Raphaël G. Git Repositories - youtubedl/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,
   6     compat_urlparse,
   7 )
   8 from ..utils import (
   9     encode_dict,
  10     get_element_by_attribute,
  11     int_or_none,
  12 )
  13
  14
  15 class MiTeleIE(InfoExtractor):
  16     IE_DESC = 'mitele.es'
  17     _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
  18
  19     _TESTS = [{
  20         'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
  21         'md5': '0ff1a13aebb35d9bc14081ff633dd324',
  22         'info_dict': {
  23             'id': '0NF1jJnxS1Wu3pHrmvFyw2',
  24             'display_id': 'programa-144',
  25             'ext': 'flv',
  26             'title': 'Tor, la web invisible',
  27             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
  28             'thumbnail': 're:(?i)^https?://.*\.jpg$',
  29             'duration': 2913,
  30         },
  31     }]
  32
  33     def _real_extract(self, url):
  34         display_id = self._match_id(url)
  35
  36         webpage = self._download_webpage(url, display_id)
  37
  38         config_url = self._search_regex(
  39             r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url')
  40         config_url = compat_urlparse.urljoin(url, config_url)
  41
  42         config = self._download_json(
  43             config_url, display_id, 'Downloading config JSON')
  44
  45         mmc = self._download_json(
  46             config['services']['mmc'], display_id, 'Downloading mmc JSON')
  47
  48         formats = []
  49         for location in mmc['locations']:
  50             gat = self._proto_relative_url(location.get('gat'), 'http:')
  51             bas = location.get('bas')
  52             loc = location.get('loc')
  53             ogn = location.get('ogn')
  54             if None in (gat, bas, loc, ogn):
  55                 continue
  56             token_data = {
  57                 'bas': bas,
  58                 'icd': loc,
  59                 'ogn': ogn,
  60                 'sta': '0',
  61             }
  62             media = self._download_json(
  63                 '%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data))),
  64                 display_id, 'Downloading %s JSON' % location['loc'])
  65             file_ = media.get('file')
  66             if not file_:
  67                 continue
  68             formats.extend(self._extract_f4m_formats(
  69                 file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
  70                 display_id, f4m_id=loc))
  71
  72         title = self._search_regex(
  73             r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>', webpage, 'title')
  74
  75         video_id = self._search_regex(
  76             r'data-media-id\s*=\s*"([^"]+)"', webpage,
  77             'data media id', default=None) or display_id
  78         thumbnail = config.get('poster', {}).get('imageUrl')
  79         duration = int_or_none(mmc.get('duration'))
  80
  81         return {
  82             'id': video_id,
  83             'display_id': display_id,
  84             'title': title,
  85             'description': get_element_by_attribute('class', 'text', webpage),
  86             'thumbnail': thumbnail,
  87             'duration': duration,
  88             'formats': formats,
  89         }