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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     ExtractorError,
   7     int_or_none,
   8     float_or_none,
   9     mimetype2ext,
  10     parse_iso8601,
  11     remove_end,
  12     update_url_query,
  13 )
  14
  15
  16 class DRTVIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
  18     _GEO_BYPASS = False
  19     _GEO_COUNTRIES = ['DK']
  20     IE_NAME = 'drtv'
  21     _TESTS = [{
  22         'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
  23         'md5': '7ae17b4e18eb5d29212f424a7511c184',
  24         'info_dict': {
  25             'id': 'klassen-darlig-taber-10',
  26             'ext': 'mp4',
  27             'title': 'Klassen - Dårlig taber (10)',
  28             'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
  29             'timestamp': 1471991907,
  30             'upload_date': '20160823',
  31             'duration': 606.84,
  32         },
  33     }, {
  34         # embed
  35         'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
  36         'info_dict': {
  37             'id': 'christiania-pusher-street-ryddes-drdkrjpo',
  38             'ext': 'mp4',
  39             'title': 'LIVE Christianias rydning af Pusher Street er i gang',
  40             'description': 'md5:2a71898b15057e9b97334f61d04e6eb5',
  41             'timestamp': 1472800279,
  42             'upload_date': '20160902',
  43             'duration': 131.4,
  44         },
  45         'params': {
  46             'skip_download': True,
  47         },
  48     }, {
  49         # with SignLanguage formats
  50         'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
  51         'info_dict': {
  52             'id': 'historien-om-danmark-stenalder',
  53             'ext': 'mp4',
  54             'title': 'Historien om Danmark: Stenalder (1)',
  55             'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
  56             'timestamp': 1490401996,
  57             'upload_date': '20170325',
  58             'duration': 3502.04,
  59             'formats': 'mincount:20',
  60         },
  61         'params': {
  62             'skip_download': True,
  63         },
  64     }]
  65
  66     def _real_extract(self, url):
  67         video_id = self._match_id(url)
  68
  69         webpage = self._download_webpage(url, video_id)
  70
  71         if '>Programmet er ikke længere tilgængeligt' in webpage:
  72             raise ExtractorError(
  73                 'Video %s is not available' % video_id, expected=True)
  74
  75         video_id = self._search_regex(
  76             (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
  77                 r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
  78             webpage, 'video id')
  79
  80         programcard = self._download_json(
  81             'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
  82             video_id, 'Downloading video JSON')
  83         data = programcard['Data'][0]
  84
  85         title = remove_end(self._og_search_title(
  86             webpage, default=None), ' | TV | DR') or data['Title']
  87         description = self._og_search_description(
  88             webpage, default=None) or data.get('Description')
  89
  90         timestamp = parse_iso8601(data.get('CreatedTime'))
  91
  92         thumbnail = None
  93         duration = None
  94
  95         restricted_to_denmark = False
  96
  97         formats = []
  98         subtitles = {}
  99
 100         for asset in data['Assets']:
 101             kind = asset.get('Kind')
 102             if kind == 'Image':
 103                 thumbnail = asset.get('Uri')
 104             elif kind in ('VideoResource', 'AudioResource'):
 105                 duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
 106                 restricted_to_denmark = asset.get('RestrictedToDenmark')
 107                 asset_target = asset.get('Target')
 108                 for link in asset.get('Links', []):
 109                     uri = link.get('Uri')
 110                     if not uri:
 111                         continue
 112                     target = link.get('Target')
 113                     format_id = target or ''
 114                     preference = None
 115                     if asset_target in ('SpokenSubtitles', 'SignLanguage'):
 116                         preference = -1
 117                         format_id += '-%s' % asset_target
 118                     if target == 'HDS':
 119                         f4m_formats = self._extract_f4m_formats(
 120                             uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
 121                             video_id, preference, f4m_id=format_id)
 122                         if kind == 'AudioResource':
