Fork me on GitHub

import cookielib, urllib, urllib2,time
 
def visit(user,password): 
    login=user
    password=password    
    # Enable cookie support for urllib2
    cookiejar = cookielib.CookieJar()
    urlOpener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookiejar))
          
    url='http://www.renren.com/PLogin.do'
    postdata={
              'email':login,
              'password':password,
              'domain':'renren.com'  
              }
    req=urllib2.Request(
                        url,
                        urllib.urlencode(postdata)            
                        )

    file=urllib2.urlopen(req).read()
     
     
    # Send login/password to the site and get the session cookie
    data = urllib.urlencode(postdata)
    request = urllib2.Request(url, data)
    url = urlOpener.open(request)  # Our cookiejar automatically receives the cookies
    page = url.read(500)
    print page
     
    # Make sure we are logged in by checking the presence of the cookie "id".
    # (which is the cookie containing the session identifier.)
    if not 'id' in [cookie.name for cookie in cookiejar]:
        raise ValueError, "Login failed with login=%s, password=%s" % (login,password)
     
    print "We are logged in !"
     
    # Make another request with our session cookie
    # (Our urlOpener automatically uses cookies from our cookiejar)
    url = urlOpener.open('http://www.renren.com/profile.do?id=279124056')
    page = url.read(200000)

while(1):
    visit(  '','')
    time.sleep(16*60)
    visit(  '','')
    time.sleep(16*60)
    print "ok"


from sgmllib import SGMLParser
import sys,urllib2,urllib,cookielib
class spider(SGMLParser):
    def __init__(self,email,password):
        SGMLParser.__init__(self)
        self.h3=False
        self.h3_is_ready=False
        self.div=False
        self.h3_and_div=False
        self.a=False
        self.depth=0
        self.names=""
        self.dic={}   
         
        self.email=email
        self.password=password
        self.domain='renren.com'
        try:
            cookie=cookielib.CookieJar()
            cookieProc=urllib2.HTTPCookieProcessor(cookie)
        except:
            raise
        else:
            opener=urllib2.build_opener(cookieProc)
            urllib2.install_opener(opener)       

    def login(self):
        url='http://www.renren.com/PLogin.do'
        postdata={
                  'email':self.email,
                  'password':self.password,
                  'domain':self.domain  
                  }
        req=urllib2.Request(
                            url,
                            urllib.urlencode(postdata)            
                            )
        
        self.file=urllib2.urlopen(req).read()
        #print self.file
    def start_h3(self,attrs):
        self.h3 = True
    def end_h3(self):
        self.h3=False
        self.h3_is_ready=True
        
    def start_a(self,attrs):
        if self.h3 or self.div:
            self.a=True
    def end_a(self):
        self.a=False
        
    def start_div(self,attrs):
        if self.h3_is_ready == False:
            return
        if self.div==True:
            self.depth += 1
            
        for k,v in attrs:
            if k == 'class' and v == 'content':
                self.div=True;
                self.h3_and_div=True   #h3 and div is connected
    def end_div(self):
        if self.depth == 0:
            self.div=False
            self.h3_and_div=False
            self.h3_is_ready=False
            self.names=""
        if self.div == True:
            self.depth-=1
    def handle_data(self,text):
        #record the name
        if self.h3 and self.a:
            self.names+=text
        #record says
        if self.h3 and (self.a==False):
            if not text:pass
            else: self.dic.setdefault(self.names,[]).append(text)
            return 
        if self.h3_and_div:
            self.dic.setdefault(self.names,[]).append(text)
            
    def show(self):
        type = sys.getfilesystemencoding()
        for key in self.dic:
            print ( (''.join(key)).replace(' ','')).decode('utf-8').encode(type), \
                  ( (''.join(self.dic[key])).replace(' ','')).decode('utf-8').encode(type)
    
    def visit(self,want_url): 
        pass
#        visitPage=opener.open(want_url)
#        data=visitPage.read()
#        file=open("a.html",'w')
#        file.writelines(data)
#        print data[100:200]
        # if visitPage.geturl()==want_url:
            # print " add one "
        # else:
            # print "failed login"
            # print visitPage.geturl()
                       




renrenspider=spider("","")
#renrenspider=spider('huashiyiqike2@qq.com','huashiyiqike')
renrenspider.login()
# renrenspider.feed(renrenspider.file)
renrenspider.show()
renrenspider.visit("http://www.renren.com/profile.do?id=279124056")
renrenspider=spider("","")
renrenspider.login()
# renrenspider.feed(renrenspider.file)
# renrenspider.show()
renrenspider.visit("http://www.renren.com/profile.do?id=279124056")
renrenspider=spider("","")
renrenspider.login()
# renrenspider.feed(renrenspider.file)
# renrenspider.show()
renrenspider.visit("http://www.renren.com/profile.do?id=279124056")

 

import cookielib, urllib, urllib2,time
 
def visit(user,password): 
    login=user
    password=password    
    # Enable cookie support for urllib2
    cookiejar = cookielib.CookieJar()
    urlOpener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookiejar))
          
    url='http://www.renren.com/PLogin.do'
    postdata={
              'email':login,
              'password':password,
              'domain':'renren.com'  
              }
    req=urllib2.Request(
                        url,
                        urllib.urlencode(postdata)            
                        )

    file=urllib2.urlopen(req).read()
     
     
    # Send login/password to the site and get the session cookie
    data = urllib.urlencode(postdata)
    request = urllib2.Request(url, data)
    url = urlOpener.open(request)  # Our cookiejar automatically receives the cookies
    page = url.read(500)
  #  print page
     
    # Make sure we are logged in by checking the presence of the cookie "id".
    # (which is the cookie containing the session identifier.)
    if not 'id' in [cookie.name for cookie in cookiejar]:
        raise ValueError, "Login failed with login=%s, password=%s" % (login,password)
     
    print "We are logged in !"
     
    # Make another request with our session cookie
    # (Our urlOpener automatically uses cookies from our cookiejar)
    url = urlOpener.open('http://www.renren.com/profile.do?id=279124056')
    page = url.read(200000)
    
count=0
while(True):
    count+=5
    visit(  'vista.blueprint@gmail.com','')
    print 'vista '+time.strftime('%H:%M:%S',time.localtime())
    time.sleep(181)

 

posted on 2013-08-08 12:01  huashiyiqike  阅读(281)  评论(0编辑  收藏  举报