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