用攻克DATA自动生成爬虫代码

今天我们要用到的数据爬取工具是攻克DATA，可以自动生成python代码来进行数据爬取

推荐码：GKA496F78CB479347D4F5B3E05892795A5

攻克DATA下载地址：1.软件安装 · 语雀

攻克DATA是一款专业的网络日志解析工具，可以0代码实现网络数据爬虫；当然也可以用它生成的python进行爬虫

import sys
sys.path.append( r'D:\Tools\GKData\ApiConfig')
import Gk
Gk.Guid2DB_Path = r'"D:\Tools\GKData\3rdLibs\Guid2DB.exe" ' 

# 实际代码：
cookie =  '__jdu=725637636; __jdv=251704139|direct|-|none|-|1695620515060; pinId=vOuujp2GM_HPXPHJr9XWTbV9-x-f3wj7; _tp=9hek%2BXTf8ylULoFOWfDPkk42THGVHy%2B5BXj2LBy9p0UMtDwuEHXu4jObkMsJl%2F%2Fq; _pst=%E7%8C%AB%E4%BA%BA%E9%92%88%E7%BA%BA-%E5%85%B3; shshshfpa=a9d0bda8-c9e3-fdb4-8d4e-34ff690a1e25-1695696762; shshshfpx=a9d0bda8-c9e3-fdb4-8d4e-34ff690a1e25-1695696762; user-key=240ad2b0-a860-473e-a689-158a491cb926; 3AB9D23F7A4B3CSS=jdd03WJDA65D4TPB54ZAZFQUFKB3T5QK23YUG2FGZIPUKBULKERNK7MH33R7KBMXWQ2QLRZ4RZKLHJ4PDSCIQUGKL5RONMMAAAAMKZ6EYE3AAAAAADOPL5F3CDQV2CIX; areaId=17; ipLoc-djd=17-1381-0-0; PCSYCityID=CN_420000_420100_0; shshshfpb=AAiuHic-KEtC9qMnj_bSNTjT_aQoeJRaVaWdiQQAAAAA; is_sz_old_version=false; ceshi3.com=000; wlfstk_smdl=ci5l1awx6j57d3jw5povx6zy70rqvjt7; 3AB9D23F7A4B3C9B=WJDA65D4TPB54ZAZFQUFKB3T5QK23YUG2FGZIPUKBULKERNK7MH33R7KBMXWQ2QLRZ4RZKLHJ4PDSCIQUGKL5RONMM; TrackID=1kca41gbvojIZ6qN4-fV0x_GhCBUHOy5W9wVxzGS9OBiH_4Tgnqt7AnLiDM3WthwN9leXfF1e-EWXGVkJbBKi6qt1hnFZPUDM_goTiAOyENs; thor=AC09D8FDB30392FA865E6CFD5D3266A21176B3C4F6131D7B7404CAB38973E369A7BE045C52865AF40D8D44B0B9B982DC59E4282BDC6D9235F7EFD73B7C3E9C4683A2646CF00DA39562238C010C1F627FA9EC7BC429EF8C01E95A33C5396D5E5BE9DBACC106B20562A5EE9289BD8AD31A1BF7B7B8BE6892D1E09CF15FAE7C52B5; flash=2_MN5cKYHGHh8Q64kqg674qvd0er6r2eJIXmquSPOZsLbiGlcmcL2N6b9as8bHPVTL-ky7SuaMq3I06GdFjryCwSei0mwAVkjBxyP-LGHdeuq*; pin=%E7%8C%AB%E4%BA%BA%E9%92%88%E7%BA%BA-%E5%85%B3; unick=%E7%8C%AB%E4%BA%BA%E9%92%88%E7%BA%BA-%E5%85%B3; __jda=251704139.725637636.1691192629.1695708521.1695719477.7; __jdc=251704139; __jdb=251704139.5.725637636|7.1695719477'
_headers_dict =  {
  "Host": "szgateway.jd.com",
  "Connection": "keep-alive",
  "sec-ch-ua": "\"Google Chrome\";v=\"117\", \"Not;A=Brand\";v=\"8\", \"Chromium\";v=\"117\"",
  "sec-ch-ua-mobile": "?0",
  "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
  "Accept": "application/json, text/plain, */*",
  "User-mup": "1695720319508",
  "p-pin": "%E7%8C%AB%E4%BA%BA%E9%92%88%E7%BA%BA-%E5%85%B3",
  "uuid": "16f92041-b34f-4e56-b659-03f5f8365f5a",
  "X-Requested-With": "XMLHttpRequest",
  "User-mnp": "fca55e7ba12357a567ec4b9a3e8e8669",
  "sec-ch-ua-platform": "\"Windows\"",
  "Origin": "https://sz.jd.com",
  "Sec-Fetch-Site": "same-site",
  "Sec-Fetch-Mode": "cors",
  "Sec-Fetch-Dest": "empty",
  "Referer": "https://sz.jd.com/szweb/sz/view/industryMarket/industryOverviews.html",
  "Accept-Encoding": "gzip, deflate",
  "Accept-Language": "zh-CN,zh;q=0.9",
  "Cookie": "__jdu=725637636; __jdv=251704139|direct|-|none|-|1695620515060; pinId=vOuujp2GM_HPXPHJr9XWTbV9-x-f3wj7; _tp=9hek%2BXTf8ylULoFOWfDPkk42THGVHy%2B5BXj2LBy9p0UMtDwuEHXu4jObkMsJl%2F%2Fq; _pst=%E7%8C%AB%E4%BA%BA%E9%92%88%E7%BA%BA-%E5%85%B3; shshshfpa=a9d0bda8-c9e3-fdb4-8d4e-34ff690a1e25-1695696762; shshshfpx=a9d0bda8-c9e3-fdb4-8d4e-34ff690a1e25-1695696762; user-key=240ad2b0-a860-473e-a689-158a491cb926; 3AB9D23F7A4B3CSS=jdd03WJDA65D4TPB54ZAZFQUFKB3T5QK23YUG2FGZIPUKBULKERNK7MH33R7KBMXWQ2QLRZ4RZKLHJ4PDSCIQUGKL5RONMMAAAAMKZ6EYE3AAAAAADOPL5F3CDQV2CIX; areaId=17; ipLoc-djd=17-1381-0-0; PCSYCityID=CN_420000_420100_0; shshshfpb=AAiuHic-KEtC9qMnj_bSNTjT_aQoeJRaVaWdiQQAAAAA; is_sz_old_version=false; ceshi3.com=000; wlfstk_smdl=ci5l1awx6j57d3jw5povx6zy70rqvjt7; 3AB9D23F7A4B3C9B=WJDA65D4TPB54ZAZFQUFKB3T5QK23YUG2FGZIPUKBULKERNK7MH33R7KBMXWQ2QLRZ4RZKLHJ4PDSCIQUGKL5RONMM; TrackID=1kca41gbvojIZ6qN4-fV0x_GhCBUHOy5W9wVxzGS9OBiH_4Tgnqt7AnLiDM3WthwN9leXfF1e-EWXGVkJbBKi6qt1hnFZPUDM_goTiAOyENs; thor=AC09D8FDB30392FA865E6CFD5D3266A21176B3C4F6131D7B7404CAB38973E369A7BE045C52865AF40D8D44B0B9B982DC59E4282BDC6D9235F7EFD73B7C3E9C4683A2646CF00DA39562238C010C1F627FA9EC7BC429EF8C01E95A33C5396D5E5BE9DBACC106B20562A5EE9289BD8AD31A1BF7B7B8BE6892D1E09CF15FAE7C52B5; flash=2_MN5cKYHGHh8Q64kqg674qvd0er6r2eJIXmquSPOZsLbiGlcmcL2N6b9as8bHPVTL-ky7SuaMq3I06GdFjryCwSei0mwAVkjBxyP-LGHdeuq*; pin=%E7%8C%AB%E4%BA%BA%E9%92%88%E7%BA%BA-%E5%85%B3; unick=%E7%8C%AB%E4%BA%BA%E9%92%88%E7%BA%BA-%E5%85%B3; __jda=251704139.725637636.1691192629.1695708521.1695719477.7; __jdc=251704139; __jdb=251704139.5.725637636|7.1695719477"
}



