_ Git - youtube-dl/blob - youtube_dl/extractor/tudou.py

   1 # coding: utf-8
   2
   3 from __future__ import unicode_literals
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     int_or_none,
   9     float_or_none,
  10     unescapeHTML,
  11 )
  12
  13
  14 class TudouIE(InfoExtractor):
  15     IE_NAME = 'tudou'
  16     _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:(?:programs|wlplay)/view|(?:listplay|albumplay)/[\w-]{11})/(?P<id>[\w-]{11})'
  17     _TESTS = [{
  18         'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
  19         'md5': '140a49ed444bd22f93330985d8475fcb',
  20         'info_dict': {
  21             'id': '159448201',
  22             'ext': 'f4v',
  23             'title': '卡马乔国足开大脚长传冲吊集锦',
  24             'thumbnail': 're:^https?://.*\.jpg$',
  25             'timestamp': 1372113489000,
  26             'description': '卡马乔卡家军，开大脚先进战术不完全集锦！',
  27             'duration': 289.04,
  28             'view_count': int,
  29             'filesize': int,
  30         }
  31     }, {
  32         'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/',
  33         'info_dict': {
  34             'id': '117049447',
  35             'ext': 'f4v',
  36             'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
  37             'thumbnail': 're:^https?://.*\.jpg$',
  38             'timestamp': 1349207518000,
  39             'description': 'md5:294612423894260f2dcd5c6c04fe248b',
  40             'duration': 5478.33,
  41             'view_count': int,
  42             'filesize': int,
  43         }
  44     }]
  45
  46     _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf'
  47
  48     def _url_for_id(self, video_id, quality=None):
  49         info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id)
  50         if quality:
  51             info_url += '&hd' + quality
  52         xml_data = self._download_xml(info_url, video_id, 'Opening the info XML page')
  53         final_url = xml_data.text
  54         return final_url
  55
  56     def _real_extract(self, url):
  57         video_id = self._match_id(url)
  58         item_data = self._download_json(
  59             'http://www.tudou.com/tvp/getItemInfo.action?ic=%s' % video_id, video_id)
  60
  61         youku_vcode = item_data.get('vcode')
  62         if youku_vcode:
  63             return self.url_result('youku:' + youku_vcode, ie='Youku')
  64
  65         title = unescapeHTML(item_data['kw'])
  66         description = item_data.get('desc')
  67         thumbnail_url = item_data.get('pic')
  68         view_count = int_or_none(item_data.get('playTimes'))
  69         timestamp = int_or_none(item_data.get('pt'))
  70
  71         segments = self._parse_json(item_data['itemSegs'], video_id)
  72         # It looks like the keys are the arguments that have to be passed as
  73         # the hd field in the request url, we pick the higher
  74         # Also, filter non-number qualities (see issue #3643).
  75         quality = sorted(filter(lambda k: k.isdigit(), segments.keys()),
  76                          key=lambda k: int(k))[-1]
  77         parts = segments[quality]
  78         result = []
  79         len_parts = len(parts)
  80         if len_parts > 1:
  81             self.to_screen('%s: found %s parts' % (video_id, len_parts))
  82         for part in parts:
  83             part_id = part['k']
  84             final_url = self._url_for_id(part_id, quality)
  85             ext = (final_url.split('?')[0]).split('.')[-1]
  86             part_info = {
  87                 'id': '%s' % part_id,
  88                 'url': final_url,
  89                 'ext': ext,
  90                 'title': title,
  91                 'thumbnail': thumbnail_url,
  92                 'description': description,
  93                 'view_count': view_count,
  94                 'timestamp': timestamp,
  95                 'duration': float_or_none(part.get('seconds'), 1000),
  96                 'filesize': int_or_none(part.get('size')),
  97                 'http_headers': {
  98                     'Referer': self._PLAYER_URL,
  99                 },
 100             }
 101             result.append(part_info)
 102
 103         return {
 104             '_type': 'multi_video',
 105             'entries': result,
 106             'id': video_id,
 107             'title': title,
 108         }
 109
 110
 111 class TudouPlaylistIE(InfoExtractor):
 112     IE_NAME = 'tudou:playlist'
 113     _VALID_URL = r'https?://(?:www\.)?tudou\.com/listplay/(?P<id>[\w-]{11})\.html'
 114     _TESTS = [{
 115         'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo.html',
 116         'info_dict': {
 117             'id': 'zzdE77v6Mmo',
 118         },
 119         'playlist_mincount': 209,
 120     }]
 121
 122     def _real_extract(self, url):
 123         playlist_id = self._match_id(url)
 124         playlist_data = self._download_json(
 125             'http://www.tudou.com/tvp/plist.action?lcode=%s' % playlist_id, playlist_id)
 126         entries = [self.url_result(
 127             'http://www.tudou.com/programs/view/%s' % item['icode'],
 128             'Tudou', item['icode'],
 129             item['kw']) for item in playlist_data['items']]
 130         return self.playlist_result(entries, playlist_id)
 131
 132
 133 class TudouAlbumIE(InfoExtractor):
 134     IE_NAME = 'tudou:album'
 135     _VALID_URL = r'https?://(?:www\.)?tudou\.com/album(?:cover|play)/(?P<id>[\w-]{11})'
 136     _TESTS = [{
 137         'url': 'http://www.tudou.com/albumplay/v5qckFJvNJg.html',
 138         'info_dict': {
 139             'id': 'v5qckFJvNJg',
 140         },
 141         'playlist_mincount': 45,
 142     }]
 143
 144     def _real_extract(self, url):
 145         album_id = self._match_id(url)
 146         album_data = self._download_json(
 147             'http://www.tudou.com/tvp/alist.action?acode=%s' % album_id, album_id)
 148         entries = [self.url_result(
 149             'http://www.tudou.com/programs/view/%s' % item['icode'],
 150             'Tudou', item['icode'],
 151             item['kw']) for item in album_data['items']]
 152         return self.playlist_result(entries, album_id)