# -*- coding: utf8 -*-import urllib2import urllibimport cookielibimport reimport bs4URL_BAIDU_INDEX = u'http://www.baidu.com/';#https://passport.baidu.com/v2/api/?getapi&class=login&tpl=mn&tangram=true 也可以用這個URL_BAIDU_TOKEN = 'https://passport.baidu.com/v2/api/?getapi&tpl=pp&apiver=v3&class=login';URL_BAIDU_LOGIN = 'https://passport.baidu.com/v2/api/?login';#設置用戶名、密碼username = '';password = '';#設置cookie，這里cookiejar可自動管理，無需手動指定cj = cookielib.CookieJar();opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj));urllib2.install_opener(opener);reqReturn = urllib2.urlopen(URL_BAIDU_INDEX);#獲取token,tokenReturn = urllib2.urlopen(URL_BAIDU_TOKEN);matchVal = re.search(u'"token" : "(?P<tokenVal>.*?)"',tokenReturn.read());tokenVal = matchVal.group('tokenVal');#構造登錄請求參數，該請求數據是通過抓包獲得，對應https://passport.baidu.com/v2/api/?login請求postData = {'username' : username,'password' : password,'u' : 'https://passport.baidu.com/','tpl' : 'pp','token' : tokenVal,'staticpage' : 'https://passport.baidu.com/static/passpc-account/html/v3Jump.html','isPhone' : 'false','charset' : 'UTF-8','callback' : 'parent.bd__pcbs__ra48vi'};postData = urllib.urlencode(postData);#發送登錄請求loginRequest = urllib2.Request(URL_BAIDU_LOGIN,postData);loginRequest.add_header('Accept','text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8');loginRequest.add_header('Accept-Encoding','gzip,deflate,sdch');loginRequest.add_header('Accept-Language','zh-CN,zh;q=0.8');loginRequest.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.72 Safari/537.36');loginRequest.add_header('Content-Type','application/x-www-form-urlencoded');sendPost = urllib2.urlopen(loginRequest);#查看貼吧個人主頁 ，測試是否登陸成功，由于cookie自動管理，這里處理起來方便很多#http://tieba.baidu.com/home/main?un=XXXX&fr=index 這個是貼吧個人主頁，各項信息都可以在此找到鏈接teibaUrl = 'http://tieba.baidu.com/f/like/mylike?v=1387441831248'content = urllib2.urlopen(teibaUrl).read();content = content.decode('gbk').encode('utf8');print content;#解析數據，用的BeautifulSoup4，感覺沒有jsoup用的爽soup = bs4.BeautifulSoup(content);list = soup.findAll('tr');list = list[1:len(list)];careTeibalist = [];print '貼吧鏈接//t吧名//t等級';for elem in list:soup1 = bs4.BeautifulSoup(str(elem));print 'http://tieba.baidu.com/'+soup1.find('a')['href']+'//t'+soup1.find('a')['title']+'//t'+soup1.find('a',{'class','like_badge'})['title'];