先上指令碼吧,等下來講下知識點:
複製代碼 代碼如下:#!/usr/bin/env python
#encoding=utf-8
import sys
import re
import urllib2
import urllib
import cookielib
class Renren(object):
def __init__(self):
self.name = self.pwd = self.content = self.domain = self.origURL = ''
self.operate = ''#登入進去的操作對象
self.cj = cookielib.LWPCookieJar()
try:
self.cj.revert('renren.coockie')
except Exception,e:
print e
self.opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cj))
urllib2.install_opener(self.opener)
def setinfo(self,username,password,domain,origURL):
'''設定使用者登入資訊'''
self.name = username
self.pwd = password
self.domain = domain
self.origURL = origURL
def login(self):
'''登入人人網'''
params = {'domain':self.domain,'origURL':self.origURL,'email':self.name, 'password':self.pwd}
print 'login.......'
req = urllib2.Request(
'http://www.renren.com/PLogin.do',
urllib.urlencode(params)
)
self.operate = self.opener.open(req)
if self.operate.geturl() == 'http://www.renren.com/Home.do':
print 'Logged on successfully!'
self.cj.save('renren.coockie')
self.__viewnewinfo()
else:
print 'Logged on error'
def __viewnewinfo(self):
'''查看好友的更新狀態'''
self.__caiinfo()
def __caiinfo(self):
'''採集資訊'''
h3patten = re.compile('<h3>(.*?)</h3>')#匹配範圍
apatten = re.compile('<a.+>(.+)</a>:')#匹配作者
cpatten = re.compile('</a>(.+)\s')#匹配內容
infocontent = self.operate.readlines()
# print infocontent
print 'friend newinfo:'
for i in infocontent:
content = h3patten.findall(i)
if len(content) != 0:
for m in content:
username = apatten.findall(m)
info = cpatten.findall(m)
if len(username) !=0:
print username[0],'說:',info[0]
print '----------------------------------------------'
else:
continue
ren = Renren()
username = ''#你的人人網的帳號
password = ''#你的人人網的密碼
domain = 'renren.com'#人人網的地址
origURL = 'http://www.renren.com/Home.do'#人人網登入以後的地址
ren.setinfo(username,password,domain,origURL)
ren.login()
主要用到了python cookielib,urllib2,urllib這3個模組,這3個模組是python做http這方面比較好的模組.
self.cj = cookielib.LWPCookieJar()
try:
self.cj.revert('renren.coockie')
except Exception,e:
print e
self.opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cj))
urllib2.install_opener(self.opener)
這幾行是在本地建立人人網的cookies,因為人人網要驗證cookies才能登入,你運行這個指令碼的話,會發現在目前的目錄 有個程式會自動建立一個renren.cookie這個檔案。
我這裡renren.cookie的資訊是: #LWP-Cookies-2.0 Set-Cookie3: WebOnLineNotice_244225225=1; path="/"; domain=".renren.com"; path_spec; domain_dot; expires="2010-04-11 06:59:33Z"; version=0 總結一下如果網站登入要用cookie的話,就要用到cookielib這個模組,不然你用程式登入不了網站,過斷時間在寫個urlib的例子,大家可以先用上面這個指令碼玩玩!體會下python 人人網代碼的樂趣!