python - 淘宝模拟登陆抓取失败

Question

淘宝模拟登陆抓取失败

# __author__ = ''
# -*- coding: utf-8 -*-
import requests
import re
s = requests.session()
login_data = {'email': 'xxx', 'password': 'xxx', }
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36',
           'Host':'log.mmstat.com',
            'Referer':'https://www.taobao.com/'
           }

# post 数据实现登录
s.post('https://login.taobao.com/member/login.jhtml?redirectURL=https%3A%2F%2Fwww.taobao.com%2F', login_data, headers=headers)
# 验证是否登陆成功，抓取'淘宝'首页看看内容
r = s.get('https://www.taobao.com')
print r.text

还是小白
用户名和密码省去嘞
得到的还是未登录时的代码，不知道自己少了什么，有成功的大神能告知一下咩

Answer 1

Be careful to attach cookies when sending requests~
It is recommended to pay attention to the following points when simulating login:
Look at the request sent during normal login in the browser: #🎜🎜 #

• What fields were submitted?

• What cookies did you bring?

• Does the requested address have parameters?

The following is the crawler I used to crawl Yunnan University Library borrowing information. The default password for Yunda Library login system is the last eight digits of the student number.

Then when submitting the form, it is not only the user name and password, but also a hidden
field. This field is written in the hidden input when the login form is generated, so it must be extracted; #🎜🎜 #In the address of the post form, there is also a jsessionid field, which you also need to extract and add from the login page; lt
In short, I hope my solution ideas can give you some guidance.

Anyway, we will take advantage of it~

When the server detects no abnormalities between your simulated login information and the normally submitted information, the login is successful~

So, a very, very important point---

Imitate normal login Action
, keep thinking about it in the network debugging tool of the browser. Attached below is the simulated login crawler I wrote some time ago

 #coding:utf-8
 #!/usr/bin/python 
  
import HTMLParser 
import urlparse 
import urllib 
import urllib2 
import cookielib 
import string 
import re
import sys
import time
reload(sys)
sys.setdefaultencoding('utf-8')

COOKIE_FLAG = True  # true使用这次cookie  false使用上次cookie

hosturl = "http://202.203.222.202/cas/login"
history = "http://202.203.222.202/myspace/reader/book/historyBorrow?pageSize=200&pageNo=1"

cj = cookielib.LWPCookieJar() 
cookie_support = urllib2.HTTPCookieProcessor(cj) 
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler) 
urllib2.install_opener(opener) 
#获取 lt
def getHTML(stdNum):
    cookie = cookielib.CookieJar()
    handler=urllib2.HTTPCookieProcessor(cookie)
    opener = urllib2.build_opener(handler)
    response = opener.open(hosturl)
    for item in cookie:
        if item.name == "JSESSIONID":
            jsessionId = item.value

    loginHTML = response.read()
    searchString = 'name="lt" value='
    try:
        index = loginHTML.index(searchString)
    except Exception as err:
        print "err:\t" + err
        return False
    lt = loginHTML[index +17:index +56]
    # print "lt:\t" + lt
    print "JD:   "+jsessionId
    targetPost = 'http://202.203.222.202/cas/login;jsessionid='+ jsessionId + '?service=http%3A%2F%2F202.203.222.202%2Fmyspace%2Freader%2Findex'
    headers = {
            'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:14.0) Gecko/20100101 Firefox/14.0.1', 
            "Host": "202.203.222.202",
            "Origin": "http://202.203.222.202",
            "Referer": "http://202.203.222.202/cas/login?service=http://202.203.222.202/myspace/reader/index",
            "Upgrade-Insecure-Requests": 1,
          } 
    postData = {
            "username":stdNum,
            "password":stdNum[3:],
            "lt": lt,
            "execution": 'e1s1',
            "_eventId": "submit",
            "submit": "登录",
          }
    postData = urllib.urlencode(postData)
    request = urllib2.Request(targetPost, postData, headers)
    logResult =  urllib2.urlopen(request).read().decode("utf8")

    if "登录系统" in logResult:
        print "失败啦！"
        return "login failed "
    historyBorrowPage = urllib2.urlopen(history) 
    historyHTML = historyBorrowPage.read().decode('utf8')

    if "登录系统" in historyHTML:
        return False
    else:
        logout = "http://202.203.222.202/myspace/reader/logout"
        logoutYa = urllib2.Request(logout)
        logoutPage = urllib2.urlopen(logoutYa)
        return historyHTML

Answer 2

By the way, why is it Taobao’s address== Just use the cookie you logged in with. Zhihu seems to have a verification code too