Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/eitb.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     float_or_none,
   7     int_or_none,
   8     parse_iso8601,
   9     sanitized_Request,
  10 )
  11
  12
  13 class EitbIE(InfoExtractor):
  14     IE_NAME = 'eitb.tv'
  15     _VALID_URL = r'https?://(?:www\.)?eitb\.tv/(?:eu/bideoa|es/video)/[^/]+/\d+/(?P<id>\d+)'
  16
  17     _TEST = {
  18         'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/4104995148001/4090227752001/lasa-y-zabala-30-anos/',
  19         'md5': 'edf4436247185adee3ea18ce64c47998',
  20         'info_dict': {
  21             'id': '4090227752001',
  22             'ext': 'mp4',
  23             'title': '60 minutos (Lasa y Zabala, 30 años)',
  24             'description': 'Programa de reportajes de actualidad.',
  25             'duration': 3996.76,
  26             'timestamp': 1381789200,
  27             'upload_date': '20131014',
  28             'tags': list,
  29         },
  30     }
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34
  35         video = self._download_json(
  36             'http://mam.eitb.eus/mam/REST/ServiceMultiweb/Video/MULTIWEBTV/%s/' % video_id,
  37             video_id, 'Downloading video JSON')
  38
  39         media = video['web_media'][0]
  40
  41         formats = []
  42         for rendition in media['RENDITIONS']:
  43             video_url = rendition.get('PMD_URL')
  44             if not video_url:
  45                 continue
  46             tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000)
  47             format_id = 'http'
  48             if tbr:
  49                 format_id += '-%d' % int(tbr)
  50             formats.append({
  51                 'url': rendition['PMD_URL'],
  52                 'format_id': format_id,
  53                 'width': int_or_none(rendition.get('FRAME_WIDTH')),
  54                 'height': int_or_none(rendition.get('FRAME_HEIGHT')),
  55                 'tbr': tbr,
  56             })
  57
  58         hls_url = media.get('HLS_SURL')
  59         if hls_url:
  60             request = sanitized_Request(
  61                 'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/',
  62                 headers={'Referer': url})
  63             token_data = self._download_json(
  64                 request, video_id, 'Downloading auth token', fatal=False)
  65             if token_data:
  66                 token = token_data.get('token')
  67                 if token:
  68                     m3u8_formats = self._extract_m3u8_formats(
  69                         '%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False)
  70                     if m3u8_formats:
  71                         formats.extend(m3u8_formats)
  72
  73         hds_url = media.get('HDS_SURL')
  74         if hds_url:
  75             f4m_formats = self._extract_f4m_formats(
  76                 '%s?hdcore=3.7.0' % hds_url.replace('euskalsvod', 'euskalvod'),
  77                 video_id, f4m_id='hds', fatal=False)
  78             if f4m_formats:
  79                 formats.extend(f4m_formats)
  80
  81         self._sort_formats(formats)
  82
  83         return {
  84             'id': video_id,
  85             'title': media.get('NAME_ES') or media.get('name') or media['NAME_EU'],
  86             'description': media.get('SHORT_DESC_ES') or video.get('desc_group') or media.get('SHORT_DESC_EU'),
  87             'thumbnail': media.get('STILL_URL') or media.get('THUMBNAIL_URL'),
  88             'duration': float_or_none(media.get('LENGTH'), 1000),
  89             'timestamp': parse_iso8601(media.get('BROADCST_DATE'), ' '),
  90             'tags': media.get('TAGS'),
  91             'formats': formats,
  92         }