音悦台mv视频下载

需要获取的页面:

参考了此处，做了修改，代码如下：

 #coding:utf-8
 import urllib2
 import urllib
 import re
 import sys
 import os
 import time

 class Yinyuetai():

     #地址初始化
     def __init__(self, url):
         self.i = 1
         self.url = url
         self.headers = {
             'User-Agent':'Mozilla/5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36',
             'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
         }
         self.timeout = 30
         self.__init()

     def __init(self, page=1):
         print u"开始下载：第 %d 页 ..." % page
         reurl = self.url + "&page=%d" %page
         page = self.getPage(reurl)
         mvPageList = self.__getMvPageList(page)
         if len(mvPageList) > 0:
             for plist in mvPageList:
                 mvlist = self.getMvURL(plist)
                 self.downLoad(mvlist[0], mvlist[1].decode("utf-8"))
                 self.i += 1
             time.sleep(2)
             page += 1
             self.__init(page)
         else:
             print u"\n~~~~~~~~~~~完成！~~~~~~~~~~~~~~"

     #获取指定页面源码
     def getPage(self, url):
         try:
             request = urllib2.Request(url, None, self.headers)
             response = urllib2.urlopen(request, None, self.timeout)
             return response.read()
         except:
             return []

     #分析列表页，返回MV地址和名字列表[0]:视频ID[1]:视频名称
     def __getMvPageList(self, page):
             reg = r"<h3><a\shref=\"http:\/\/v.yinyuetai.com\/video\/([0-9]+)\".*title=\"(.*)\".*"
             pattern = re.compile(reg)
             findList = re.findall(pattern, page)
             return findList
             #print findList

     def getMvURL(self, mvlist):
         url = "http://www.yinyuetai.com/insite/get-video-info?flex=true&videoId=%d" % int(mvlist[0])
         html = self.getPage(url)

         reg = r"http://\w*?\.yinyuetai\.com/uploads/videos/common/.*?(?=&br)"
         pattern=re.compile(reg)
         findList = re.findall(pattern, html)

         if len(findList) >= 3:
             return [findList[2], mvlist[1]]
         else:
             return [findList[0], mvlist[1]]

     #end def

     #下载文件
     def downLoad(self, url, name):
         name = name + '.flv'
         print u"下载：[%s] [%d]" % (name, self.i)
         local = self.makeDirs() + '/' + name
         try:
             urllib.urlretrieve(url, local, self.schedule)
             print u"下载完成：[%s]\n" % name
         except:
             print u"下载失败！\n"

     def makeDirs(self):
         path = sys.path[0]
         newPath = os.path.join(path, 'flv')
         if not os.path.isdir(newPath):
             os.mkdir(newPath)
         return newPath

     """
     回调函数获取进度
     @ a 已经下载的数据块
     @ b 数据块的大小
     @ c 远程文件的大小
     """
     def schedule(self, a, b, c):
         per = 100.0 *a * b / c
         if per > 100 : per = 100
         sys.stdout.write(u" 进度:%.1f%%\r" % per)
         sys.stdout.flush()

 if __name__ == '__main__':
     url = 'http://mv.yinyuetai.com/all?pageType=page&sort=weekViews&tab=allmv&parenttab=mv'
     Yinyuetai(url)