音悦台mv视频下载

  1 #coding:utf-8
  2 import urllib2
  3 import urllib
  4 import re
  5 import sys
  6 import os
  7 import time
  8 
  9 
 10 class Yinyuetai():
 11 
 12     #地址初始化
 13     def __init__(self, url):
 14         self.i = 1
 15         self.url = url
 16         self.headers = {
 17             ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36‘,
 18             ‘Accept‘:‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8‘
 19         }
 20         self.timeout = 30
 21         self.__init()
 22 
 23 
 24     def __init(self, page=1):
 25         print u"开始下载：第 %d 页 ..." % page
 26         reurl = self.url + "&page=%d" %page
 27         page = self.getPage(reurl)
 28         mvPageList = self.__getMvPageList(page)
 29         if len(mvPageList) > 0:
 30             for plist in mvPageList:
 31                 mvlist = self.getMvURL(plist)
 32                 self.downLoad(mvlist[0], mvlist[1].decode("utf-8"))
 33                 self.i += 1
 34             time.sleep(2)
 35             page += 1
 36             self.__init(page)
 37         else:
 38             print u"\n~~~~~~~~~~~完成！~~~~~~~~~~~~~~"
 39 
 40 
 41 
 42     #获取指定页面源码
 43     def getPage(self, url):
 44         try:
 45             request = urllib2.Request(url, None, self.headers)
 46             response = urllib2.urlopen(request, None, self.timeout)
 47             return response.read()
 48         except:
 49             return []
 50 
 51     #分析列表页，返回MV地址和名字列表[0]:视频ID[1]:视频名称
 52     def __getMvPageList(self, page):
 53             reg = r"<h3><a\shref=\"http:\/\/v.yinyuetai.com\/video\/([0-9]+)\".*title=\"(.*)\".*"
 54             pattern = re.compile(reg)
 55             findList = re.findall(pattern, page)
 56             return findList
 57             #print findList
 58 
 59 
 60 
 61     def getMvURL(self, mvlist):
 62         url = "http://www.yinyuetai.com/insite/get-video-info?flex=true&videoId=%d" % int(mvlist[0])
 63         html = self.getPage(url)
 64 
 65         reg = r"http://\w*?\.yinyuetai\.com/uploads/videos/common/.*?(?=&br)"
 66         pattern=re.compile(reg)
 67         findList = re.findall(pattern, html)
 68 
 69         if len(findList) >= 3:
 70             return [findList[2], mvlist[1]]
 71         else:
 72             return [findList[0], mvlist[1]]
 73 
 74 
 75     #end def
 76 
 77     #下载文件
 78     def downLoad(self, url, name):
 79         name = name + ‘.flv‘
 80         print u"下载：[%s] [%d]" % (name, self.i)
 81         local = self.makeDirs() + ‘/‘ + name
 82         try:
 83             urllib.urlretrieve(url, local, self.schedule)
 84             print u"下载完成：[%s]\n" % name
 85         except:
 86             print u"下载失败！\n"
 87 
 88     def makeDirs(self):
 89         path = sys.path[0]
 90         newPath = os.path.join(path, ‘flv‘)
 91         if not os.path.isdir(newPath):
 92             os.mkdir(newPath)
 93         return newPath
 94 
 95     """
 96     回调函数获取进度
 97     @ a 已经下载的数据块
 98     @ b 数据块的大小
 99     @ c 远程文件的大小
100     """
101     def schedule(self, a, b, c):
102         per = 100.0 *a * b / c
103         if per > 100 : per = 100
104         sys.stdout.write(u" 进度:%.1f%%\r" % per)
105         sys.stdout.flush()
106 
107 
108 
109 
110 if __name__ == ‘__main__‘:
111     url = ‘http://mv.yinyuetai.com/all?pageType=page&sort=weekViews&tab=allmv&parenttab=mv‘
112     Yinyuetai(url)