yt_dlp/extractor/vidly.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     mimetype2ext,
   5     url_or_none,
   6 )
   7 from ..utils.traversal import traverse_obj
   8
   9
  10 class VidlyIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:vid\.ly/|(?:s\.)?vid\.ly/embeded\.html\?(?:[^#]+&)?link=)(?P<id>\w+)'
  12     _EMBED_REGEX = [r'<script[^>]+\bsrc=[\'"](?P<url>(?:https?:)?//vid\.ly/\w+/embed[^\'"]+)',
  13                     r'<iframe[^>]+\bsrc=[\'"](?P<url>(?:https?:)?//(?:s\.)?vid\.ly/embeded\.html\?(?:[^#\'"]+&)?link=\w+[^\'"]+)']
  14     _TESTS = [{
  15         # JWPlayer 7, Embeds forbidden
  16         'url': 'https://vid.ly/2i3o9j/embed',
  17         'info_dict': {
  18             'id': '2i3o9j',
  19             'ext': 'mp4',
  20             'title': '2i3o9j',
  21             'thumbnail': r're:https://\w+\.cloudfront\.net/',
  22         },
  23     }, {
  24         # JWPlayer 6
  25         'url': 'http://s.vid.ly/embeded.html?link=jw_test&new=1&autoplay=true&controls=true',
  26         'info_dict': {
  27             'id': 'jw_test',
  28             'ext': 'mp4',
  29             'title': '2x8m8t',
  30             'thumbnail': r're:https://\w+\.cloudfront\.net/',
  31         },
  32     }, {
  33         # Vidlyplayer
  34         'url': 'https://vid.ly/7x0e6l',
  35         'info_dict': {
  36             'id': '7x0e6l',
  37             'ext': 'mp4',
  38             'title': '7x0e6l',
  39         },
  40     }]
  41     _WEBPAGE_TESTS = [{
  42         'url': 'https://www.petfinder.com/dog/gus-57378930/tn/ooltewah/furever-furkids-rescue-tn592/',
  43         'info_dict': {
  44             'id': 'w8p5b0',
  45             'ext': 'mp4',
  46             'title': 'w8p5b0',
  47             'thumbnail': r're:https://\w+\.cloudfront\.net/',
  48         },
  49     }]
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53
  54         embed_script = self._download_webpage(
  55             f'https://vid.ly/{video_id}/embed', video_id, headers={'Referer': 'https://vid.ly/'})
  56         player = self._search_json(r'initCallback\(', embed_script, 'player', video_id)
  57
  58         player_type = player.get('player') or ''
  59         if player_type.startswith('jwplayer'):
  60             return self._parse_jwplayer_data(player['config'], video_id)
  61         elif not player_type.startswith('vidly'):
  62             raise ExtractorError(f'Unknown player type {player_type!r}')
  63
  64         formats = []
  65         ext = mimetype2ext(traverse_obj(player, ('config', 'type')))
  66         for source, fid in [('source', 'sd'), ('source_hd', 'hd')]:
  67             if traverse_obj(player, ('config', source, {url_or_none})):
  68                 formats.append({
  69                     'url': player['config'][source],
  70                     'format_id': f'http-{fid}',
  71                     'ext': ext,
  72                 })
  73         # Has higher quality formats
  74         formats.extend(self._extract_m3u8_formats(
  75             f'https://d3fenhwk93s16g.cloudfront.net/{video_id}/hls.m3u8', video_id,
  76             fatal=False, note='Requesting higher quality m3u8 formats',
  77             errnote='No higher quality m3u8 formats found') or [])
  78
  79         return {
  80             'id': video_id,
  81             'title': video_id,
  82             'formats': formats,
  83         }