复制代码 代码如下:
from sgmllib import SGMLParser
import sys, urllib2, urllib, cookielib
import datetime, time
class spider(SGMLParser):
def __init__(self, email, password):
SGMLParser.__init__(self)
self.email = email
self.password = password
self.domain = 'renren.com'
try:
cookie = cookielib.CookieJar()
# a class to handle HTTP cookies
cookieProc = urllib2.HTTPCookieProcessor(cookie)
except:
raise
else:
opener = urllib2.build_opener(cookieProc)
urllib2.install_opener(opener)
def login(self):
print '开始登录'
url = 'http://www.renren.com/PLogin.do'
#url = 'http://www.renren.com/SysHome.do'
postdata = {
'email': self.email,
'password': self.password,
'domain': self.domain
}
# 一般情况下引入urllib2的地方都需要引入urllib,因为需要urlencode()
req = urllib2.Request(
url,
urllib.urlencode(postdata)
)
self.file = urllib2.urlopen(req).read()
# urlopen后 成功后进入首页 因此self.file的内容就是首页的html文件的内容
# print self.file
idPos = self.file.index("'id':'")
self.id = self.file[idPos+6:idPos+15]
tokPos = self.file.index("get_check:'")
self.tok = self.file[tokPos+11:tokPos+21]
rtkPos = self.file.index("get_check_x:'")
self.rtk = self.file[rtkPos+13:rtkPos+21]
def publish(self, content):
url1 = 'http://shell.renren.com/' +self.id+ '/status'
print 'self.id = ' , self.id
postdata = {
'content': content,
'hostid': self.id,
'requestToken': self.tok,
'_rtk': self.rtk,
'channel': 'renren',
}
req1 = urllib2.Request(
url1,
urllib.urlencode(postdata)
)
self.file1 = urllib2.urlopen(req1).read()
print datetime.datetime.now()
print '刚才账号 %s发了一条状态' % self.email
print '内容为: %s' % postdata.get('content', '')
renrenspider = spider('qich555550@163.com', 'qishibo123')
renrenspider.login()
contents =["祝","各","位","同","学","盆","友","在","新","的","一","年","里","身","体","健","康","万","事","如","意","不小心刷屏了,望大家谅解"]
for content in contents:
renrenspider.publish(content)
Copyright© 2013-2020
All Rights Reserved 京ICP备2023019179号-8