Python模擬163登陸獲取郵件列表
作者：小五義
近期看了《python模擬登陸163郵箱并獲取通訊錄》一文，受到啟發，試著對收件箱、發件箱等進行了分析，并列出了所有郵件列表及狀態，包括發件人、收件人、主題、發信時間、已讀未讀等狀態。
利用cookielib和urllib2模塊模擬登陸163的例子有很多，近期看了《python模擬登陸163郵箱并獲取通訊錄》一文，受到啟發，試著對收件箱、發件箱等進行了分析，并列出了所有郵件列表及狀態，包括發件人、收件人、主題、發信時間、已讀未讀等狀態。
1、參考代碼：http://hi.baidu.com/fc_lamp/blog/item/2466d1096fcc532de8248839.html%EF%BB%BF
- #-*- coding:UTF-8 -*-
- import urllib,urllib2,cookielib
- import xml.etree.ElementTree as etree #xml解析類
- class Login163:
- #偽裝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對象
- cookiefile = './cookies.dat' #cookie臨時存放地
- user = ''
- def __init__(self,username,passwd):
- self.username = username
- self.passwd = passwd
- #cookie設置
- self.cookie = cookielib.LWPCookieJar() #自定義cookie存放
- opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cookie))
- urllib2.install_opener(opener)
- #登陸
- def login(self):
- #請求參數設置
- postdata = {
- 'username':self.username,
- 'password':self.passwd,
- 'type':1
- }
- postdata = urllib.urlencode(postdata)
- #發起請求
- 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,#請求數據
- headers = self.header #請求頭
- )
- result = urllib2.urlopen(req).read()
- result = str(result)
- self.user = self.username.split('@')[0]
- self.cookie.save(self.cookiefile)#保存cookie
- if '登錄成功，正在跳轉...' in result:
- #print("%s 你已成功登陸163郵箱。---------\n" %(user))
- flag = True
- else:
- flag = '%s 登陸163郵箱失敗。'%(self.user)
- return flag
- #獲取通訊錄
- def address_list(self):
- #獲取認證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()用于同時返數字索引與數值，實際上是一個元組:((0,test[0]),(1,test[1]).......)這有點像php里的foreach 語句的作用
- sid = str(sid)
- if 'sid' in sid:
- sid = sid.split()[1].split('=')[1]
- break
- self.cookie.save(self.cookiefile)
- #請求地址
- url = 'http://twebmail.mail.163.com/js4/s?sid='+sid+'&func=global:sequential&showAd=false&userType=browser&uid='+self.username
- #參數設定(var 變量是必需要的,不然就只能看到:<code>S_OK</code><messages/>這類信息)
- #這里參數也是在firebug下查看的。
- postdata = {
- 'func':'global:sequential',
- 'showAd':'false',
- 'sid':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)
- #組裝請求
- req = urllib2.Request(
- url = url,
- data = postdata,
- headers = self.header
- )
- res = urllib2.urlopen(req).read()
- #解析XML，轉換成json
- #說明：由于這樣請求后163給出的是xml格式的數據，
- #為了返回的數據能方便使用最好是轉為JSON
- json = []
- tree = etree.fromstring(res)
- obj = None
- for child in tree:
- if child.tag == 'array':
- obj = child
- break
- #這里多參考一下，etree元素的方法屬性等，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('xxxx@163.com','xxxxx')
- flag = login.login()
- if type(flag) is bool:
- print("Successful landing,Resolved contacts......\n\n")
- res = login.address_list()
- for x in res:
- print(x['email'])
- else:
- print(flag)
#p#
2、分析收件箱、發件箱等網址
在參考代碼中，獲取通訊錄的url為
url = 'http://twebmail.mail.163.com/js4/s?sid='+sid+'&func=global:sequential&showAd=false&userType=browser&uid='+self.username，通過對郵箱地址的分析，發現收件箱、發件箱等的url為url = 'http://twebmail.mail.163.com/js4/s？sid='+sid+'&func=mbox:listMessages&showAd=false&userType=browser&uid='+self.username，其中func=mbox:listMessages。其對收件箱、發件箱的具體區分在下面的postdata中，具體為：
（1）收件箱
- postdata = {
- 'func':'global:sequential',
- 'showAd':'false',
- 'sid':'qACVwiwOfuumHPdcYqOOUTAjEXNbBeAr',
- 'uid':self.username,
- 'userType':'browser',
