youtube_dl/extractor/mitele.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import uuid
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_urllib_parse_urlencode,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     int_or_none,
  14     extract_attributes,
  15     determine_ext,
  16     smuggle_url,
  17     parse_duration,
  18 )
  19
  20
  21 class MiTeleBaseIE(InfoExtractor):
  22     def _get_player_info(self, url, webpage):
  23         player_data = extract_attributes(self._search_regex(
  24             r'(?s)(<ms-video-player.+?</ms-video-player>)',
  25             webpage, 'ms video player'))
  26         video_id = player_data['data-media-id']
  27         config_url = compat_urlparse.urljoin(url, player_data['data-config'])
  28         config = self._download_json(
  29             config_url, video_id, 'Downloading config JSON')
  30         mmc_url = config['services']['mmc']
  31
  32         duration = None
  33         formats = []
  34         for m_url in (mmc_url, mmc_url.replace('/flash.json', '/html5.json')):
  35             mmc = self._download_json(
  36                 m_url, video_id, 'Downloading mmc JSON')
  37             if not duration:
  38                 duration = int_or_none(mmc.get('duration'))
  39             for location in mmc['locations']:
  40                 gat = self._proto_relative_url(location.get('gat'), 'http:')
  41                 bas = location.get('bas')
  42                 loc = location.get('loc')
  43                 ogn = location.get('ogn')
  44                 if None in (gat, bas, loc, ogn):
  45                     continue
  46                 token_data = {
  47                     'bas': bas,
  48                     'icd': loc,
  49                     'ogn': ogn,
  50                     'sta': '0',
  51                 }
  52                 media = self._download_json(
  53                     '%s/?%s' % (gat, compat_urllib_parse_urlencode(token_data)),
  54                     video_id, 'Downloading %s JSON' % location['loc'])
  55                 file_ = media.get('file')
  56                 if not file_:
  57                     continue
  58                 ext = determine_ext(file_)
  59                 if ext == 'f4m':
  60                     formats.extend(self._extract_f4m_formats(
  61                         file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
  62                         video_id, f4m_id='hds', fatal=False))
  63                 elif ext == 'm3u8':
  64                     formats.extend(self._extract_m3u8_formats(
  65                         file_, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
  66         self._sort_formats(formats)
  67
  68         return {
  69             'id': video_id,
  70             'formats': formats,
  71             'thumbnail': player_data.get('data-poster') or config.get('poster', {}).get('imageUrl'),
  72             'duration': duration,
  73         }
  74
  75
  76 class MiTeleIE(InfoExtractor):
  77     IE_DESC = 'mitele.es'
  78     _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
  79
  80     _TESTS = [{
  81         'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
  82         'info_dict': {
  83             'id': '57b0dfb9c715da65618b4afa',
  84             'ext': 'mp4',
  85             'title': 'Tor, la web invisible',
  86             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
  87             'series': 'Diario de',
  88             'season': 'La redacción',
  89             'episode': 'Programa 144',
  90             'thumbnail': 're:(?i)^https?://.*\.jpg$',
  91             'duration': 2913,
  92         },
  93         'add_ie': ['Ooyala'],
  94     }, {
  95         # no explicit title
  96         'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
  97         'info_dict': {
  98             'id': '57b0de3dc915da14058b4876',
  99             'ext': 'mp4',
 100             'title': 'Cuarto Milenio Temporada 6 Programa 226',
 101             'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
 102             'series': 'Cuarto Milenio',
 103             'season': 'Temporada 6',
 104             'episode': 'Programa 226',
 105             'thumbnail': 're:(?i)^https?://.*\.jpg$',
 106             'duration': 7313,
 107         },
 108         'params': {
 109             'skip_download': True,
 110         },
 111         'add_ie': ['Ooyala'],
 112     }, {
 113         'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
 114         'only_matching': True,
 115     }]
 116
 117     def _real_extract(self, url):
 118         video_id = self._match_id(url)
 119         webpage = self._download_webpage(url, video_id)
 120
 121         gigya_url = self._search_regex(r'<gigya-api>[^>]*</gigya-api>[^>]*<script\s*src="([^"]*)">[^>]*</script>', webpage, 'gigya', default=None)
 122         gigya_sc = self._download_webpage(compat_urlparse.urljoin(r'http://www.mitele.es/', gigya_url), video_id, 'Downloading gigya script')
 123         # Get a appKey/uuid for getting the session key
 124         appKey_var = self._search_regex(r'value\("appGridApplicationKey",([0-9a-f]+)\)', gigya_sc, 'appKey variable')
 125         appKey = self._search_regex(r'var %s="([0-9a-f]+)"' % appKey_var, gigya_sc, 'appKey')
 126         uid = compat_str(uuid.uuid4())
 127         session_url = 'https://appgrid-api.cloud.accedo.tv/session?appKey=%s&uuid=%s' % (appKey, uid)
 128         session_json = self._download_json(session_url, video_id, 'Downloading session keys')
 129         sessionKey = compat_str(session_json['sessionKey'])
 130
 131         paths_url = 'https://appgrid-api.cloud.accedo.tv/metadata/general_configuration,%20web_configuration?sessionKey=' + sessionKey
 132         paths = self._download_json(paths_url, video_id, 'Downloading paths JSON')
 133         ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
 134         data_p = (
 135             'http://' + ooyala_s['base_url'] + ooyala_s['full_path'] + ooyala_s['provider_id'] +
 136             '/docs/' + video_id + '?include_titles=Series,Season&product_name=test&format=full')
 137         data = self._download_json(data_p, video_id, 'Downloading data JSON')
 138         source = data['hits']['hits'][0]['_source']
 139         embedCode = source['offers'][0]['embed_codes'][0]
 140
 141         titles = source['localizable_titles'][0]
 142         title = titles.get('title_medium') or titles['title_long']
 143         episode = titles['title_sort_name']
 144         description = titles['summary_long']
 145         titles_series = source['localizable_titles_series'][0]
 146         series = titles_series['title_long']
 147         titles_season = source['localizable_titles_season'][0]
 148         season = titles_season['title_medium']
 149         duration = parse_duration(source['videos'][0]['duration'])
 150
 151         return {
 152             '_type': 'url_transparent',
 153             # for some reason only HLS is supported
 154             'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8'}),
 155             'id': video_id,
 156             'title': title,
 157             'description': description,
 158             'series': series,
 159             'season': season,
 160             'episode': episode,
 161             'duration': duration,
 162             'thumbnail': source['images'][0]['url'],
 163         }