yt_dlp/extractor/filmon.py

   1 from .common import InfoExtractor
   2 from ..compat import (
   3     compat_str,
   4     compat_HTTPError,
   5 )
   6 from ..utils import (
   7     qualities,
   8     strip_or_none,
   9     int_or_none,
  10     ExtractorError,
  11 )
  12
  13
  14 class FilmOnIE(InfoExtractor):
  15     IE_NAME = 'filmon'
  16     _VALID_URL = r'(?:https?://(?:www\.)?filmon\.com/vod/view/|filmon:)(?P<id>\d+)'
  17     _TESTS = [{
  18         'url': 'https://www.filmon.com/vod/view/24869-0-plan-9-from-outer-space',
  19         'info_dict': {
  20             'id': '24869',
  21             'ext': 'mp4',
  22             'title': 'Plan 9 From Outer Space',
  23             'description': 'Dead human, zombies and vampires',
  24         },
  25     }, {
  26         'url': 'https://www.filmon.com/vod/view/2825-1-popeye-series-1',
  27         'info_dict': {
  28             'id': '2825',
  29             'title': 'Popeye Series 1',
  30             'description': 'The original series of Popeye.',
  31         },
  32         'playlist_mincount': 8,
  33     }]
  34
  35     def _real_extract(self, url):
  36         video_id = self._match_id(url)
  37
  38         try:
  39             response = self._download_json(
  40                 'https://www.filmon.com/api/vod/movie?id=%s' % video_id,
  41                 video_id)['response']
  42         except ExtractorError as e:
  43             if isinstance(e.cause, compat_HTTPError):
  44                 errmsg = self._parse_json(e.cause.read().decode(), video_id)['reason']
  45                 raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
  46             raise
  47
  48         title = response['title']
  49         description = strip_or_none(response.get('description'))
  50
  51         if response.get('type_id') == 1:
  52             entries = [self.url_result('filmon:' + episode_id) for episode_id in response.get('episodes', [])]
  53             return self.playlist_result(entries, video_id, title, description)
  54
  55         QUALITY = qualities(('low', 'high'))
  56         formats = []
  57         for format_id, stream in response.get('streams', {}).items():
  58             stream_url = stream.get('url')
  59             if not stream_url:
  60                 continue
  61             formats.append({
  62                 'format_id': format_id,
  63                 'url': stream_url,
  64                 'ext': 'mp4',
  65                 'quality': QUALITY(stream.get('quality')),
  66                 'protocol': 'm3u8_native',
  67             })
  68         self._sort_formats(formats)
  69
  70         thumbnails = []
  71         poster = response.get('poster', {})
  72         thumbs = poster.get('thumbs', {})
  73         thumbs['poster'] = poster
  74         for thumb_id, thumb in thumbs.items():
  75             thumb_url = thumb.get('url')
  76             if not thumb_url:
  77                 continue
  78             thumbnails.append({
  79                 'id': thumb_id,
  80                 'url': thumb_url,
  81                 'width': int_or_none(thumb.get('width')),
  82                 'height': int_or_none(thumb.get('height')),
  83             })
  84
  85         return {
  86             'id': video_id,
  87             'title': title,
  88             'formats': formats,
  89             'description': description,
  90             'thumbnails': thumbnails,
  91         }
  92
  93
  94 class FilmOnChannelIE(InfoExtractor):
  95     IE_NAME = 'filmon:channel'
  96     _VALID_URL = r'https?://(?:www\.)?filmon\.com/(?:tv|channel)/(?P<id>[a-z0-9-]+)'
  97     _TESTS = [{
  98         # VOD
  99         'url': 'http://www.filmon.com/tv/sports-haters',
 100         'info_dict': {
 101             'id': '4190',
 102             'ext': 'mp4',
 103             'title': 'Sports Haters',
 104             'description': 'md5:dabcb4c1d9cfc77085612f1a85f8275d',
 105         },
 106     }, {
 107         # LIVE
 108         'url': 'https://www.filmon.com/channel/filmon-sports',
 109         'only_matching': True,
 110     }, {
 111         'url': 'https://www.filmon.com/tv/2894',
 112         'only_matching': True,
 113     }]
 114
 115     _THUMBNAIL_RES = [
 116         ('logo', 56, 28),
 117         ('big_logo', 106, 106),
 118         ('extra_big_logo', 300, 300),
 119     ]
 120
 121     def _real_extract(self, url):
 122         channel_id = self._match_id(url)
 123
 124         try:
 125             channel_data = self._download_json(
 126                 'http://www.filmon.com/api-v2/channel/' + channel_id, channel_id)['data']
 127         except ExtractorError as e:
 128             if isinstance(e.cause, compat_HTTPError):
 129                 errmsg = self._parse_json(e.cause.read().decode(), channel_id)['message']
 130                 raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True)
 131             raise
 132
 133         channel_id = compat_str(channel_data['id'])
 134         is_live = not channel_data.get('is_vod') and not channel_data.get('is_vox')
 135         title = channel_data['title']
 136
 137         QUALITY = qualities(('low', 'high'))
 138         formats = []
 139         for stream in channel_data.get('streams', []):
 140             stream_url = stream.get('url')
 141             if not stream_url:
 142                 continue
 143             if not is_live:
 144                 formats.extend(self._extract_wowza_formats(
 145                     stream_url, channel_id, skip_protocols=['dash', 'rtmp', 'rtsp']))
 146                 continue
 147             quality = stream.get('quality')
 148             formats.append({
 149                 'format_id': quality,
 150                 # this is an m3u8 stream, but we are deliberately not using _extract_m3u8_formats
 151                 # because it doesn't have bitrate variants anyway
 152                 'url': stream_url,
 153                 'ext': 'mp4',
 154                 'quality': QUALITY(quality),
 155             })
 156         self._sort_formats(formats)
 157
 158         thumbnails = []
 159         for name, width, height in self._THUMBNAIL_RES:
 160             thumbnails.append({
 161                 'id': name,
 162                 'url': 'http://static.filmon.com/assets/channels/%s/%s.png' % (channel_id, name),
 163                 'width': width,
 164                 'height': height,
 165             })
 166
 167         return {
 168             'id': channel_id,
 169             'display_id': channel_data.get('alias'),
 170             'title': title,
 171             'description': channel_data.get('description'),
 172             'thumbnails': thumbnails,
 173             'formats': formats,
 174             'is_live': is_live,
 175         }