【Python爬虫】教务处模拟登陆

Python2模拟登陆获取cookie

import urllib

import urllib2

import cookielib

filename = 'cookie.txt'

#声明一个MozillaCookieJar对象实例来保存cookie，之后写入文件

cookie = cookielib.MozillaCookieJar(filename)

opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))

#设置请求参数

values = {}

values['__VIEWSTATE'] = "******"

values['tbxUserID'] = "XXXXXXX"

values['InputPwd'] = "XXXXXX"

values['btnLogin.x'] = "55"

values['btnLogin.y'] = "23"

postdata = urllib.urlencode(values)

#登录教务系统的URL

loginUrl = 'http://yjsgl.***.edu.cn/login.aspx'

#模拟登录，并把cookie保存到变量

#设置header

user_agent = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'

opener.addheaders.append( ('Host', 'yjsgl.fzu.edu.cn') )

opener.addheaders.append( ('User-Agent', user_agent) )

opener.addheaders.append( ('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8') )

opener.addheaders.append( ('Accept-Language', 'zh-CN,zh;q=0.8') )

opener.addheaders.append( ('Accept-Encoding', 'gzip, deflate') )

opener.addheaders.append( ('Connection', 'keep-alive') )

opener.addheaders.append( ('Referer', 'http://yjsgl.fzu.edu.cn/login.aspx') )

try:

    result = opener.open(loginUrl,postdata)

except opener.URLError, e:

    print e.reason

for item in cookie:

    print 'Name = '+item.name

    print 'Value = '+item.value

#保存cookie到cookie.txt中

cookie.save(ignore_discard=True, ignore_expires=True)

#利用cookie请求访问另一个网址，此网址是成绩查询网址

gradeUrl = 'http://yjsgl.***.edu.cn/xsgl/xsxx_show.aspx'

#请求访问成绩查询网址

result = opener.open(gradeUrl)

print result.read()

直接从本地读取cookie模拟登陆

# -*- coding: utf-8 -*-

"""

Created on Fri Apr 14 16:12:55 2017

@author: zeze

"""

import cookielib

import urllib2

#创建MozillaCookieJar实例对象

cookie = cookielib.MozillaCookieJar()

#从文件中读取cookie内容到变量

cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)

#创建请求的request

Url = urllib2.Request("http://yjsgl.***.edu.cn/xsgl/xsxx_show.aspx")

#利用urllib2的build_opener方法创建一个opener

opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))

response = opener.open(Url)

print response.read()

　　Python3版本

import urllib

#import cookielib

import  http.cookiejar

filename = 'cookie.txt'

# 声明一个MozillaCookieJar对象实例来保存cookie，之后写入文件

#设置一个cookie处理器，它负责从服务器下载cookie到本地，并且在发送请求时带上本地的cookie

cookie = http.cookiejar.MozillaCookieJar(filename)

#opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))

cookie_support = urllib.request.HTTPCookieProcessor(cookie)

opener = urllib.request.build_opener(cookie_support, urllib.request.HTTPHandler)

urllib.request.install_opener(opener)

# 设置请求参数

values = {}

values['__VIEWSTATE'] = "/wEPDwUJODA3MTI1345b2xzUmVxdWlyZVBvc3RCYWNrS2V5X18WAgUIYnRuTG9naW4FDEltYWdlQnV0dG9uMQ=="

values['tbxUserID'] = "1345"

values['InputPwd'] = "5345e"

values['btnLogin.x'] = "55"

values['btnLogin.y'] = "23"

#postdata = urllib.urlencode(values)

postdata=urllib.parse.urlencode(values).encode('utf-8')

# 登录教务系统的URL

loginUrl = 'http://yjsgl.123.e34u.cn/login.aspx'

# 模拟登录，并把cookie保存到变量

# 设置header

user_agent = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'

opener.addheaders.append(('Host', 'yjsgl.fzu.edu.cn'))

opener.addheaders.append(('User-Agent', user_agent))

opener.addheaders.append(

    ('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'))

opener.addheaders.append(('Accept-Language', 'zh-CN,zh;q=0.8'))

opener.addheaders.append(('Accept-Encoding', 'gzip, deflate'))

opener.addheaders.append(('Connection', 'keep-alive'))

opener.addheaders.append(('Referer', 'http://yjsgl.f234u.cn/login.aspx'))

try:

    result = opener.open(loginUrl, postdata)

except opener.URLError as e:

    print(e.reason)

for item in cookie:

    print('Name = ' + item.name)

    print('Value = ' + item.value)

# 保存cookie到cookie.txt中

cookie.save(ignore_discard=True, ignore_expires=True)

# 利用cookie请求访问另一个网址，此网址是成绩查询网址

gradeUrl = 'http://yjsgl.fzu.edu.cn/xsgl/xsxx_show.aspx'

# 请求访问成绩查询网址

result = opener.open(gradeUrl)

print("返回的结果")

print(result.read().decode('utf8'))#先看.info 解决乱码的问题

text = result.read()

save_path="D:/snatch2.txt"

# save_path 's file unnecessary to be exist

f_obj = open(save_path,'wb')

f_obj.write(text)

print("snatch successfully.")