New upstream version 2019.01.16

[youtubedl] / youtube_dl / extractor / mitele.py

diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py
index d8897eb90d526b7b7d2e5a5ace5bec84ebb40031..40f214a873a7dcbb5087726aa270b74a5dab3e76 100644 (file)
--- a/youtube_dl/extractor/mitele.py
+++ b/youtube_dl/extractor/mitele.py
@@ -1,68 +1,120 @@
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import json
-

 from .common import InfoExtractor
 from .common import InfoExtractor

-from ..compat import (
-    compat_urllib_parse,
-    compat_urlparse,
-)

 from ..utils import (
 from ..utils import (

-    get_element_by_attribute,
+    int_or_none,
+    smuggle_url,

     parse_duration,
     parse_duration,

-    strip_jsonp,

 )
 
 
 class MiTeleIE(InfoExtractor):
 )
 
 
 class MiTeleIE(InfoExtractor):

-    IE_NAME = 'mitele.es'
-    _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
+    IE_DESC = 'mitele.es'
+    _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'

 
     _TESTS = [{
 
     _TESTS = [{

-        'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
-        'md5': '6a75fe9d0d3275bead0cb683c616fddb',
+        'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',

         'info_dict': {
         'info_dict': {

-            'id': '0fce117d',
+            'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Programa 144 - Tor, la web invisible',
+            'title': 'Tor, la web invisible',

             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
             'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',

-            'display_id': 'programa-144',
+            'series': 'Diario de',
+            'season': 'La redacción',
+            'season_number': 14,
+            'season_id': 'diario_de_t14_11981',
+            'episode': 'Programa 144',
+            'episode_number': 3,
+            'thumbnail': r're:(?i)^https?://.*\.jpg$',

             'duration': 2913,
         },
             'duration': 2913,
         },

+        'add_ie': ['Ooyala'],
+    }, {
+        # no explicit title
+        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
+        'info_dict': {
+            'id': 'oyNG1iNTE6TAPP-JmCjbwfwJqqMMX3Vq',
+            'ext': 'mp4',
+            'title': 'Cuarto Milenio Temporada 6 Programa 226',
+            'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
+            'series': 'Cuarto Milenio',
+            'season': 'Temporada 6',
+            'season_number': 6,
+            'season_id': 'cuarto_milenio_t06_12715',
+            'episode': 'Programa 226',
+            'episode_number': 24,
+            'thumbnail': r're:(?i)^https?://.*\.jpg$',
+            'duration': 7313,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Ooyala'],
+    }, {
+        'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):

-        episode = self._match_id(url)
-        webpage = self._download_webpage(url, episode)
-        embed_data_json = self._search_regex(
-            r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
-        ).replace('\'', '"')
-        embed_data = json.loads(embed_data_json)
-
-        domain = embed_data['mediaUrl']
-        if not domain.startswith('http'):
-            # only happens in telecinco.es videos
-            domain = 'http://' + domain
-        info_url = compat_urlparse.urljoin(
-            domain,
-            compat_urllib_parse.unquote(embed_data['flashvars']['host'])
-        )
-        info_el = self._download_xml(info_url, episode).find('./video/info')
-
-        video_link = info_el.find('videoUrl/link').text
-        token_query = compat_urllib_parse.urlencode({'id': video_link})
-        token_info = self._download_json(
-            embed_data['flashvars']['ov_tk'] + '?' + token_query,
-            episode,
-            transform_source=strip_jsonp
-        )
+        video_id = self._match_id(url)
+
+        paths = self._download_json(
+            'https://www.mitele.es/amd/agp/web/metadata/general_configuration',
+            video_id, 'Downloading paths JSON')
+
+        ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
+        base_url = ooyala_s.get('base_url', 'cdn-search-mediaset.carbyne.ps.ooyala.com')
+        full_path = ooyala_s.get('full_path', '/search/v1/full/providers/')
+        source = self._download_json(
+            '%s://%s%s%s/docs/%s' % (
+                ooyala_s.get('protocol', 'https'), base_url, full_path,
+                ooyala_s.get('provider_id', '104951'), video_id),
+            video_id, 'Downloading data JSON', query={
+                'include_titles': 'Series,Season',
+                'product_name': ooyala_s.get('product_name', 'test'),
+                'format': 'full',
+            })['hits']['hits'][0]['_source']
+
+        embedCode = source['offers'][0]['embed_codes'][0]
+        titles = source['localizable_titles'][0]
+
+        title = titles.get('title_medium') or titles['title_long']
+
+        description = titles.get('summary_long') or titles.get('summary_medium')
+
+        def get(key1, key2):
+            value1 = source.get(key1)
+            if not value1 or not isinstance(value1, list):
+                return
+            if not isinstance(value1[0], dict):
+                return
+            return value1[0].get(key2)
+
+        series = get('localizable_titles_series', 'title_medium')
+
+        season = get('localizable_titles_season', 'title_medium')
+        season_number = int_or_none(source.get('season_number'))
+        season_id = source.get('season_id')
+
+        episode = titles.get('title_sort_name')
+        episode_number = int_or_none(source.get('episode_number'))
+
+        duration = parse_duration(get('videos', 'duration'))

 
         return {
 
         return {

-            'id': embed_data['videoId'],
-            'display_id': episode,
-            'title': info_el.find('title').text,
-            'url': token_info['tokenizedUrl'],
-            'description': get_element_by_attribute('class', 'text', webpage),
-            'thumbnail': info_el.find('thumb').text,
-            'duration': parse_duration(info_el.find('duration').text),
+            '_type': 'url_transparent',
+            # for some reason only HLS is supported
+            'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8,dash'}),
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'series': series,
+            'season': season,
+            'season_number': season_number,
+            'season_id': season_id,
+            'episode': episode,
+            'episode_number': episode_number,
+            'duration': duration,
+            'thumbnail': get('images', 'url'),

         }
         }