qpl_ks.py 8.9 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169
  1. import random
  2. import time
  3. from datetime import datetime
  4. import requests
  5. import json
  6. from common import Feishu
  7. from common.sql_help import sqlCollect
  8. class QplKs:
  9. @classmethod
  10. def ks_data_list(cls):
  11. content_type = [{'美食': '673'}, {'短剧': '674'}, {'时尚': '675'}, {'母婴亲子': '676'}, {'生活': '677'},
  12. {'汽车': '678'}, {'旅游': '679'}, {'体育运动': '680'}, {'艺术文化': '682'}, {'房产家居': '683'},
  13. {'健康医疗': '684'}, {'教育培训': '685'}, {'高新数码': '686'}, {'音乐': '687'}, {'舞蹈': '688'}, {'读书': '689'},
  14. {'摄影': '704'},
  15. {'财经投资': '690'}, {'萌宠': '691'}, {'时政资讯': '692'}, {'科学与法律': '693'}, {'三农': '694'}, {'搞笑': '695'},
  16. {'情感': '696'},
  17. {'人文': '697'}, {'星座命理': '699'}, {'奇人异象': '700'}, {'军事': '701'}, {'影视娱乐': '702'},
  18. {'民生资讯': '703'}, {'健身达人': '706'}, {'纪实类': '705'}]
  19. # fans_count = [{0: 100000}, {100000: 1000000}, {1000000: 3000000}, {3000000: 5000000}, {5000000: 10000000},
  20. # {10000000: 0}]
  21. fans_count = [{10000000: 0}, {5000000: 10000000}]
  22. url = "https://k.kuaishou.com/rest/web/star/list"
  23. headers = {
  24. 'Accept': 'application/json',
  25. 'Accept-Language': 'zh-CN,zh;q=0.9',
  26. 'Content-Type': 'application/json',
  27. 'Cookie': 'did=web_9c6a04a4004fdb7c95a658a56ed275b6; didv=1711519980000; apdid=328ac94f-4040-41fe-a038-b60140291aca99fb22e9862c74736f53d57b666ee53b:1719580529:1; language=zh-CN; ud=2205012540; app_id=ks686235996059836592; expire_time=1800; userId=2574854626; access_token=ChFvYXV0aC5hY2Nlc3NUb2tlbhIw_udZziw8HOh4U0o0WCfzpedDFI8kxpzxIBDWKVcHSLl3CMo-cd3EZ3NiAga2_iwdGhIgQfvkqD5FqqWtQ2y0WGxSDjAiIHiWTCrCAkIo1TCQBj86fzBQzXnHCB_yplzArTKHIMzbKAUwAQ; nc_user_id=CiVhZC5ub3RpZnkuY2VudGVyLm9hdXRoLnVzZXIuaWQuc2VjcmV0EiCvobb+fVYYwtCYKsf+mX20zN6suQFLe2M1LXGeHAlWZBoSVM0G49/nJB/JmO0PwfOBK4qSIiCBBpQGJdpxBHdVNj7YLARdxkJ4HmillU9+D5S9vVlsSigFMAE=; kuaishou.ad.social_st=ChVrdWFpc2hvdS5hZC5zb2NpYWwuc3QSoAEqEbh762nhDKS1eTc-dqLlcbzwfEJSNxogQ2rgbqvb63xgQyz7U0ikGgN_r5hsOCuYQupi5PkEqOzFmB_9gYJnYjjyH50TWQjcHFgv0eVl4Dwh6tVFvz7XWi6xpFJEQ_SUU960P6KVG2cu9uhyMfVRRPbGSHJuQoi08cd1BaPYBkRJmBLbNf2IMB4bZwudF_3DlbbSfi2PYhoNpG0xVdRdGhIFcNIwV0BDDJn-zdzp3B-cqPIiIOO8CYtWIKOg8Bo5mfUyrJzIkN6eZqbKtNIGuQsj3oWuKAUwAQ; kuaishou.ad.social_ph=df0e43b95caa8ff41e6cdb3b0f1b7b93c071; did=web_9c6a04a4004fdb7c95a658a56ed275b6; didv=1711522726000',
  28. 'Origin': 'https://k.kuaishou.com',
  29. 'Pragma': 'no-cache',
  30. 'Referer': 'https://k.kuaishou.com/',
  31. 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
  32. }
  33. for count in fans_count:
  34. (fans_min_num, fans_max_num), = count.items()
  35. for content in content_type:
  36. (content_name, content_id), = content.items()
  37. current_page = 1
  38. while True:
  39. payload_data = {
  40. "currentPage": current_page,
  41. "pageSize": 20,
  42. "starOrderTag": 3,
  43. "taskType": 1,
  44. "marketingGoal": 1,
  45. "viewerAgeList": [ # 观众画像 50+
  46. {
  47. "from": "0.50",
  48. "to": "1.00",
  49. "queryName": "50+"
  50. }
  51. ],
  52. "userName": "",
