yt_dlp/extractor/indavideo.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     parse_age_limit,
   5     parse_iso8601,
   6     time_seconds,
   7     update_url_query,
   8 )
   9
  10
  11 class IndavideoEmbedIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
  13     # Some example URLs covered by generic extractor:
  14     #   https://indavideo.hu/video/Vicces_cica_1
  15     #   https://index.indavideo.hu/video/Hod_Nemetorszagban
  16     #   https://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
  17     #   https://film.indavideo.hu/video/f_farkaslesen
  18     #   https://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes
  19     _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)//embed\.indavideo\.hu/player/video/[\da-f]+)']
  20     _TESTS = [{
  21         'url': 'https://indavideo.hu/player/video/1bdc3c6d80/',
  22         'md5': 'c8a507a1c7410685f83a06eaeeaafeab',
  23         'info_dict': {
  24             'id': '1837039',
  25             'ext': 'mp4',
  26             'title': 'Cicatánc',
  27             'description': '',
  28             'thumbnail': r're:^https?://.*\.jpg$',
  29             'uploader': 'cukiajanlo',
  30             'uploader_id': '83729',
  31             'timestamp': 1439193826,
  32             'upload_date': '20150810',
  33             'duration': 72,
  34             'age_limit': 0,
  35             'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom'],
  36         },
  37     }, {
  38         'url': 'https://embed.indavideo.hu/player/video/1bdc3c6d80?autostart=1&hide=1',
  39         'only_matching': True,
  40     }]
  41     _WEBPAGE_TESTS = [{
  42         'url': 'https://indavideo.hu/video/Vicces_cica_1',
  43         'info_dict': {
  44             'id': '1335611',
  45             'ext': 'mp4',
  46             'title': 'Vicces cica',
  47             'description': 'Játszik a tablettel. :D',
  48             'thumbnail': r're:^https?://.*\.jpg$',
  49             'uploader': 'Jet_Pack',
  50             'uploader_id': '491217',
  51             'timestamp': 1390821212,
  52             'upload_date': '20140127',
  53             'duration': 7,
  54             'age_limit': 0,
  55             'tags': ['cica', 'Jet_Pack'],
  56         },
  57     }]
  58
  59     def _real_extract(self, url):
  60         video_id = self._match_id(url)
  61
  62         video = self._download_json(
  63             f'https://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/{video_id}/',
  64             video_id, query={'_': time_seconds()})['data']
  65
  66         video_urls = []
  67
  68         video_files = video.get('video_files')
  69         if isinstance(video_files, list):
  70             video_urls.extend(video_files)
  71         elif isinstance(video_files, dict):
  72             video_urls.extend(video_files.values())
  73
  74         video_urls = list(set(video_urls))
  75
  76         filesh = video.get('filesh') or {}
  77
  78         formats = []
  79         for video_url in video_urls:
  80             height = int_or_none(self._search_regex(
  81                 r'\.(\d{3,4})\.mp4(?:\?|$)', video_url, 'height', default=None))
  82             if not height and len(filesh) == 1:
  83                 height = int_or_none(next(iter(filesh.keys())))
  84             token = filesh.get(str(height))
  85             if token is None:
  86                 continue
  87             formats.append({
  88                 'url': update_url_query(video_url, {'token': token}),
  89                 'height': height,
  90             })
  91
  92         timestamp = video.get('date')
  93         if timestamp:
  94             # upload date is in CEST
  95             timestamp = parse_iso8601(timestamp + ' +0200', ' ')
  96
  97         thumbnails = [{
  98             'url': self._proto_relative_url(thumbnail),
  99         } for thumbnail in video.get('thumbnails', [])]
 100
 101         tags = [tag['title'] for tag in video.get('tags') or []]
 102
 103         return {
 104             'id': video.get('id') or video_id,
 105             'title': video.get('title'),
 106             'description': video.get('description'),
 107             'thumbnails': thumbnails,
 108             'uploader': video.get('user_name'),
 109             'uploader_id': video.get('user_id'),
 110             'timestamp': timestamp,
 111             'duration': int_or_none(video.get('length')),
 112             'age_limit': parse_age_limit(video.get('age_limit')),
 113             'tags': tags,
 114             'formats': formats,
 115         }