Raphaël G. Git Repositories - youtubedl/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     ExtractorError,
   9     int_or_none,
  10     InAdvancePagedList,
  11     float_or_none,
  12     unescapeHTML,
  13 )
  14
  15
  16 class TudouIE(InfoExtractor):
  17     IE_NAME = 'tudou'
  18     _VALID_URL = r'https?://(?:www\.)?tudou\.com/(?:(?:programs|wlplay)/view|(?:listplay|albumplay)/[\w-]{11})/(?P<id>[\w-]{11})'
  19     _TESTS = [{
  20         'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
  21         'md5': '140a49ed444bd22f93330985d8475fcb',
  22         'info_dict': {
  23             'id': '159448201',
  24             'ext': 'f4v',
  25             'title': '卡马乔国足开大脚长传冲吊集锦',
  26             'thumbnail': 're:^https?://.*\.jpg$',
  27             'timestamp': 1372113489000,
  28             'description': '卡马乔卡家军，开大脚先进战术不完全集锦！',
  29             'duration': 289.04,
  30             'view_count': int,
  31             'filesize': int,
  32         }
  33     }, {
  34         'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/',
  35         'info_dict': {
  36             'id': '117049447',
  37             'ext': 'f4v',
  38             'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
  39             'thumbnail': 're:^https?://.*\.jpg$',
  40             'timestamp': 1349207518000,
  41             'description': 'md5:294612423894260f2dcd5c6c04fe248b',
  42             'duration': 5478.33,
  43             'view_count': int,
  44             'filesize': int,
  45         }
  46     }]
  47
  48     _PLAYER_URL = 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf'
  49
  50     # Translated from tudou/tools/TVCHelper.as in PortalPlayer_193.swf
  51     # 0001, 0002 and 4001 are not included as they indicate temporary issues
  52     TVC_ERRORS = {
  53         '0003': 'The video is deleted or does not exist',
  54         '1001': 'This video is unavailable due to licensing issues',
  55         '1002': 'This video is unavailable as it\'s under review',
  56         '1003': 'This video is unavailable as it\'s under review',
  57         '3001': 'Password required',
  58         '5001': 'This video is available in Mainland China only due to licensing issues',
  59         '7001': 'This video is unavailable',
  60         '8001': 'This video is unavailable due to licensing issues',
  61     }
  62
  63     def _url_for_id(self, video_id, quality=None):
  64         info_url = 'http://v2.tudou.com/f?id=' + compat_str(video_id)
  65         if quality:
  66             info_url += '&hd' + quality
  67         xml_data = self._download_xml(info_url, video_id, 'Opening the info XML page')
  68         error = xml_data.attrib.get('error')
  69         if error is not None:
  70             raise ExtractorError('Tudou said: %s' % error, expected=True)
  71         final_url = xml_data.text
  72         return final_url
  73
  74     def _real_extract(self, url):
  75         video_id = self._match_id(url)
  76         item_data = self._download_json(
  77             'http://www.tudou.com/tvp/getItemInfo.action?ic=%s' % video_id, video_id)
  78
  79         youku_vcode = item_data.get('vcode')
  80         if youku_vcode:
  81             return self.url_result('youku:' + youku_vcode, ie='Youku')
  82
  83         if not item_data.get('itemSegs'):
  84             tvc_code = item_data.get('tvcCode')
  85             if tvc_code:
  86                 err_msg = self.TVC_ERRORS.get(tvc_code)
  87                 if err_msg:
  88                     raise ExtractorError('Tudou said: %s' % err_msg, expected=True)
  89                 raise ExtractorError('Unexpected error %s returned from Tudou' % tvc_code)
  90             raise ExtractorError('Unxpected error returned from Tudou')
  91
  92         title = unescapeHTML(item_data['kw'])
  93         description = item_data.get('desc')
  94         thumbnail_url = item_data.get('pic')
  95         view_count = int_or_none(item_data.get('playTimes'))
  96         timestamp = int_or_none(item_data.get('pt'))
  97
  98         segments = self._parse_json(item_data['itemSegs'], video_id)
  99         # It looks like the keys are the arguments that have to be passed as
 100         # the hd field in the request url, we pick the higher
 101         # Also, filter non-number qualities (see issue #3643).
 102         quality = sorted(filter(lambda k: k.isdigit(), segments.keys()),
 103                          key=lambda k: int(k))[-1]
 104         parts = segments[quality]
 105         len_parts = len(parts)
 106         if len_parts > 1:
 107             self.to_screen('%s: found %s parts' % (video_id, len_parts))
 108
 109         def part_func(partnum):
 110             part = parts[partnum]
 111             part_id = part['k']
 112             final_url = self._url_for_id(part_id, quality)
 113             ext = (final_url.split('?')[0]).split('.')[-1]
 114             return [{
 115                 'id': '%s' % part_id,
 116                 'url': final_url,
 117                 'ext': ext,
 118                 'title': title,
 119                 'thumbnail': thumbnail_url,
 120                 'description': description,
 121                 'view_count': view_count,
 122                 'timestamp': timestamp,
 123                 'duration': float_or_none(part.get('seconds'), 1000),
 124                 'filesize': int_or_none(part.get('size')),
 125                 'http_headers': {
 126                     'Referer': self._PLAYER_URL,
 127                 },
 128             }]
 129
 130         entries = InAdvancePagedList(part_func, len_parts, 1)
 131
 132         return {
 133             '_type': 'multi_video',
 134             'entries': entries,
 135             'id': video_id,
 136             'title': title,
 137         }
 138
 139
 140 class TudouPlaylistIE(InfoExtractor):
 141     IE_NAME = 'tudou:playlist'
 142     _VALID_URL = r'https?://(?:www\.)?tudou\.com/listplay/(?P<id>[\w-]{11})\.html'
 143     _TESTS = [{
 144         'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo.html',
 145         'info_dict': {
 146             'id': 'zzdE77v6Mmo',
 147         },
 148         'playlist_mincount': 209,
 149     }]
 150
 151     def _real_extract(self, url):
 152         playlist_id = self._match_id(url)
 153         playlist_data = self._download_json(
 154             'http://www.tudou.com/tvp/plist.action?lcode=%s' % playlist_id, playlist_id)
 155         entries = [self.url_result(
 156             'http://www.tudou.com/programs/view/%s' % item['icode'],
 157             'Tudou', item['icode'],
 158             item['kw']) for item in playlist_data['items']]
 159         return self.playlist_result(entries, playlist_id)
 160
 161
 162 class TudouAlbumIE(InfoExtractor):
 163     IE_NAME = 'tudou:album'
 164     _VALID_URL = r'https?://(?:www\.)?tudou\.com/album(?:cover|play)/(?P<id>[\w-]{11})'
 165     _TESTS = [{
 166         'url': 'http://www.tudou.com/albumplay/v5qckFJvNJg.html',
 167         'info_dict': {
 168             'id': 'v5qckFJvNJg',
 169         },
 170         'playlist_mincount': 45,
 171     }]
 172
 173     def _real_extract(self, url):
 174         album_id = self._match_id(url)
 175         album_data = self._download_json(
 176             'http://www.tudou.com/tvp/alist.action?acode=%s' % album_id, album_id)
 177         entries = [self.url_result(
 178             'http://www.tudou.com/programs/view/%s' % item['icode'],
 179             'Tudou', item['icode'],
 180             item['kw']) for item in album_data['items']]
 181         return self.playlist_result(entries, album_id)