favorite_cnt": {"min": 0, "max": 0},
  139. "videos_cnt": {"min": 10, "max": 20},
  140. "share_cnt": {"min": 0, "max": 0}}
  141. ZfshRecommend.get_videoList("recommend", "zhufushenghuo,", "16QspO", rule_dict1, 'dev')