python登陆asp网站页面的实现代码
程序员文章站
2022-06-30 09:22:33
使用python来登录asp网站和登录其他网站差不多,只是因为asp页面在每次请求的时候都要带上viewstate,因此使用python来登录的话就多了一个步骤,获得这个页...
使用python来登录asp网站和登录其他网站差不多,只是因为asp页面在每次请求的时候都要带上viewstate,因此使用python来登录的话就多了一个步骤,获得这个页面的viewstate之后带上这个和你要post或get到该页面的请求数据就好了,下面这段程序是登录一个asp系统,然后搜索某些数据并将这些数据保存下来.
#coding=utf-8 import urllib2 from bs4 import beautifulsoup import urllib import cookielib import re import httplib import time loginurl="登录地址" headers={"user-agent":"mozilla/5.0 (windows nt 6.1) applewebkit/537.36 (khtml, like gecko) chrome/37.0.2062.120 safari/537.36"} studentcookie = cookielib.cookiejar() pageopener = urllib2.build_opener(urllib2.httpcookieprocessor(studentcookie)) loginpagerequest = urllib2.request(loginurl) loginpagehtml = pageopener.open(loginpagerequest).read() """ s=requests.session() s.headers.update(headers) r=s.get(loginurl) """ print loginpagehtml soup=beautifulsoup(loginpagehtml) __viewstate=soup.find(id="__viewstate")['value'] __eventvalidation=soup.find(id="__eventvalidation")['value'] print __viewstate print __eventvalidation login_data={ ' __eventtarget':'', '__eventargument':'', '__lastfocus':'', '__viewstate':__viewstate, '__eventvalidation':__eventvalidation, 'clienscreentheight':'768', 'textboxuserid':'username', 'textboxpwd':'password', 'drplanguage':'zh-cn', 'buttonconfirm.x':'45', 'buttonconfirm.y':'64' } loginheader = { 'user-agent':'sssssssssssssssssssssss' } logindata=urllib.urlencode(login_data) loginrequest = urllib2.request(loginurl , logindata , headers) loginresponse = pageopener.open(loginrequest) print loginresponse theurl='登录后搜索页面地址' mainpagerequest = urllib2.request(theurl) mainpagehtml = pageopener.open(mainpagerequest).read() soup=beautifulsoup(mainpagehtml) __viewstate=soup.find(id="__viewstate")['value'] #__eventvalidation=soup.find(id="__eventvalidation")['value'] print __viewstate #print __eventvalidation searchdata={ '__viewstate':__viewstate, '__eventvalidation':'', 'txtcopno':'', 'txtcar_no_s':'', 'drpstatus':'', 'txthiddenoronline':'none', 'txtauto_id':'', 'drptype':'', 'drpbasetype':'', 'ddlisstatus':0, 'txticcard':'', 'txtbill_no':'', 'txtgdatetime1':'', 'txtgdatetime2':'', 'drpfromka':'', 'drptoka':'', 'btnsearch':'%e6%9f%a5+%e8%af%a2%28f%29' } data2=urllib.urlencode(searchdata) searchdata=urllib.urlencode(searchdata) searcgrequest=urllib2.request(theurl , searchdata , headers) searchresponse=pageopener.open(searcgrequest) print loginresponse print searchresponse searchhtml=searchresponse.read() filename= r'c:\users\dell\desktop\getlogin\file'+time.strftime('%d%h%m',time.localtime(time.time()))+'.html' file=open(filename,'w') file.write(searchhtml) file.close() print 'end' #raw_input()
原文: