python爬取四川建设行业数据共享平台

最新推荐文章于 2024-10-07 01:36:35 发布

qq_33955847

最新推荐文章于 2024-10-07 01:36:35 发布

阅读量7.8k

点赞数

文章标签： python

本文链接：https://blog.csdn.net/qq_33955847/article/details/105553417

版权

1.直接上代码

本人第一次写博客，文笔不好，有问题留言评论吧！

import csv
import requests
import time
import tools
from lxml import etree
url = 'http://jst.sc.gov.cn/xxgx/Enterprise/eLWQYList.aspx'
def getres(VIEWSTATE,EVENTVALIDATION,page):
    session=requests.session()
    header="""Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8
    Accept-Encoding: gzip, deflate
    Accept-Language: zh-CN,zh;q=0.9
    Cache-Control: no-cache
    Connection: keep-alive
    Host: jst.sc.gov.cn
    Pragma: no-cache
    Upgrade-Insecure-Requests: 1
    User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"""
    data="""__VIEWSTATEGENERATOR: 763777C1
__EVENTTARGET: ctl00$MainContent$gvBiddingResultPager
mc: 
xydm: """
    datas=tools.make_header(data)
    datas['__VIEWSTATE'] = VIEWSTATE
    datas['__EVENTVALIDATION'] = EVENTVALIDATION
    datas['__EVENTARGUMENT'] = page
    headers=tools.make_header(header)
    res = session.post(url,headers=headers,data=datas)
    html=etree.HTML(res.text)
    item={
   }
    item['gsname'] = html.xpath("//table[@class='table  table-striped table-hover table-search-list']/tbody/tr/td[1]/text()")