  53. "vitalityTags": [ # 活跃度 近期短视频活跃
  54. "668"
  55. ],
  56. "contentTagIdList": [ # 内容类型
  57. {
  58. "id": str(content_id),
  59. "selectFirstLevelId": True
  60. }
  61. ],
  62. # "fansMinNum": 1000000, # 粉丝数量
  63. # "fansMaxNum": 3000000, # 粉丝数量
  64. }
  65. if fans_min_num > 0:
  66. payload_data["fansMinNum"] = fans_min_num
  67. if fans_max_num > 0:
  68. payload_data["fansMaxNum"] = fans_max_num
  69. payload = json.dumps(payload_data)
  70. time.sleep(random.randint(10, 20))
  71. response = requests.request("POST", url, headers=headers, data=payload)
  72. response = response.json()
  73. print(f"开始扫描{content}")
  74. result = response["result"]
  75. if result == 1:
  76. total = response["total"] # 总条数
  77. if total == 0:
  78. print(f"没有扫描到数据{content}")
  79. break
  80. star_list = response["starList"]
  81. if len(star_list) == 0 or star_list == []:
  82. break
  83. for star in star_list:
  84. print(f"扫描到一条数据{content}")
  85. user_id = star["userId"]
  86. star_id = star["starId"]
  87. name = star["name"] # 用户名
  88. kwai_id = star["kwaiId"] # 用户名id
  89. gender = star["gender"] # 性别
  90. fans_number = star["fansNumber"] # 粉丝数
  91. profile_id = star["profileId"] # 主页id
  92. star_tag_str = star["starTagStr"] # 内容类型1
  93. industry_tag_str = star["industryTagStr"] # 内容类型2
  94. photo_expect_play = star["photoExpectPlay"] # 预期播放量
  95. photo_expect_cpm = star["photoExpectCpm"] # 预期CPM
  96. photo_interaction_rate = star["photoInteractionRate"] # 互动率
  97. photo_complete_play_rate = star["photoCompletePlayRate"] # 完播率
  98. fans_increase_num = star["fansIncreaseNum"] # 粉丝增长量
  99. fans_increase_rate = star["fansIncreaseRate"] # 粉丝增长率
  100. res = sqlCollect.insert_ks_qpl_data(user_id, star_id, name, kwai_id, gender, fans_number, profile_id, star_tag_str, industry_tag_str, photo_expect_play, photo_expect_cpm, photo_interaction_rate, photo_complete_play_rate, fans_increase_num, fans_increase_rate)
  101. if res == 1:
  102. current_time = datetime.now()
  103. formatted_time = current_time.strftime("%Y-%m-%d %H:%M:%S")
  104. if fans_min_num == 0:
  105. fans = f"{fans_max_num}及以下"
  106. if fans_max_num == 0:
  107. fans = f"{fans_min_num}及以上"
  108. else:
  109. fans = f"{fans_min_num}~{fans_max_num}"
  110. values = [
  111. [
  112. name,
  113. gender,
  114. fans_number,
  115. "https://www.kuaishou.com/profile/"+profile_id,
  116. star_tag_str,
  117. industry_tag_str,
  118. photo_expect_play,
  119. photo_expect_cpm,
  120. photo_interaction_rate,
  121. photo_complete_play_rate,
  122. fans_increase_num,
  123. fans_increase_rate,
  124. fans,
  125. formatted_time
  126. ]
  127. ]
  128. Feishu.insert_columns("GjGZsmW2ahaCe4tmzDTc58tVnbe", "4a9d77", "ROWS", 1, 2)
  129. time.sleep(0.5)
  130. Feishu.update_values("GjGZsmW2ahaCe4tmzDTc58tVnbe", "4a9d77", "A2:Z2", values)
  131. current_page += 1
  132. print(f"入库到一条数据{content}")
  133. if total < 20:
  134. break
  135. else:
  136. page = int(total)/20
  137. if current_page > int(page):
  138. break
  139. if __name__ == '__main__':
  140. QplKs.ks_data_list()