- 'var':'<!--?xml version="1.0"?--><object><int name="fid">1</int><string name="order">date</string><boolean name="desc">true</boolean><boolean name="topFirst">false</boolean><int name="start">0</int><int name="limit">20</int></object>'
- }
（2）發件箱
- postdata = {
- 'func':'global:sequential',
- 'showAd':'false',
- 'sid':'qACVwiwOfuumHPdcYqOOUTAjEXNbBeAr',
- 'uid':self.username,
- 'userType':'browser',
- 'var':'<!--?xml version="1.0"?--><object><int name="fid">3</int><string name="order">date</string><boolean name="desc">true</boolean><boolean name="topFirst">false</boolean><int name="start">0</int><int name="limit">20</int></object>'
- }
可以看出，兩段代碼的不同之處就是fid的取值不同，其中收件箱為1，發件箱為3，草稿箱為2。
#p#
3、xml解析
利用ElementTree 類來進行xml到字典的轉換。在獲取通訊錄的實例中，主要使用了這一方法。本例子（具體代碼見后文）在收取郵件列表時，并沒有用這一方法，仍然使用的是字符串的處理方法。但這里還是列一下ElementTree 類對xml的處理。如（參考地址：http://hi.baidu.com/fc_lamp/blog/item/8ed2d53ada4586f714cecb3d.html）：
- -<result>
- <code>S_OK</code>
- -<array name="var">
- -<object>
- <string name="code">S_OK</string>
- -<array name="var">
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- +<object></object>
- </array>
- </object>
- +<object></object>
- </array>
- </result>
解決方法：
- #-*- coding:UTF-8 -*-
- import xml.etree.ElementTree as etree #xml解析類
- def xml2json(xml):
- json = []
- tree = etree.fromstring(xml) #如果是文件可用parse(source)
- obj = None
- for child in tree:
- if child.tag == 'array':
- obj = child
- break
- #這里多參考一下，etree元素的方法屬性等，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
#p#
4、收件箱郵件列表
本例子只列出了收件箱郵件列表，如果需要，可根據以上介紹調整fid值，列出發件箱、草稿箱等的郵件列表。程序在windosxp、py2.6環境下調查通過，運行后，會在當前目錄下生成三個文件：inboxlistfile.txt記錄收件箱郵件列表，addfile.txt記錄通訊錄，cookies.dat記錄cookies。具體代碼如下：
- #-*- coding:UTF-8 -*-
- import urllib,urllib2,cookielib
- import xml.etree.ElementTree as etree #xml解析類
- class Login163:
- #偽裝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對象
- cookiefile = './cookies.dat' #cookie臨時存放地
- user = ''
- def __init__(self,username,passwd):
- self.username = username
- self.passwd = passwd
- #cookie設置
- self.cookie = cookielib.LWPCookieJar() #自定義cookie存放
- opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cookie))
- urllib2.install_opener(opener)
- #登陸
- def login(self):
- #請求參數設置
- postdata = {
- 'username':self.username,
- 'password':self.passwd,
- 'type':1
- }
- postdata = urllib.urlencode(postdata)
- #發起請求
- 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,#請求數據
- headers = self.header #請求頭
- )
- result = urllib2.urlopen(req).read()
- result = str(result)
- #print result
- self.user = self.username.split('@')[0]
- self.cookie.save(self.cookiefile)#保存cookie
- if '登錄成功，正在跳轉...' in result:
- #print("%s 你已成功登陸163郵箱。---------n" %(user))
- flag = True
- else:
- flag = '%s 登陸163郵箱失敗。'%(self.user)
- return flag
- #獲取通訊錄
- def address_list(self):
- #獲取認證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()
- #authstr=str(auth)
- #print authstr
- for i,sid in enumerate(self.cookie):
- sid = str(sid)
- #print 'sid:%s' %sid
- if 'sid' in sid:
- sid = sid.split()[1].split('=')[1]
- break
- self.cookie.save(self.cookiefile)
- #請求地址
- url = 'http://twebmail.mail.163.com/js4/s?sid='+sid+'&func=global:sequential&showAd=false&userType=browser&uid='+self.username
- #參數設定(var 變量是必需要的,不然就只能看到:<code>S_OK</code><messages>這類信息)
- #這里參數也是在firebug下查看的。
- postdata = {
- 'func':'global:sequential',
- 'showAd':'false',
- 'sid':'qACVwiwOfuumHPdcYqOOUTAjEXNbBeAr',
