yt_dlp/extractor/indavideo.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     int_or_none,
   5     parse_age_limit,
   6     parse_iso8601,
   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     #   http://indavideo.hu/video/Vicces_cica_1
  15     #   http://index.indavideo.hu/video/2015_0728_beregszasz
  16     #   http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
  17     #   http://erotika.indavideo.hu/video/Amator_tini_punci
  18     #   http://film.indavideo.hu/video/f_hrom_nagymamm_volt
  19     #   http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes
  20     _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//embed\.indavideo\.hu/player/video/[\da-f]+)']
  21     _TESTS = [{
  22         'url': 'http://indavideo.hu/player/video/1bdc3c6d80/',
  23         'md5': 'c8a507a1c7410685f83a06eaeeaafeab',
  24         'info_dict': {
  25             'id': '1837039',
  26             'ext': 'mp4',
  27             'title': 'Cicatánc',
  28             'description': '',
  29             'thumbnail': r're:^https?://.*\.jpg$',
  30             'uploader': 'cukiajanlo',
  31             'uploader_id': '83729',
  32             'timestamp': 1439193826,
  33             'upload_date': '20150810',
  34             'duration': 72,
  35             'age_limit': 0,
  36             'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom'],
  37         },
  38     }, {
  39         'url': 'http://embed.indavideo.hu/player/video/1bdc3c6d80?autostart=1&hide=1',
  40         'only_matching': True,
  41     }, {
  42         'url': 'http://assets.indavideo.hu/swf/player.swf?v=fe25e500&vID=1bdc3c6d80&autostart=1&hide=1&i=1',
  43         'only_matching': True,
  44     }]
  45
  46     def _real_extract(self, url):
  47         video_id = self._match_id(url)
  48
  49         video = self._download_json(
  50             'https://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id,
  51             video_id)['data']
  52
  53         title = video['title']
  54
  55         video_urls = []
  56
  57         video_files = video.get('video_files')
  58         if isinstance(video_files, list):
  59             video_urls.extend(video_files)
  60         elif isinstance(video_files, dict):
  61             video_urls.extend(video_files.values())
  62
  63         video_file = video.get('video_file')
  64         if video:
  65             video_urls.append(video_file)
  66         video_urls = list(set(video_urls))
  67
  68         video_prefix = video_urls[0].rsplit('/', 1)[0]
  69
  70         for flv_file in video.get('flv_files', []):
  71             flv_url = '%s/%s' % (video_prefix, flv_file)
  72             if flv_url not in video_urls:
  73                 video_urls.append(flv_url)
  74
  75         filesh = video.get('filesh')
  76
  77         formats = []
  78         for video_url in video_urls:
  79             height = int_or_none(self._search_regex(
  80                 r'\.(\d{3,4})\.mp4(?:\?|$)', video_url, 'height', default=None))
  81             if filesh:
  82                 if not height:
  83                     continue
  84                 token = filesh.get(compat_str(height))
  85                 if token is None:
  86                     continue
  87                 video_url = update_url_query(video_url, {'token': token})
  88             formats.append({
  89                 'url': video_url,
  90                 'height': height,
  91             })
  92         self._sort_formats(formats)
  93
  94         timestamp = video.get('date')
  95         if timestamp:
  96             # upload date is in CEST
  97             timestamp = parse_iso8601(timestamp + ' +0200', ' ')
  98
  99         thumbnails = [{
 100             'url': self._proto_relative_url(thumbnail)
 101         } for thumbnail in video.get('thumbnails', [])]
 102
 103         tags = [tag['title'] for tag in video.get('tags') or []]
 104
 105         return {
 106             'id': video.get('id') or video_id,
 107             'title': title,
 108             'description': video.get('description'),
 109             'thumbnails': thumbnails,
 110             'uploader': video.get('user_name'),
 111             'uploader_id': video.get('user_id'),
 112             'timestamp': timestamp,
 113             'duration': int_or_none(video.get('length')),
 114             'age_limit': parse_age_limit(video.get('age_limit')),
 115             'tags': tags,
 116             'formats': formats,
 117         }