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': '25e659cccc9a2ed956110a299fdf5983',
  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         'params': {
  34             'skip_download': True,
  35         },
  36     }, {
  37         'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
  38         'md5': '2c37175c718155930f939ef59952474a',
  39         'info_dict': {
  40             'id': 'christiania-pusher-street-ryddes-drdkrjpo',
  41             'ext': 'mp4',
  42             'title': 'LIVE Christianias rydning af Pusher Street er i gang',
  43             'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
  44             'timestamp': 1472800279,
  45             'upload_date': '20160902',
  46             'duration': 131.4,
  47         },
  48     }]
  49
  50     def _real_extract(self, url):
  51         video_id = self._match_id(url)
  52
  53         webpage = self._download_webpage(url, video_id)
  54
  55         if '>Programmet er ikke længere tilgængeligt' in webpage:
  56             raise ExtractorError(
  57                 'Video %s is not available' % video_id, expected=True)
  58
  59         video_id = self._search_regex(
  60             (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
  61                 r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
  62             webpage, 'video id')
  63
  64         programcard = self._download_json(
  65             'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
  66             video_id, 'Downloading video JSON')
  67         data = programcard['Data'][0]
  68
  69         title = remove_end(self._og_search_title(
  70             webpage, default=None), ' | TV | DR') or data['Title']
  71         description = self._og_search_description(
  72             webpage, default=None) or data.get('Description')
  73
  74         timestamp = parse_iso8601(data.get('CreatedTime'))
  75
  76         thumbnail = None
  77         duration = None
  78
  79         restricted_to_denmark = False
  80
  81         formats = []
  82         subtitles = {}
  83
  84         for asset in data['Assets']:
  85             kind = asset.get('Kind')
  86             if kind == 'Image':
  87                 thumbnail = asset.get('Uri')
  88             elif kind in ('VideoResource', 'AudioResource'):
  89                 duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
  90                 restricted_to_denmark = asset.get('RestrictedToDenmark')
  91                 spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
  92                 for link in asset.get('Links', []):
  93                     uri = link.get('Uri')
  94                     if not uri:
  95                         continue
  96                     target = link.get('Target')
  97                     format_id = target or ''
  98                     preference = None
  99                     if spoken_subtitles:
 100                         preference = -1
 101                         format_id += '-spoken-subtitles'
 102                     if target == 'HDS':
 103                         f4m_formats = self._extract_f4m_formats(
 104                             uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
 105                             video_id, preference, f4m_id=format_id)
 106                         if kind == 'AudioResource':
 107                             for f in f4m_formats:
 108                                 f['vcodec'] = 'none'
 109                         formats.extend(f4m_formats)
 110                     elif target == 'HLS':
 111                         formats.extend(self._extract_m3u8_formats(
 112                             uri, video_id, 'mp4', entry_protocol='m3u8_native',
 113                             preference=preference, m3u8_id=format_id))
 114                     else:
 115                         bitrate = link.get('Bitrate')
 116                         if bitrate:
 117                             format_id += '-%s' % bitrate
 118                         formats.append({
 119                             'url': uri,
 120                             'format_id': format_id,
 121                             'tbr': int_or_none(bitrate),
 122                             'ext': link.get('FileFormat'),
 123                             'vcodec': 'none' if kind == 'AudioResource' else None,
 124                         })
 125                 subtitles_list = asset.get('SubtitlesList')
 126                 if isinstance(subtitles_list, list):
 127                     LANGS = {
 128                         'Danish': 'da',
 129                     }
 130                     for subs in subtitles_list:
 131                         if not subs.get('Uri'):
 132                             continue
 133                         lang = subs.get('Language') or 'da'
 134                         subtitles.setdefault(LANGS.get(lang, lang), []).append({
 135                             'url': subs['Uri'],
 136                             'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
 137                         })
 138
 139         if not formats and restricted_to_denmark:
 140             self.raise_geo_restricted(
 141                 'Unfortunately, DR is not allowed to show this program outside Denmark.',
 142                 countries=self._GEO_COUNTRIES)
 143
 144         self._sort_formats(formats)
 145
 146         return {
 147             'id': video_id,
 148             'title': title,
 149             'description': description,
 150             'thumbnail': thumbnail,
 151             'timestamp': timestamp,
 152             'duration': duration,
 153             'formats': formats,
 154             'subtitles': subtitles,
 155         }
 156
 157
 158 class DRTVLiveIE(InfoExtractor):
 159     IE_NAME = 'drtv:live'
 160     _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
 161     _GEO_COUNTRIES = ['DK']
 162     _TEST = {
 163         'url': 'https://www.dr.dk/tv/live/dr1',
 164         'info_dict': {
 165             'id': 'dr1',
 166             'ext': 'mp4',
 167             'title': 're:^DR1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 168         },
 169         'params': {
 170             # m3u8 download
 171             'skip_download': True,
 172         },
 173     }
 174
 175     def _real_extract(self, url):
 176         channel_id = self._match_id(url)
 177         channel_data = self._download_json(
 178             'https://www.dr.dk/mu-online/api/1.0/channel/' + channel_id,
 179             channel_id)
 180         title = self._live_title(channel_data['Title'])
 181
 182         formats = []
 183         for streaming_server in channel_data.get('StreamingServers', []):
 184             server = streaming_server.get('Server')
 185             if not server:
 186                 continue
 187             link_type = streaming_server.get('LinkType')
 188             for quality in streaming_server.get('Qualities', []):
 189                 for stream in quality.get('Streams', []):
 190                     stream_path = stream.get('Stream')
 191                     if not stream_path:
 192                         continue
 193                     stream_url = update_url_query(
 194                         '%s/%s' % (server, stream_path), {'b': ''})
 195                     if link_type == 'HLS':
 196                         formats.extend(self._extract_m3u8_formats(
 197                             stream_url, channel_id, 'mp4',
 198                             m3u8_id=link_type, fatal=False, live=True))
 199                     elif link_type == 'HDS':
 200                         formats.extend(self._extract_f4m_formats(update_url_query(
 201                             '%s/%s' % (server, stream_path), {'hdcore': '3.7.0'}),
 202                             channel_id, f4m_id=link_type, fatal=False))
 203         self._sort_formats(formats)
 204
 205         return {
 206             'id': channel_id,
 207             'title': title,
 208             'thumbnail': channel_data.get('PrimaryImageUri'),
 209             'formats': formats,
 210             'is_live': True,
 211         }