- '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)
- #組裝請求
- req = urllib2.Request(
- url = url,
- data = postdata,
- headers = self.header
- )
- res = urllib2.urlopen(req).read()
- #print str(res)
- #解析XML，轉換成json
- #說明：由于這樣請求后163給出的是xml格式的數據，
- #為了返回的數據能方便使用最好是轉為JSON
- json = []
- tree = etree.fromstring(res)
- obj = None
- for child in tree:
- if child.tag == 'array':
- obj = child
- break
- #這里多參考一下，etree元素的方法屬性等，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
- #獲取收件箱
- def minbox(self):
- #獲取認證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()
- #authstr=str(auth)
- #print authstr
- for i,sid in enumerate(self.cookie):
- sid = str(sid)
- #print 'sid:%s' %sid
- if 'sid' in sid:
- sid = sid.split()[1].split('=')[1]
- break
- self.cookie.save(self.cookiefile)
- 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':'<!--?xml version="1.0"?--><object><int name="fid">1</int><string name="order">date</string><boolean name="desc">true</boolean><boolean name="topFirst">false</boolean><int name="start">0</int><int name="limit">20</int></object>'
- }
- postdata = urllib.urlencode(postdata)
- #組裝請求
- req = urllib2.Request(
- url = url,
- data = postdata,
- headers = self.header
- )
- res = urllib2.urlopen(req).read()
- liststr=str(res).split('<object>')#用object進行分割
- inboxlistcount=len(liststr)-1#記錄郵件封數
- inboxlistfile=open('inboxlistfile.txt','w')
- t=0 #記錄當前第幾封信
- for i in liststr:
- if 'xml' in i and ' version=' in i:
- inboxlistfile.write('inbox 共'+str(inboxlistcount)+'信')
- inboxlistfile.write('\n')
- if 'name="id"' in i:
- t=t+1
- inboxlistfile.write('第'+str(t)+'封：')
- inboxlistfile.write('\n')
- #寫入from
- beginnum=i.find('name="from"')
- endnum=i.find('</string>',beginnum)
- inboxlistfile.write('From:'+i[beginnum+12:endnum])
- inboxlistfile.write('\n')
- #寫入to
- beginnum=i.find('name="to"')
- endnum=i.find('</string>',beginnum)
- inboxlistfile.write('TO:'+i[beginnum+10:endnum])
- inboxlistfile.write('\n')
- #寫入subject
- beginnum=i.find('name="subject"')
- endnum=i.find('</string>',beginnum)
- inboxlistfile.write('Subject:'+i[beginnum+15:endnum])
- inboxlistfile.write('\n')
- #寫入date：
- beginnum=i.find('name="sentDate"')
- endnum=i.find('</date>',beginnum)
- inboxlistfile.write('Date:'+i[beginnum+16:endnum])
- inboxlistfile.write('\n')
- if 'name="read">true' in i:
- inboxlistfile.write('郵件狀態:已讀')
- inboxlistfile.write('\n')
- else:
- inboxlistfile.write('郵件狀態:未讀')
- inboxlistfile.write('\n')
- #寫用郵件尺寸
- beginnum=i.find('name="size"')
- endnum=i.find('</int>',beginnum)
- inboxlistfile.write('郵件尺寸:'+i[beginnum+12:endnum])
- inboxlistfile.write('\n')
- #寫入郵件編號，用于下載郵件
- beginnum=i.find('name="id"')
- endnum=i.find('</string>',beginnum)
- inboxlistfile.write('郵件編號:'+i[beginnum+10:endnum])
- inboxlistfile.write('\n\n')
- inboxlistfile.close()
- if __name__=='__main__':
- print("Edit @xiaowuyi V1.0 http://www.cnblogs.com/xiaowuyi")
- login = Login163('XXXX@163.com','AAAAA')
- flag = login.login()
- if type(flag) is bool:
- #login.letterdown()
- print("登陸成功，正在下載列表和通訊錄………………")
- login.minbox()
- res = login.address_list()
- addfile=open('addfile.txt','w')
- for x in res:
- addfile.write(x['email'])
- addfile.close()
- print("已完成")
- else:
- print(flag)
原文鏈接：http://www.cnblogs.com/xiaowuyi/archive/2012/05/21/2511428.html
責任編輯：張偉
來源：
小五義的博客
