代码如下:
# -*- coding: utf8 -*-”’created on 2013-12-19
@author: good-temper”’
import urllib2import urllibimport cookielibimport reimport bs4
url_baidu_index = u’http://www.baidu.com/’;#https://passport.baidu.com/v2/api/?getapi&https://passport.baidu.com/v2/api/?getapi&tpl=pp&apiver=v3&;url_baidu_login = ‘https://passport.baidu.com/v2/api/?login’;#设置用户名、密码username = ”;password = ”;#设置cookie，这里cookiejar可自动管理，无需手动指定cj = cookielib.cookiejar();opener = urllib2.build_opener(urllib2.httpcookieprocessor(cj));urllib2.install_opener(opener);reqreturn = urllib2.urlopen(url_baidu_index);#获取token,tokenreturn = urllib2.urlopen(url_baidu_token);matchval = re.search(u'”token” : “(?p.*?)”‘,tokenreturn.read());tokenval = matchval.group(‘tokenval’);#构造登录请求参数，该请求数据是通过抓包获得，对应https://passport.baidu.com/v2/api/?login请求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);#发送登录请求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);#查看贴吧个人主页 ，测试是否登陆成功，由于cookie自动管理，这里处理起来方便很多#http://tieba.baidu.com/home/main?un=xxxx&fr=index 这个是贴吧个人主页，各项信息都可以在此找到链接teibaurl = ‘http://tieba.baidu.com/f/like/mylike?v=1387441831248’content = urllib2.urlopen(teibaurl).read();content = content.decode(‘gbk’).encode(‘utf8’);print content;
#解析数据，用的beautifulsoup4，感觉没有jsoup用的爽soup = bs4.beautifulsoup(content);list = soup.findall(‘tr’);list = list[1:len(list)];careteibalist = [];print ‘贴吧链接\t吧名\t等级’;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’];