Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/bbccouk.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .subtitles import SubtitlesInfoExtractor
   6 from ..utils import ExtractorError
   7
   8
   9 class BBCCoUkIE(SubtitlesInfoExtractor):
  10     IE_NAME = 'bbc.co.uk'
  11     IE_DESC = 'BBC iPlayer'
  12     _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:programmes|iplayer/episode)/(?P<id>[\da-z]{8})'
  13
  14     _TESTS = [
  15         {
  16             'url': 'http://www.bbc.co.uk/programmes/p01q7wz1',
  17             'info_dict': {
  18                 'id': 'p01q7wz4',
  19                 'ext': 'flv',
  20                 'title': 'Friction: Blu Mar Ten guest mix: Blu Mar Ten - Guest Mix',
  21                 'description': 'Blu Mar Ten deliver a Guest Mix for Friction.',
  22                 'duration': 1936,
  23             },
  24             'params': {
  25                 # rtmp download
  26                 'skip_download': True,
  27             }
  28         },
  29         {
  30             'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
  31             'info_dict': {
  32                 'id': 'b00yng1d',
  33                 'ext': 'flv',
  34                 'title': 'The Man in Black: Series 3: The Printed Name',
  35                 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
  36                 'duration': 1800,
  37             },
  38             'params': {
  39                 # rtmp download
  40                 'skip_download': True,
  41             }
  42         },
  43         {
  44             'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
  45             'info_dict': {
  46                 'id': 'b00yng1d',
  47                 'ext': 'flv',
  48                 'title': 'The Voice UK: Series 3: Blind Auditions 5',
  49                 'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.",
  50                 'duration': 5100,
  51             },
  52             'params': {
  53                 # rtmp download
  54                 'skip_download': True,
  55             },
  56             'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
  57         }
  58     ]
  59
  60     def _extract_asx_playlist(self, connection, programme_id):
  61         asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
  62         return [ref.get('href') for ref in asx.findall('./Entry/ref')]
  63
  64     def _extract_connection(self, connection, programme_id):
  65         formats = []
  66         protocol = connection.get('protocol')
  67         supplier = connection.get('supplier')
  68         if protocol == 'http':
  69             href = connection.get('href')
  70             # ASX playlist
  71             if supplier == 'asx':
  72                 for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
  73                     formats.append({
  74                         'url': ref,
  75                         'format_id': 'ref%s_%s' % (i, supplier),
  76                     })
  77             # Direct link
  78             else:
  79                 formats.append({
  80                     'url': href,
  81                     'format_id': supplier,
  82                 })
  83         elif protocol == 'rtmp':
  84             application = connection.get('application', 'ondemand')
  85             auth_string = connection.get('authString')
  86             identifier = connection.get('identifier')
  87             server = connection.get('server')
  88             formats.append({
  89                 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
  90                 'play_path': identifier,
  91                 'app': '%s?%s' % (application, auth_string),
  92                 'page_url': 'http://www.bbc.co.uk',
  93                 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
  94                 'rtmp_live': False,
  95                 'ext': 'flv',
  96                 'format_id': supplier,
  97             })
  98         return formats
  99
 100     def _extract_items(self, playlist):
 101         return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
 102
 103     def _extract_medias(self, media_selection):
 104         return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
 105
 106     def _extract_connections(self, media):
 107         return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
 108
 109     def _extract_video(self, media, programme_id):
 110         formats = []
 111         vbr = int(media.get('bitrate'))
 112         vcodec = media.get('encoding')
 113         service = media.get('service')
 114         width = int(media.get('width'))
 115         height = int(media.get('height'))
 116         file_size = int(media.get('media_file_size'))
 117         for connection in self._extract_connections(media):
 118             conn_formats = self._extract_connection(connection, programme_id)
 119             for format in conn_formats:
 120                 format.update({
 121                     'format_id': '%s_%s' % (service, format['format_id']),
 122                     'width': width,
 123                     'height': height,
 124                     'vbr': vbr,
 125                     'vcodec': vcodec,
 126                     'filesize': file_size,
 127                 })
 128             formats.extend(conn_formats)
 129         return formats
 130
 131     def _extract_audio(self, media, programme_id):
 132         formats = []
 133         abr = int(media.get('bitrate'))
 134         acodec = media.get('encoding')
 135         service = media.get('service')
 136         for connection in self._extract_connections(media):
 137             conn_formats = self._extract_connection(connection, programme_id)
 138             for format in conn_formats:
 139                 format.update({
 140                     'format_id': '%s_%s' % (service, format['format_id']),
 141                     'abr': abr,
 142                     'acodec': acodec,
 143                 })
 144             formats.extend(conn_formats)
 145         return formats
 146
 147     def _extract_captions(self, media, programme_id):
 148         subtitles = {}
 149         for connection in self._extract_connections(media):
 150             captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
 151             lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
 152             ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}'))
 153             srt = ''
 154             for pos, p in enumerate(ps):
 155                 srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'),
 156                                                           p.text.strip() if p.text is not None else '')
 157             subtitles[lang] = srt
 158         return subtitles
 159
 160     def _real_extract(self, url):
 161         mobj = re.match(self._VALID_URL, url)
 162         group_id = mobj.group('id')
 163
 164         playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id,
 165             'Downloading playlist XML')
 166
 167         no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
 168         if no_items is not None:
 169             reason = no_items.get('reason')
 170             if reason == 'preAvailability':
 171                 msg = 'Episode %s is not yet available' % group_id
 172             elif reason == 'postAvailability':
 173                 msg = 'Episode %s is no longer available' % group_id
 174             else:
 175                 msg = 'Episode %s is not available: %s' % (group_id, reason)
 176             raise ExtractorError(msg, expected=True)
 177
 178         formats = []
 179         subtitles = None
 180
 181         for item in self._extract_items(playlist):
 182             kind = item.get('kind')
 183             if kind != 'programme' and kind != 'radioProgramme':
 184                 continue
 185             title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
 186             description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
 187
 188             programme_id = item.get('identifier')
 189             duration = int(item.get('duration'))
 190
 191             media_selection = self._download_xml(
 192                 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'  % programme_id,
 193                 programme_id, 'Downloading media selection XML')
 194
 195             for media in self._extract_medias(media_selection):
 196                 kind = media.get('kind')
 197                 if kind == 'audio':
 198                     formats.extend(self._extract_audio(media, programme_id))
 199                 elif kind == 'video':
 200                     formats.extend(self._extract_video(media, programme_id))
 201                 elif kind == 'captions':
 202                     subtitles = self._extract_captions(media, programme_id)
 203
 204         if self._downloader.params.get('listsubtitles', False):
 205             self._list_available_subtitles(programme_id, subtitles)
 206             return
 207
 208         self._sort_formats(formats)
 209
 210         return {
 211             'id': programme_id,
 212             'title': title,
 213             'description': description,
 214             'duration': duration,
 215             'formats': formats,
 216             'subtitles': subtitles,
 217         }