python自动获取163邮箱的通讯录、收件箱中的寄件人和标题

2019独角兽企业重金招聘Python工程师标准>>>

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

class Login163:
   #伪装browser
    header = {'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}
    username = ''
    passwd = ''
    cookie = None #cookie对象
    cookiefile = './cookies.dat' #cookie临时存放地
    user = ''
    address=''
    mail=''
    
    def __init__(self,username,passwd,address,mail):
        self.username = username
        self.passwd = passwd
        self.address=address
        self.mail=mail
        #cookie设置
        self.cookie = cookielib.LWPCookieJar() #自定义cookie存放
        opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cookie))
        urllib2.install_opener(opener)

   #登陆    
    def login(self):       

        #请求参数设置
        postdata = {
            'username':self.username,
            'password':self.passwd,
            'type':1
            }
        postdata = urllib.urlencode(postdata)

        #发起请求
        req = urllib2.Request(
                url='http://reg.163.com/logins.jsp?type=1&product=mail163&url=http://entry.mail.163.com/coremail/fcg/ntesdoor2?lightweight%3D1%26verifycookie%3D1%26language%3D-1%26style%3D1',
                data= postdata,#请求数据
                headers = self.header #请求头
            )

        result = urllib2.urlopen(req).read()
        result = str(result)
        self.user = self.username.split('@')[0]

        self.cookie.save(self.cookiefile)#保存cookie
        
        if '登录成功，正在跳转...' in result:
            flag = True
        else:
            flag = False
           
        return flag

   #获取通讯录
    def address_list(self):

        #获取认证sid
        auth = urllib2.Request(
                url='http://entry.mail.163.com/coremail/fcg/ntesdoor2?username='+self.user+'&lightweight=1&verifycookie=1&language=-1&style=1',
                headers = self.header
            )
        auth = urllib2.urlopen(auth).read()
        for i,sid in enumerate(self.cookie):#enumerate()用于同时返数字索引与数值，实际上是一个元组:((0,test[0]),(1,test[1]).......)这有点像php里的foreach 语句的作用
            sid = str(sid)
            if 'sid' in sid:
                sid = sid.split()[1].split('=')[1]
                break
        self.cookie.save(self.cookiefile)
        
        #请求地址
        url = 'http://twebmail.mail.163.com/js4/s?sid='+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:S_OK这类信息)
        #这里参数也是在firebug下查看的。
        postdata = {
            'func':'global:sequential',
            'showAd':'false',
            'sid':sid,
            'uid':self.username,
            'userType':'browser',
            'var':''
            }
        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)
        #将通讯录保存在address.txt中
        F=open(self.address+'.txt','w+')           
        for x in json:
            F.write(x['email'])
            F.write('\n')
        F.close()
    
    #获取收件箱
    def minbox(self):#收件箱，fid为1，发件箱为3，草稿箱为2
        #获取认证sid
        auth = urllib2.Request(
                url='http://entry.mail.163.com/coremail/fcg/ntesdoor2?username='+self.user+'&lightweight=1&verifycookie=1&language=-1&style=1',
                headers = self.header
            )
        auth = urllib2.urlopen(auth).read()

        for i,sid in enumerate(self.cookie):
            sid = str(sid)
            if 'sid' in sid:
                sid = sid.split()[1].split('=')[1]
                break
        self.cookie.save(self.cookiefile)
        
        #请求地址
        url = 'http://twebmail.mail.163.com/js4/s?sid='+sid+'&func=mbox:listMessages&showAd=false&userType=browser&uid='+self.username
        postdata = {
            'func':'global:sequential',
            'showAd':'false',
            'sid':'qACVwiwOfuumHPdcYqOOUTAjEXNbBeAr',
            'uid':self.username,
            'userType':'browser',
            'var':''
            }
        postdata = urllib.urlencode(postdata)
        
        #组装请求
        req = urllib2.Request(
            url = url,
            data = postdata,
            headers = self.header
            )
        res = urllib2.urlopen(req).read()
        
        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.getchildren()
        for child in obj:
            for x in child:
                attr = x.attrib
                value=[]
                if attr['name']== 'from':
                    value.append(x.text.encode("utf-8"))
                if attr['name']=='subject':
                    value.append(x.text.encode("utf-8"))
                if len(value)>0:
                    json.extend(value)
        
        F=open(self.mail+'.txt','w+')           
        for x in json:
            F.write(x)
            F.write('\n')
        F.close()
        
#Demo
print("Requesting......\n\n")
login = Login163('[email protected]','8602280','youraddressname','yourmailboxname')
flag = login.login()
if flag==True:
    print("Successful landing")
    login.address_list()
    login.minbox()

转载于:https://my.oschina.net/u/923087/blog/279371