_ 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 compat_urllib_parse
   5 from ..utils import (
   6     encode_dict,
   7     get_element_by_attribute,
   8     int_or_none,
   9 )
  10
  11
  12 class MiTeleIE(InfoExtractor):
  13     IE_DESC = 'mitele.es'
  14     _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
  15
  16     _TESTS = [{
  17         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
  18         'md5': 'ace7635b2a0b286aaa37d3ff192d2a8a',
  19         'info_dict': {
  20             'id': '0NF1jJnxS1Wu3pHrmvFyw2',
  21             'display_id': 'programa-144',
  22             'ext': 'flv',
  23             'title': 'Tor, la web invisible',
  24             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
  25             'thumbnail': 're:(?i)^https?://.*\.jpg$',
  26             'duration': 2913,
  27         },
  28     }]
  29
  30     def _real_extract(self, url):
  31         display_id = self._match_id(url)
  32
  33         webpage = self._download_webpage(url, display_id)
  34
  35         config_url = self._search_regex(
  36             r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url')
  37
  38         config = self._download_json(
  39             config_url, display_id, 'Downloading config JSON')
  40
  41         mmc = self._download_json(
  42             config['services']['mmc'], display_id, 'Downloading mmc JSON')
  43
  44         formats = []
  45         for location in mmc['locations']:
  46             gat = self._proto_relative_url(location.get('gat'), 'http:')
  47             bas = location.get('bas')
  48             loc = location.get('loc')
  49             ogn = location.get('ogn')
  50             if None in (gat, bas, loc, ogn):
  51                 continue
  52             token_data = {
  53                 'bas': bas,
  54                 'icd': loc,
  55                 'ogn': ogn,
  56                 'sta': '0',
  57             }
  58             media = self._download_json(
  59                 '%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data)).encode('utf-8')),
  60                 display_id, 'Downloading %s JSON' % location['loc'])
  61             file_ = media.get('file')
  62             if not file_:
  63                 continue
  64             formats.extend(self._extract_f4m_formats(
  65                 file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
  66                 display_id, f4m_id=loc))
  67
  68         title = self._search_regex(
  69             r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>', webpage, 'title')
  70
  71         video_id = self._search_regex(
  72             r'data-media-id\s*=\s*"([^"]+)"', webpage,
  73             'data media id', default=None) or display_id
  74         thumbnail = config.get('poster', {}).get('imageUrl')
  75         duration = int_or_none(mmc.get('duration'))
  76
  77         return {
  78             'id': video_id,
  79             'display_id': display_id,
  80             'title': title,
  81             'description': get_element_by_attribute('class', 'text', webpage),
  82             'thumbnail': thumbnail,
  83             'duration': duration,
  84             'formats': formats,
  85         }