yt_dlp/extractor/eitb.py

   1 from .common import InfoExtractor
   2 from ..networking import Request
   3 from ..utils import float_or_none, int_or_none, parse_iso8601
   4
   5
   6 class EitbIE(InfoExtractor):
   7     IE_NAME = 'eitb.tv'
   8     _VALID_URL = r'https?://(?:www\.)?eitb\.tv/(?:eu/bideoa|es/video)/[^/]+/\d+/(?P<id>\d+)'
   9
  10     _TEST = {
  11         'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/4104995148001/4090227752001/lasa-y-zabala-30-anos/',
  12         'md5': 'edf4436247185adee3ea18ce64c47998',
  13         'info_dict': {
  14             'id': '4090227752001',
  15             'ext': 'mp4',
  16             'title': '60 minutos (Lasa y Zabala, 30 años)',
  17             'description': 'Programa de reportajes de actualidad.',
  18             'duration': 3996.76,
  19             'timestamp': 1381789200,
  20             'upload_date': '20131014',
  21             'tags': list,
  22         },
  23     }
  24
  25     def _real_extract(self, url):
  26         video_id = self._match_id(url)
  27
  28         video = self._download_json(
  29             f'http://mam.eitb.eus/mam/REST/ServiceMultiweb/Video/MULTIWEBTV/{video_id}/',
  30             video_id, 'Downloading video JSON')
  31
  32         media = video['web_media'][0]
  33
  34         formats = []
  35         for rendition in media['RENDITIONS']:
  36             video_url = rendition.get('PMD_URL')
  37             if not video_url:
  38                 continue
  39             tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000)
  40             format_id = 'http'
  41             if tbr:
  42                 format_id += f'-{int(tbr)}'
  43             formats.append({
  44                 'url': rendition['PMD_URL'],
  45                 'format_id': format_id,
  46                 'width': int_or_none(rendition.get('FRAME_WIDTH')),
  47                 'height': int_or_none(rendition.get('FRAME_HEIGHT')),
  48                 'tbr': tbr,
  49             })
  50
  51         hls_url = media.get('HLS_SURL')
  52         if hls_url:
  53             request = Request(
  54                 'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/',
  55                 headers={'Referer': url})
  56             token_data = self._download_json(
  57                 request, video_id, 'Downloading auth token', fatal=False)
  58             if token_data:
  59                 token = token_data.get('token')
  60                 if token:
  61                     formats.extend(self._extract_m3u8_formats(
  62                         f'{hls_url}?hdnts={token}', video_id, m3u8_id='hls', fatal=False))
  63
  64         hds_url = media.get('HDS_SURL')
  65         if hds_url:
  66             formats.extend(self._extract_f4m_formats(
  67                 '{}?hdcore=3.7.0'.format(hds_url.replace('euskalsvod', 'euskalvod')),
  68                 video_id, f4m_id='hds', fatal=False))
  69
  70         return {
  71             'id': video_id,
  72             'title': media.get('NAME_ES') or media.get('name') or media['NAME_EU'],
  73             'description': media.get('SHORT_DESC_ES') or video.get('desc_group') or media.get('SHORT_DESC_EU'),
  74             'thumbnail': media.get('STILL_URL') or media.get('THUMBNAIL_URL'),
  75             'duration': float_or_none(media.get('LENGTH'), 1000),
  76             'timestamp': parse_iso8601(media.get('BROADCST_DATE'), ' '),
  77             'tags': media.get('TAGS'),
  78             'formats': formats,
  79         }