利用攻克进行京东类目采集目前是有两种方式可以实现:
一、自己利用selenium或者影刀点击切换店铺,然后通过攻克配置直接保存数据到数据库
下载地址:https://www.yuque.com/gk.ai/gkdata/zn5r4grngkk2lidp
推荐:GKA496F78CB479347D4F5B3E05892795A5
二、第二种是利用攻克先全部店铺登录一遍拿到cookie
然后利用攻克生成的python代码再循环遍历cookie就可以形成一套完整的京东类目数据采集啦
生成的python是下面这样的:
import sys
sys.path.append( r'D:\Tools\GKData\ApiConfig')
import Gk
Gk.Guid2DB_Path = r'"D:\Tools\GKData\3rdLibs\Guid2DB.exe" '
def 从数据库账号批量下载实例():
import pymssql
db = pymssql.connect(连接信息,charset='utf8')
cursor = db.cursor()
cursor.execute("SELECT [平台店铺ID],[请求头],[Cookie] FROM [账号信息] where 平台='京东' and 状态='RUN' order by 1 desc")
result_login = cursor.fetchall()
# print(result_login)
db.commit()
cursor.close( )
db.close()
for rec in result_login:
cookie=rec[2]
# 根据实际代码替换下面代码:
_headers_dict = {
"Host": "sz.jd.com",
"Connection": "keep-alive",
"Cookie": f"{cookie}",
}
# 自动生成的代码,设置的新值会当作变量传入url
_url = f'https://sz.jd.com/sz/api/realtime/getRealtimeData.ajax?'#.format()
_post_data_string = ''''''
response = Gk.get_request(_url, _headers_dict,True)
print(response)
#Gk.Guid2DB( _url, _headers_dict, _post_data_string, response)
#从数据库账号批量下载实例()
# 实际代码:
_headers_dict = {
"Host": "sz.jd.com",
"Connection": "keep-alive",
"sec-ch-ua": "\"Not.A/Brand\";v=\"8\", \"Chromium\";v=\"114\", \"Google Chrome\";v=\"114\"",
"sec-ch-ua-mobile": "?0",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36",
"Accept": "application/json, text/plain, */*",
"User-mup": "1689572845832",
"p-pin": "%E7%8C%AB%E4%BA%BA%E9%92%88%E7%BA%BA-%E5%85%B3",
"uuid": "84e6f8ada79706ac744f-1896263a908",
"X-Requested-With": "XMLHttpRequest",
"User-mnp": "95d5423e4ed45e52e84701e0d15ae9e3",
"sec-ch-ua-platform": "\"Windows\"",
"Sec-Fetch-Site": "same-origin",
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Dest": "empty",
"Referer": "https://sz.jd.com/sz/view/dealAnalysis/dealFeatures.html",
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "zh-CN,zh;q=0.9",
"Cookie": "__jdu=1677815960962839351025; shshshfpa=84c470ea-cff6-210a-eff2-eddfcca5378b-1678864499; shshshfpx=84c470ea-cff6-210a-eff2-eddfcca5378b-1678864499; shshshfpb=pGTg8S96J3RZFlKtDAOleTQ; close_2021_datuanyuan=true; shshshfp=753d08fe4cee56f22e819f80a5297de6; unpl=JF8EALJnNSttW01WBE4LTxEWT15RWwgITB5QbmYDAQ9QTVBSE1JIGhV7XlVdXxRKER9uYhRUWVNKVg4eASsSEXteU11bD00VB2xXVgQFDQ8WUUtBSUt-SVxRWFULSBMCa2IFZG1bS2QFGjIbFRZNVFRaVQ9KHwRsbgdcX1xLVQYfMhoiF3ttZFxbC0IeAV9mNVVtGh8IAxIFGRAYBl1TWFsBSxMLaGYNU15RSVwHHwIaERR7XGRd; __jdv=76161171|baidu-search|t_262767352_baidusearch|cpc|304792250541_0_2730d8e275244d168b007dc975f9ab94|1688454222885; ipLoc-djd=17-1381-50712-62966; is_sz_old_version=false; user-key=059944c8-5b2e-4668-9d75-6a43caf8bf29; 3AB9D23F7A4B3CSS=jdd037FBOII2QKMVBJK6SEC5YPMDDI6YD5FSKEGFXTAH5Q7GJ4XCJTNPL2EDDAI3MQI5UUXHZFCT3PANI6B4WO5DN4ID65QAAAAMJETFX6MYAAAAACWIF5EBHCF4FFQX; language=zh_CN; ceshi3.com=000; __USE_NEW_PAGEFRAME__=false; _base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wlfstk_smdl=xg2q7y91uxstwp64sn5tx5y7q0x1uxbr; TrackID=1U-ntEgeiDPOb41NtpY-cU96XGYnJRqYJX9h7_nVDr4V1LLNKrlTCjPQa7uIo5z3nQRRheMv7mtMgbinoZXE_YnUAIJfhtUa-V3QWJVcaUGQ; thor=AC09D8FDB30392FA865E6CFD5D3266A2C84E7F880265F87DB8B93AC0D2E235727F1B4CF99CD68D9A0B288CF0A902AF537AFFB154805A76C36D7AEDC3ABAF559149F411760E9891389A2D1AD9DFCE34585D2908E301515F0E395AD23AC32270D9F0658DBFD8ABBB16FB24F5BB1CDF921C44429E9C7067832568F4926949DD4884; flash=2_VQXRRX-sMATCwFpHDiPEGl3SDbxAFKgllVMgqviWCUUI6t4liDBuBgYa8TzoZJVBP4MuofDeeL28plXx0WqZ_xUAVnKkqATPnGv8WggCLmP*; pinId=vOuujp2GM_HPXPHJr9XWTbV9-x-f3wj7; 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; _tp=9hek%2BXTf8ylULoFOWfDPkk42THGVHy%2B5BXj2LBy9p0UMtDwuEHXu4jObkMsJl%2F%2Fq; _pst=%E7%8C%AB%E4%BA%BA%E9%92%88%E7%BA%BA-%E5%85%B3; b-sec=RMBIUHLOT4656L65AOYFDSLB47B34Y73NCLRJM6JOLYJDMCSFHLOMYAASYIPO7BXQWPT73RMQO37K; __jda=251704139.1677815960962839351025.1677815960.1689565995.1689572723.149; __jdc=251704139; __jdb=251704139.6.1677815960962839351025|149.1689572723"
}
# 自动生成的代码,设置的新值会当作变量传入url
_url = f'https://sz.jd.com/sz/api/trade/getCategoryFeatureData.ajax?channel=99&date=2023-07-16&endDate=2023-07-16&startDate=2023-07-16'#.format()
_post_data_string = ''''''
response = Gk.get_request(_url, _headers_dict,True)
print(response)
Gk.Guid2DB( _url, _headers_dict, _post_data_string, response)
然后需要自己加工一下日期之类的就可以了,如果不考虑日期这个代码就可以直接运行啦。