Python cookielib 模块

#!/usr/bin/env python
#-*- coding:utf-8 -*-

import urllib2
import cookielib

url = ‘http://www.baidu.com/‘
cookies = cookielib.CookieJar()                   # CookieJar()方法用于收集cookie信息，只有当我们访问一个URL的时候才会有cookie信息，目前只是创建一个cookie对象，里面是没有值的
handler = urllib2.HTTPCookieProcessor(cookies)    # 使用 urllib2 的 HTTPCookieProcessor() 方法，创建一个 cookie 处理器，对收集到的 cookie 进行处理
opener = urllib2.build_opener(handler)            # 使用 urllib2 的 build_opener() 方法，创建一个 opener 实例，该实例用于处理给定的URL链接
response = opener.open(url)                       # opener.open(url) 相当于 urllib2.urlopen(url)，打开链接之后，上面定义的 cookies 就有值了

for cookie in cookies:
    print "%s: %s" % (cookie.name, cookie.value)

[root@localhost ~]$ python 1.py 
BAIDUID: 006F1423AFEFD18A005B7C77DF41CF12:FG=1
BIDUPSID: 006F1423AFEFD18A005B7C77DF41CF12
H_PS_PSSID: 1431_21104_18560_26350_22157
PSTM: 1550233508
delPer: 0
BDSVRTM: 0
BD_HOME: 0

#!/usr/bin/env python
#-*- coding:utf-8 -*-

import re
import sys
import urllib
import urllib2
import cookielib

class AdminSite(object):

    def __init__(self):
        self.login_url = ‘http://www.xxxx.com:8899/accounts/login/‘    # 登录页面的URL
        self.request_url = ‘http://www.xxxx.com:8899/yunwei/index/‘    # 要爬取的页面的URL
        self.headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.81 Safari/537.36‘}
        
    def getPage(self):
        cookie = cookielib.CookieJar()
        handler = urllib2.HTTPCookieProcessor(cookie)
        self.opener = urllib2.build_opener(handler)

        try:
            request = urllib2.Request(url=self.request_url, headers=self.headers)
            response = self.opener.open(request)
            return response.read()
        except urllib2.URLError, e:
            if hasattr(e, ‘code‘):
                print ‘连接服务器失败，错误代码：%s‘ % e.code
            if hasattr(e, ‘reason‘):
                print ‘连接服务器失败，失败原因：%s‘ % e.reason
            else:
                print ‘连接服务器失败，失败原因：%s‘ % e
            sys.exit(1)
          
    def getToken(self):
        page = self.getPage()
        regular = re.compile(r"<form.*?<input.*?value=‘(.*?)‘.*?>", re.S)
        token = regular.search(page)
        if token:
            return token.group(1)
        else:
            return None

    def login(self):
        form_data = {‘csrfmiddlewaretoken‘: self.getToken(),
                     ‘username‘: ‘xxxxxx‘,
                     ‘password‘: ‘xxxxxx‘,
                     ‘next‘: ‘/yunwei/index/‘}
        self.post_data = urllib.urlencode(form_data) 
        try:
            request = urllib2.Request(url=self.login_url, data=self.post_data, headers=self.headers)
            response = self.opener.open(request)
            print response.read()
            return response.read()
        except urllib2.URLError, e:
            if hasattr(e, ‘code‘):
                print ‘连接服务器失败，错误代码：%s‘ % e.code
            if hasattr(e, ‘reason‘):
                print ‘连接服务器失败，失败原因：%s‘ % e.reason
            else:
                print ‘连接服务器失败，失败原因：%s‘ % e
            sys.exit(1)

if __name__ == ‘__main__‘:
    obj = AdminSite()
    obj.login()