douban reder

douban

#encoding: utf-8
#author:t-y  
#http://pythoner.net
import time,math,os,re,urllib,urllib2,cookielib
 
class douban_robot:
    email = '[email protected]'
    password = 'sdhjl200'
    login_path = 'https://www.douban.com/accounts/login'
     
    def __init__(self):
        self.cj =cookielib.LWPCookieJar()
        self.opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(self.cj))
        urllib2.install_opener(self.opener)
        self.opener.addheaders = [('User-agent','Opera/9.23')]
  self.opener.addheaders = [('Accept-Charset', 'utf-8')]
  
    def login(self):
        post_data = urllib.urlencode({
            'form_email':self.email,
            'form_password':self.password,
            'remeber':'on',
            })
        
        request = urllib2.Request(self.login_path,post_data)
        html = self.opener.open(request).read()
	
	#encoding=request.headers['content-type'].split('charset=')[-1]
	html = unicode(html, 'utf-8')
        print re.findall('<h1>(.*)</h1>',html,re.S)[0].decode('utf-8') 
        get_url = self.opener.open(request).geturl()
        if get_url == 'http://www.douban.com/':
            self.cj.save('douban.cookie')
            print 'Login success !'
            return True
        else:
            print get_url
            print 'Login error'
            return False
 
    def run(self,d_url):
        self.login()
        return
        self.post_url = d_url       
        while True:
            if self.sleep_time() > 10:
                timer = self.sleep_time()-10
                print '%s:waiting %s' %(time.strftime('%H:%M:%S'),timer) 
                time.sleep(timer)
            response = urllib2.Request(self.post_url)
            html = urllib2.urlopen(response).read()
            ck = re.findall('(?<=class=\"page\"  \/><\/div>)',html,re.S)[0]
            if ck[0]<>'':
                print 'get ck success!'
		print ck[0]
            timer = self.sleep_time()
            time.sleep(timer)
            dt = list(time.localtime())
            minit = dt[4]
            second = dt[5]
            #if minit==second==0:
                #request = urllib2.Request(self.post_url,post_data)
                #urllib2.urlopen(request)
 
    def sleep_time(self):
        dt = list(time.localtime())
        hour = dt[3]
        minut = dt[4]
        second = dt[5]
        return 3600-(minut*60+second)
 
    def get_title(self):
        title = re.findall('<title>(.*)</title>',self.html,re.S)[0].decode('utf8')   
        h1 = re.findall('<h1>(.*)</h1>',self.html,re.S)[0].decode('utf8')
        print '%s--%s' %(title,h1)
 
    def write_log(self,text):
        os.system('cls')
        print text
        log = open('log.txt','a')
        log.write(text)
        log.close()      
 
url = 'http://read.douban.com/reader/ebook/384559/page/121/' 
app = douban_robot()
app.run(url)