Python抓取美剧天堂bt

使用urllib,urllib2,beautifulsoup.

执行下面代码，输入要查找的美剧名即可:

查询到所有结果并遍历每一个结果中不同视频格式的所有下载链接

# coding: utf-8

import urllib

import urllib2

from bs4 import BeautifulSoup

import sys

reload(sys)

sys.setdefaultencoding('utf8')

host= "http://www.meijutt.com"

def getUrlRespHtml(url,data=None):

   heads = {'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

           'Accept-Charset':'GB2312,utf-8;q=0.7,*;q=0.7',

           'Accept-Language':'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',

           'Cache-Control':'max-age=0',

           'Host':host,

           'Connection':'keep-alive',

           'Referer':url,

           'User-Agent':'Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.14) Gecko/20110221 Ubuntu/10.10 (maverick) Firefox/3.6.14'}

   req = urllib2.Request(url)

   opener = urllib2.build_opener(urllib2.HTTPCookieProcessor())

   opener.addheaders = heads.items()

   if data:

       data = urllib.urlencode(data)

       respHtml = opener.open(req,data).read()

   else:

       respHtml = opener.open(req).read()

   return respHtml

def get_bt(url):

   html = getUrlRespHtml(url)

   bs_html = BeautifulSoup(html)

   download_list = bs_html.find_all('div','down_list')

   for index,down_list in enumerate(download_list):

       if len(download_list)>1:

           print '<<<<<视频格式%s>>>>>'%(index+1)

       for li in down_list.find_all('li'):

           f_attrs = li.find('input','down_url').attrs

           print f_attrs.get('value')

def get_bts(searchword):

   data ={'searchword':searchword}

   url = host+'/search.asp'

   html=getUrlRespHtml(url,data)

   bs = BeautifulSoup(html)

   cn_box2 = bs.find_all('div','cn_box2')

   print '\n搜索结果：%s\n'%len(cn_box2)

   for index,div in enumerate(cn_box2):

       print '------搜索结果%s------'%(index+1)

       attrs = div.a.attrs

       title = attrs.get('title')

       href = attrs.get('href')

       print title,(host+href)

       get_bt(host+href)

       print '------end--------\n'

searchword=raw_input("请输入要搜索的美剧:")

get_bts(searchword.encode('gb2312'))