import urllib,urllib2,sys,os
from BeautifulSoup import BeautifulSoup
import itertools,re
url_i =1
pic_num = 1
#自己定義的引號格式轉換函數
def _en_to_cn(str):
  obj = itertools.cycle(['“','”'])
  _obj = lambda x: obj.next()
  return re.sub(r"['\"]",_obj,str)
if __name__ == '__main__':
  #下載連續(xù)3個網頁的視頻
  while url_i <= 3:
    webContent = urllib2.urlopen("http://news.youku.com/focus/index/_page26716_" + str(url_i) + ".html")
    data = webContent.read()
    #利用BeautifulSoup讀取視頻列表網頁數據
    soup = BeautifulSoup(data)
    print "-------------------------Page " + str(url_i) + "-------------------------"
    #獲得相應頁面的視頻thumbnail和title的list
    tag_list_thumb = soup.findAll('li','v_thumb')
    tag_list = soup.findAll('li', "v_title")
    for item in tag_list:
      #通過每個thumbnail中的herf導向視頻播放頁面
      web_video_play = urllib2.urlopen(item.a['href'])
      data_vp = web_video_play.read()
      #利用BeautifulSoup讀取視頻播放網頁數據
      soup_vp = BeautifulSoup(data_vp)
      #找到“下載”對應的鏈接
      tag_vp_list = soup_vp.findAll('a', id = 'fn_download')
      for item_vp in tag_vp_list:
        #將下載鏈接保存到url_dw中
        url_dw = '"' + item_vp['_href'] + '"'
        print item.a['title'] + ": " + url_dw
        #調用命令行運行iku下載視頻，需將iku加入環(huán)境變量
        os.system("iku " + url_dw)
    #保存每個視頻的thumbnail
    for item_thumb in tag_list_thumb:
      urllib.urlretrieve(item_thumb.img['src'], "E:\\下載視頻\\thumbnails\\" + str(pic_num) + "." +
                _en_to_cn(item_thumb.img['title']) + ".jpg")
      pic_num += 1
    print "--------------------------------------------------------------"
    print "--------Page " + str(url_i) + "'s video thumbnails have been saved!"
    url_i += 1