 123                             for f in f4m_formats:
 124                                 f['vcodec'] = 'none'
 125                         formats.extend(f4m_formats)
 126                     elif target == 'HLS':
 127                         formats.extend(self._extract_m3u8_formats(
 128                             uri, video_id, 'mp4', entry_protocol='m3u8_native',
 129                             preference=preference, m3u8_id=format_id))
 130                     else:
 131                         bitrate = link.get('Bitrate')
 132                         if bitrate:
 133                             format_id += '-%s' % bitrate
 134                         formats.append({
 135                             'url': uri,
 136                             'format_id': format_id,
 137                             'tbr': int_or_none(bitrate),
 138                             'ext': link.get('FileFormat'),
 139                             'vcodec': 'none' if kind == 'AudioResource' else None,
 140                         })
 141                 subtitles_list = asset.get('SubtitlesList')
 142                 if isinstance(subtitles_list, list):
 143                     LANGS = {
 144                         'Danish': 'da',
 145                     }
 146                     for subs in subtitles_list:
 147                         if not subs.get('Uri'):
 148                             continue
 149                         lang = subs.get('Language') or 'da'
 150                         subtitles.setdefault(LANGS.get(lang, lang), []).append({
 151                             'url': subs['Uri'],
 152                             'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
 153                         })
 154
 155         if not formats and restricted_to_denmark:
 156             self.raise_geo_restricted(
 157                 'Unfortunately, DR is not allowed to show this program outside Denmark.',
 158                 countries=self._GEO_COUNTRIES)
 159
 160         self._sort_formats(formats)
 161
 162         return {
 163             'id': video_id,
 164             'title': title,
 165             'description': description,
 166             'thumbnail': thumbnail,
 167             'timestamp': timestamp,
 168             'duration': duration,
 169             'formats': formats,
 170             'subtitles': subtitles,
 171         }
 172
 173
 174 class DRTVLiveIE(InfoExtractor):
 175     IE_NAME = 'drtv:live'
 176     _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
 177     _GEO_COUNTRIES = ['DK']
 178     _TEST = {
 179         'url': 'https://www.dr.dk/tv/live/dr1',
 180         'info_dict': {
 181             'id': 'dr1',
 182             'ext': 'mp4',
 183             'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 184         },
 185         'params': {
 186             # m3u8 download
 187             'skip_download': True,
 188         },
 189     }
 190
 191     def _real_extract(self, url):
 192         channel_id = self._match_id(url)
 193         channel_data = self._download_json(
 194             'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id,
 195             channel_id)
 196         title = self._live_title(channel_data['Title'])
 197
 198         formats = []
 199         for streaming_server in channel_data.get('StreamingServers', []):
 200             server = streaming_server.get('Server')
 201             if not server:
 202                 continue
 203             link_type = streaming_server.get('LinkType')
 204             for quality in streaming_server.get('Qualities', []):
 205                 for stream in quality.get('Streams', []):
 206                     stream_path = stream.get('Stream')
 207                     if not stream_path:
 208                         continue
 209                     stream_url = update_url_query(
 210                         '%s/%s' % (server, stream_path), {'b': ''})
 211                     if link_type == 'HLS':
 212                         formats.extend(self._extract_m3u8_formats(
 213                             stream_url, channel_id, 'mp4',
 214                             m3u8_id=link_type, fatal=False, live=True))
 215                     elif link_type == 'HDS':
 216                         formats.extend(self._extract_f4m_formats(update_url_query(
 217                             '%s/%s' % (server, stream_path), {'hdcore': '3.7.0'}),
 218                             channel_id, f4m_id=link_type, fatal=False))
 219         self._sort_formats(formats)
 220
 221         return {
 222             'id': channel_id,
 223             'title': title,
 224             'thumbnail': channel_data.get('PrimaryImageUri'),
 225             'formats': formats,
 226             'is_live': True,
 227         }