Python写的163邮箱的登陆并抓出联系人

#-*- coding:utf-8 -*-
import urllib, urllib2, cookielib
import xml.etree.ElementTree as etree

class Login163:
    header = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}
    username = ''
    passwd = ''
    cookie = None #cookie
    cookiefile = './cookie.dat'
    user = ''
    sid = ''
    
    def __init__(self, username, passwd):
        self.username = username
        self.passwd = passwd
        #cookie
        self.cookie = cookielib.LWPCookieJar()
        opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cookie))
        urllib2.install_opener(opener)
    
    def login(self):
        postdata = {
                    'username': self.username,
                    'password': self.passwd,
                    'type': 1
                    }
        postdata = urllib.urlencode(postdata)
        
        #用户登录
        req = urllib2.Request(
                              url = 'https://ssl.mail.163.com/entry/coremail/fcg/ntesdoor2?df=webmail163&from=web&funcid=loginone&iframe=1&language=-1&net=null&passtype=1&product=mail163&race=-2_-2_-2_db&style=-1&uid=' + self.username, 
                              data = postdata,#POST请求发送的参数
                              headers = self.header#
        )
        result = urllib2.urlopen(req).read()
        result = str(result)
        self.user = self.username.split('@')[0]
        self.cookie.save(self.cookiefile)#
        
        if 'sid=' in result:
            print ('%s  你已成功登陆163邮箱') %(self.user)
            self.sid = result.split('=')[3].split('"')[0]
            self.cookie.save(self.cookiefile)
            flag = True
        else:
            flag = False
            print '%s 登陆163邮箱失败' %(self.user)
        return flag
    
#获取通讯录
    def address_list(self):
        
        #请求地址
        url = 'http://twebmail.mail.163.com/js4/s?sid='+self.sid+'&func=global:sequential&showAd=false&userType=browser&uid='+self.username
        #参数设定(var 变量是必需要的,不然就只能看到:<code>S_OK</code><messages/>这类信息)
        #这里参数也是在firebug下查看的。
        postdata = {
            'func':'global:sequential',
            'showAd':'false',
            'sid':self.sid,
            'uid':self.username,
            'userType':'browser',
            'var':'<?xml version="1.0"?><object><array name="items"><object><string name="func">pab:searchContacts</string><object name="var"><array name="order"><object><string name="field">FN</string><boolean name="desc">false</boolean><boolean name="ignoreCase">true</boolean></object></array></object></object><object><string name="func">pab:getAllGroups</string></object></array></object>'
            }
        postdata = urllib.urlencode(postdata)
        
        #组装请求
        req = urllib2.Request(
            url = url,
            data = postdata,
            headers = self.header
            )
        res = urllib2.urlopen(req).read()
        
        #解析XML，转换成json
        #说明：由于这样请求后163给出的是xml格式的数据，
        #为了返回的数据能方便使用最好是转为JSON
        json = []
        tree = etree.fromstring(res)
        obj = None
        for child in tree:
            if child.tag == 'array':
                obj = child            
                break
        #这里多参考一下，etree元素的方法属性等，包括attrib,text,tag,getchildren()等
        obj = obj[0].getchildren().pop()
        for child in obj:
            for x in child:
                attr = x.attrib
                if attr['name']== 'EMAIL;PREF':
                    value = {'email':x.text}
                    json.append(value)
        return json
        
#Demo
print("Requesting......\n\n")
login = Login163('XXX@163.com','XXXXXX')
flag = login.login()
if flag is True:
    print("Successful landing,Resolved contacts......\n\n")
    res = login.address_list()
    for x in res:
        print(x['email'])
else:
    print(flag)

参考了http://www.cnblogs.com/xiaowuyi/archive/2012/05/21/2511428.html的写法。

只是在登陆的时候改了一下，

归根结底，登陆就是要获取sid号，你拥有了sid号，你才能登陆并进行相关操作。

我的程序在获取sid号方面，跟参考程序有所不同，我是从网页中解析出的sid，

而参考程序是从cookie中，找出的sid。

其实都差不多，了解原理就好。