Python類比登陸163郵箱並擷取通訊:
#-*- 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設定
self.cookie = cookielib.LWPCookieJar()
#自訂cookie存放
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cookie))
urllib2.install_opener(opener)
#登陸
def login(self):
#請求參數設定
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,#請求資料
headers = self.header
#要求標頭
)
result = urllib2.urlopen(req).read()
result = str(result)
self.user = self.username.split('@')[0]
self.cookie.save(self.cookiefile)#儲存cookie
if '登入成功,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
#擷取通訊錄
def address_list(self):
#擷取認證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):
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 變數是必需要的,不然就只能看到:<code>S_OK</code><messages/>這類資訊)
#這裡參數也是在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()
#解析XML,轉換成json
#說明:由於這樣請求後163給出的是xml格式的資料,
#為了返回的資料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
#這裡多參考一下,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)