yt_dlp/extractor/indavideo.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     int_or_none,
   7     parse_age_limit,
   8     parse_iso8601,
   9     update_url_query,
  10 )
  11
  12
  13 class IndavideoEmbedIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
  15     _TESTS = [{
  16         'url': 'http://indavideo.hu/player/video/1bdc3c6d80/',
  17         'md5': 'c8a507a1c7410685f83a06eaeeaafeab',
  18         'info_dict': {
  19             'id': '1837039',
  20             'ext': 'mp4',
  21             'title': 'Cicatánc',
  22             'description': '',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24             'uploader': 'cukiajanlo',
  25             'uploader_id': '83729',
  26             'timestamp': 1439193826,
  27             'upload_date': '20150810',
  28             'duration': 72,
  29             'age_limit': 0,
  30             'tags': ['tánc', 'cica', 'cuki', 'cukiajanlo', 'newsroom'],
  31         },
  32     }, {
  33         'url': 'http://embed.indavideo.hu/player/video/1bdc3c6d80?autostart=1&hide=1',
  34         'only_matching': True,
  35     }, {
  36         'url': 'http://assets.indavideo.hu/swf/player.swf?v=fe25e500&vID=1bdc3c6d80&autostart=1&hide=1&i=1',
  37         'only_matching': True,
  38     }]
  39
  40     # Some example URLs covered by generic extractor:
  41     #   http://indavideo.hu/video/Vicces_cica_1
  42     #   http://index.indavideo.hu/video/2015_0728_beregszasz
  43     #   http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
  44     #   http://erotika.indavideo.hu/video/Amator_tini_punci
  45     #   http://film.indavideo.hu/video/f_hrom_nagymamm_volt
  46     #   http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes
  47
  48     @staticmethod
  49     def _extract_urls(webpage):
  50         return re.findall(
  51             r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//embed\.indavideo\.hu/player/video/[\da-f]+)',
  52             webpage)
  53
  54     def _real_extract(self, url):
  55         video_id = self._match_id(url)
  56
  57         video = self._download_json(
  58             'https://amfphp.indavideo.hu/SYm0json.php/player.playerHandler.getVideoData/%s' % video_id,
  59             video_id)['data']
  60
  61         title = video['title']
  62
  63         video_urls = []
  64
  65         video_files = video.get('video_files')
  66         if isinstance(video_files, list):
  67             video_urls.extend(video_files)
  68         elif isinstance(video_files, dict):
  69             video_urls.extend(video_files.values())
  70
  71         video_file = video.get('video_file')
  72         if video:
  73             video_urls.append(video_file)
  74         video_urls = list(set(video_urls))
  75
  76         video_prefix = video_urls[0].rsplit('/', 1)[0]
  77
  78         for flv_file in video.get('flv_files', []):
  79             flv_url = '%s/%s' % (video_prefix, flv_file)
  80             if flv_url not in video_urls:
  81                 video_urls.append(flv_url)
  82
  83         filesh = video.get('filesh')
  84
  85         formats = []
  86         for video_url in video_urls:
  87             height = int_or_none(self._search_regex(
  88                 r'\.(\d{3,4})\.mp4(?:\?|$)', video_url, 'height', default=None))
  89             if filesh:
  90                 if not height:
  91                     continue
  92                 token = filesh.get(compat_str(height))
  93                 if token is None:
  94                     continue
  95                 video_url = update_url_query(video_url, {'token': token})
  96             formats.append({
  97                 'url': video_url,
  98                 'height': height,
  99             })
 100         self._sort_formats(formats)
 101
 102         timestamp = video.get('date')
 103         if timestamp:
 104             # upload date is in CEST
 105             timestamp = parse_iso8601(timestamp + ' +0200', ' ')
 106
 107         thumbnails = [{
 108             'url': self._proto_relative_url(thumbnail)
 109         } for thumbnail in video.get('thumbnails', [])]
 110
 111         tags = [tag['title'] for tag in video.get('tags') or []]
 112
 113         return {
 114             'id': video.get('id') or video_id,
 115             'title': title,
 116             'description': video.get('description'),
 117             'thumbnails': thumbnails,
 118             'uploader': video.get('user_name'),
 119             'uploader_id': video.get('user_id'),
 120             'timestamp': timestamp,
 121             'duration': int_or_none(video.get('length')),
 122             'age_limit': parse_age_limit(video.get('age_limit')),
 123             'tags': tags,
 124             'formats': formats,
 125         }