_ Git - youtube-dl/blob - youtube_dl/extractor/mitele.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_urllib_parse_urlencode,
   6     compat_urlparse,
   7 )
   8 from ..utils import (
   9     get_element_by_attribute,
  10     int_or_none,
  11 )
  12
  13
  14 class MiTeleIE(InfoExtractor):
  15     IE_DESC = 'mitele.es'
  16     _VALID_URL = r'https?://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
  17
  18     _TESTS = [{
  19         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
  20         'md5': '0ff1a13aebb35d9bc14081ff633dd324',
  21         'info_dict': {
  22             'id': '0NF1jJnxS1Wu3pHrmvFyw2',
  23             'display_id': 'programa-144',
  24             'ext': 'flv',
  25             'title': 'Tor, la web invisible',
  26             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
  27             'thumbnail': 're:(?i)^https?://.*\.jpg$',
  28             'duration': 2913,
  29         },
  30     }]
  31
  32     def _real_extract(self, url):
  33         display_id = self._match_id(url)
  34
  35         webpage = self._download_webpage(url, display_id)
  36
  37         config_url = self._search_regex(
  38             r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url')
  39         config_url = compat_urlparse.urljoin(url, config_url)
  40
  41         config = self._download_json(
  42             config_url, display_id, 'Downloading config JSON')
  43
  44         mmc = self._download_json(
  45             config['services']['mmc'], display_id, 'Downloading mmc JSON')
  46
  47         formats = []
  48         for location in mmc['locations']:
  49             gat = self._proto_relative_url(location.get('gat'), 'http:')
  50             bas = location.get('bas')
  51             loc = location.get('loc')
  52             ogn = location.get('ogn')
  53             if None in (gat, bas, loc, ogn):
  54                 continue
  55             token_data = {
  56                 'bas': bas,
  57                 'icd': loc,
  58                 'ogn': ogn,
  59                 'sta': '0',
  60             }
  61             media = self._download_json(
  62                 '%s/?%s' % (gat, compat_urllib_parse_urlencode(token_data)),
  63                 display_id, 'Downloading %s JSON' % location['loc'])
  64             file_ = media.get('file')
  65             if not file_:
  66                 continue
  67             formats.extend(self._extract_f4m_formats(
  68                 file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
  69                 display_id, f4m_id=loc))
  70
  71         title = self._search_regex(
  72             r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>', webpage, 'title')
  73
  74         video_id = self._search_regex(
  75             r'data-media-id\s*=\s*"([^"]+)"', webpage,
  76             'data media id', default=None) or display_id
  77         thumbnail = config.get('poster', {}).get('imageUrl')
  78         duration = int_or_none(mmc.get('duration'))
  79
  80         return {
  81             'id': video_id,
  82             'display_id': display_id,
  83             'title': title,
  84             'description': get_element_by_attribute('class', 'text', webpage),
  85             'thumbnail': thumbnail,
  86             'duration': duration,
  87             'formats': formats,
  88         }