python利用cookie爬淘宝数据

最新推荐文章于 2023-12-30 12:07:45 发布

jidawanghao

最新推荐文章于 2023-12-30 12:07:45 发布

阅读量495

点赞数

本文链接：https://blog.csdn.net/jidawanghao/article/details/108320035

版权

import re
import requests
import pandas as pd
import json
import re
import requests

headers={'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
        'referer': 'https://www.taobao.com/',
        'cookie':'t=************; cna=*******; thw=cn; ali_ab=*********; tg=0; hng=*****; _cc_=*****; uc3=id2=&amp;nk2=&amp;lg2=; tracknick=; enc=*****; cookie2=*****; _tb_token_=*****; x=*****; uc1=cookie14=*****;lng=zh_CN; skt=***; csg=***; v=0; alitrackid=www.taobao.com; lastalitrackid=www.taobao.com; _m_h5_tk=*****; _m_h5_tk_enc=*****; JSESSIONID=*****; l=*****; isg=*****' }
url_1='https://s.taobao.com/search?q=%E6%89%8B%E6%9C%BA&imgfile=&js=1&stats_click=search_radio_all%3A1&initiative_id=staobaoz_20200831&ie=utf8'
res=requests.get(url_1,headers=headers,timeout=10)
res.text
data=re.findall('g_page_config =(.*?)g_srp_loadCss.*',res.text,re.S)
price=[]
name=[]
address=[]
count=[]
title=[]
id_=[]
detail_url=[]
sale=[]
for i in range(10):
    url=url_1.format(i)
    res=requests.get(url,headers=headers,timeout=10)
    data=re.findall('g_page_config =(.*?)g_srp_loadCss',res.text,re.S)
    cont=json.loads(data[0].strip()[:-1])
    for item in cont['mods']['itemlist']['data']['auctions']:
        name.append(item['nick'])
        print(item['nick'])
    print('第'+str(i)+'页爬取完成')
result={'店铺名称':name}
results=pd.DataFrame(result)

https://mp.weixin.qq.com/s/BWgwZGoD5-iex7khNcwW3w