# 自动生成的代码，设置的新值会当作变量传入url
_url = f'https://szgateway.jd.com/szpaas/szajax/industry/industryMarket/getIndustryTrendData.ajax?date=2023-09-25&startDate=2023-09-25&endDate=2023-09-25&dateType=day&channel=99&secondIndId=1345&thirdIndId=999999&h5st=20230926172519502%3b5555478986302294%3b188b4%3btk02w95a31c0c18nOqmNvJMbE1BF%2bBPoz36e3ym0GsxBqBs0TCPW6zSv7sXaLLqgLj7eDM4gXgPTLvqjFPhDCTu7Dpff%3b61b757258b2cfca3b21f60857b483cf4d048ca8bd0538f2c7df32da3adac2083%3b3.1%3b1695720319502%3b24c9ee85e67cf80746dd82817ecbeafc7a829b35c7f446a4c7d476cc9faa1d8834a93323ad7bce9bef1bba682b93d2e33f60c8e1e07512b8d21daffd39fc258791c06ac72719ec111aa6667196e575abf2d870ac874cbf3f4e145e6afdd9e1f6dec0e47bf1ae6dd64a0183f2d1517cf65d8d5e741072ef4ccf12c132ac94eb0e&_stk=date%2cdateType%2cendDate%2cstartDate'#.format()
_post_data_string = ''''''
response = Gk.get_request(_url, _headers_dict,True) 
print(response)
Gk.Guid2DB( _url, _headers_dict, _post_data_string, response)

让我们来看下视频演示效果：

攻克DATA自动生成python代码爬取网页数据