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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_parse_urlencode,
   9     compat_urlparse,
  10 )
  11 from ..utils import (
  12     get_element_by_attribute,
  13     int_or_none,
  14     remove_start,
  15     extract_attributes,
  16     determine_ext,
  17 )
  18
  19
  20 class MiTeleBaseIE(InfoExtractor):
  21     def _get_player_info(self, url, webpage):
  22         player_data = extract_attributes(self._search_regex(
  23             r'(?s)(<ms-video-player.+?</ms-video-player>)',
  24             webpage, 'ms video player'))
  25         video_id = player_data['data-media-id']
  26         config_url = compat_urlparse.urljoin(url, player_data['data-config'])
  27         config = self._download_json(
  28             config_url, video_id, 'Downloading config JSON')
  29         mmc_url = config['services']['mmc']
  30
  31         duration = None
  32         formats = []
  33         for m_url in (mmc_url, mmc_url.replace('/flash.json', '/html5.json')):
  34             mmc = self._download_json(
  35                 m_url, video_id, 'Downloading mmc JSON')
  36             if not duration:
  37                 duration = int_or_none(mmc.get('duration'))
  38             for location in mmc['locations']:
  39                 gat = self._proto_relative_url(location.get('gat'), 'http:')
  40                 bas = location.get('bas')
  41                 loc = location.get('loc')
  42                 ogn = location.get('ogn')
  43                 if None in (gat, bas, loc, ogn):
  44                     continue
  45                 token_data = {
  46                     'bas': bas,
  47                     'icd': loc,
  48                     'ogn': ogn,
  49                     'sta': '0',
  50                 }
  51                 media = self._download_json(
  52                     '%s/?%s' % (gat, compat_urllib_parse_urlencode(token_data)),
  53                     video_id, 'Downloading %s JSON' % location['loc'])
  54                 file_ = media.get('file')
  55                 if not file_:
  56                     continue
  57                 ext = determine_ext(file_)
  58                 if ext == 'f4m':
  59                     formats.extend(self._extract_f4m_formats(
  60                         file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
  61                         video_id, f4m_id='hds', fatal=False))
  62                 elif ext == 'm3u8':
  63                     formats.extend(self._extract_m3u8_formats(
  64                         file_, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
  65         self._sort_formats(formats)
  66
  67         return {
  68             'id': video_id,
  69             'formats': formats,
  70             'thumbnail': player_data.get('data-poster') or config.get('poster', {}).get('imageUrl'),
  71             'duration': duration,
  72         }
  73
  74
  75 class MiTeleIE(MiTeleBaseIE):
  76     IE_DESC = 'mitele.es'
  77     _VALID_URL = r'https?://www\.mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
  78
  79     _TESTS = [{
  80         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
  81         # MD5 is unstable
  82         'info_dict': {
  83             'id': '0NF1jJnxS1Wu3pHrmvFyw2',
  84             'display_id': 'programa-144',
  85             'ext': 'mp4',
  86             'title': 'Tor, la web invisible',
  87             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
  88             'series': 'Diario de',
  89             'season': 'La redacción',
  90             'episode': 'Programa 144',
  91             'thumbnail': 're:(?i)^https?://.*\.jpg$',
  92             'duration': 2913,
  93         },
  94     }, {
  95         # no explicit title
  96         'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/temporada-6/programa-226/',
  97         'info_dict': {
  98             'id': 'eLZSwoEd1S3pVyUm8lc6F',
  99             'display_id': 'programa-226',
 100             'ext': 'mp4',
 101             'title': 'Cuarto Milenio - Temporada 6 - Programa 226',
 102             'description': 'md5:50daf9fadefa4e62d9fc866d0c015701',
 103             'series': 'Cuarto Milenio',
 104             'season': 'Temporada 6',
 105             'episode': 'Programa 226',
 106             'thumbnail': 're:(?i)^https?://.*\.jpg$',
 107             'duration': 7312,
 108         },
 109         'params': {
 110             'skip_download': True,
 111         },
 112     }]
 113
 114     def _real_extract(self, url):
 115         display_id = self._match_id(url)
 116
 117         webpage = self._download_webpage(url, display_id)
 118
 119         info = self._get_player_info(url, webpage)
 120
 121         title = self._search_regex(
 122             r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>',
 123             webpage, 'title', default=None)
 124
 125         mobj = re.search(r'''(?sx)
 126                             class="Destacado-text"[^>]*>.*?<h1>\s*
 127                             <span>(?P<series>[^<]+)</span>\s*
 128                             <span>(?P<season>[^<]+)</span>\s*
 129                             <span>(?P<episode>[^<]+)</span>''', webpage)
 130         series, season, episode = mobj.groups() if mobj else [None] * 3
 131
 132         if not title:
 133             if mobj:
 134                 title = '%s - %s - %s' % (series, season, episode)
 135             else:
 136                 title = remove_start(self._search_regex(
 137                     r'<title>([^<]+)</title>', webpage, 'title'), 'Ver online ')
 138
 139         info.update({
 140             'display_id': display_id,
 141             'title': title,
 142             'description': get_element_by_attribute('class', 'text', webpage),
 143             'series': series,
 144             'season': season,
 145             'episode': episode,
 146         })
 147         return info