]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/mitele.py
Rapsys Git / youtubedl / blobdiff
? search:
summary | shortlog | log | commit | commitdiff | tree
raw | inline | side by side
Initiate new release.
[youtubedl] / youtube_dl / extractor / mitele.py
diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py
index cd169f3616729871fcad9e6c619e67f392f73312..ad9da96125b92d66d4e6367e23b7ed9a1a633aaf 100644 (file)
--- a/youtube_dl/extractor/mitele.py
+++ b/youtube_dl/extractor/mitele.py
@@ -1,147 +1,93 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_urlencode,
-    compat_urlparse,
-)
 from ..utils import (
 from ..utils import (
-    get_element_by_attribute,
     int_or_none,
     int_or_none,
-    remove_start,
-    extract_attributes,
-    determine_ext,
+    parse_iso8601,
+    smuggle_url,
 )
 
 
 )
 
 
-class MiTeleBaseIE(InfoExtractor):
-    def _get_player_info(self, url, webpage):
-        player_data = extract_attributes(self._search_regex(
-            r'(?s)(<ms-video-player.+?</ms-video-player>)',
-            webpage, 'ms video player'))
-        video_id = player_data['data-media-id']
-        config_url = compat_urlparse.urljoin(url, player_data['data-config'])
-        config = self._download_json(
-            config_url, video_id, 'Downloading config JSON')
-        mmc_url = config['services']['mmc']
-
-        duration = None
-        formats = []
-        for m_url in (mmc_url, mmc_url.replace('/flash.json', '/html5.json')):
-            mmc = self._download_json(
-                m_url, video_id, 'Downloading mmc JSON')
-            if not duration:
-                duration = int_or_none(mmc.get('duration'))
-            for location in mmc['locations']:
-                gat = self._proto_relative_url(location.get('gat'), 'http:')
-                bas = location.get('bas')
-                loc = location.get('loc')
-                ogn = location.get('ogn')
-                if None in (gat, bas, loc, ogn):
-                    continue
-                token_data = {
-                    'bas': bas,
-                    'icd': loc,
-                    'ogn': ogn,
-                    'sta': '0',
-                }
-                media = self._download_json(
-                    '%s/?%s' % (gat, compat_urllib_parse_urlencode(token_data)),
-                    video_id, 'Downloading %s JSON' % location['loc'])
-                file_ = media.get('file')
-                if not file_:
-                    continue
-                ext = determine_ext(file_)
-                if ext == 'f4m':
-                    formats.extend(self._extract_f4m_formats(
-                        file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
-                        video_id, f4m_id='hds', fatal=False))
-                elif ext == 'm3u8':
-                    formats.extend(self._extract_m3u8_formats(
-                        file_, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'formats': formats,
-            'thumbnail': player_data.get('data-poster') or config.get('poster', {}).get('imageUrl'),
-            'duration': duration,
-        }
-
-
-class MiTeleIE(MiTeleBaseIE):
+class MiTeleIE(InfoExtractor):
     IE_DESC = 'mitele.es'
     IE_DESC = 'mitele.es'
-    _VALID_URL = r'https?://www\.mitele\.es/(?:[^/]+/){3}(?P<id>[^/]+)/'
+    _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 is unstable
+        'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
         'info_dict': {
         'info_dict': {
-            'id': '0NF1jJnxS1Wu3pHrmvFyw2',
-            'display_id': 'programa-144',
+            'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg',
             'ext': 'mp4',
             'ext': 'mp4',
-            'title': 'Tor, la web invisible',
-            'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
+            'title': 'Diario de La redacción Programa 144',
+            'description': 'md5:07c35a7b11abb05876a6a79185b58d27',
             'series': 'Diario de',
             'series': 'Diario de',
-            'season': 'La redacción',
-            'episode': 'Programa 144',
-            'thumbnail': 're:(?i)^https?://.*\.jpg$',
+            'season': 'Season 14',
+            'season_number': 14,
+            'episode': 'Tor, la web invisible',
+            'episode_number': 3,
+            'thumbnail': r're:(?i)^https?://.*\.jpg$',
             'duration': 2913,
             'duration': 2913,
+            'age_limit': 16,
+            'timestamp': 1471209401,
+            'upload_date': '20160814',
         },
         },
+        'add_ie': ['Ooyala'],
     }, {
         # no explicit title
     }, {
         # no explicit title
-        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/temporada-6/programa-226/',
+        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
         'info_dict': {
         'info_dict': {
-            'id': 'eLZSwoEd1S3pVyUm8lc6F',
-            'display_id': 'programa-226',
+            'id': 'oyNG1iNTE6TAPP-JmCjbwfwJqqMMX3Vq',
             'ext': 'mp4',
             'ext': 'mp4',
-            'title': 'Cuarto Milenio - Temporada 6 - Programa 226',
-            'description': 'md5:50daf9fadefa4e62d9fc866d0c015701',
+            'title': 'Cuarto Milenio Temporada 6 Programa 226',
+            'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
             'series': 'Cuarto Milenio',
             'series': 'Cuarto Milenio',
-            'season': 'Temporada 6',
-            'episode': 'Programa 226',
-            'thumbnail': 're:(?i)^https?://.*\.jpg$',
-            'duration': 7312,
+            'season': 'Season 6',
+            'season_number': 6,
+            'episode': 'Episode 24',
+            'episode_number': 24,
+            'thumbnail': r're:(?i)^https?://.*\.jpg$',
+            'duration': 7313,
+            'age_limit': 12,
+            'timestamp': 1471209021,
+            'upload_date': '20160814',
         },
         'params': {
             'skip_download': True,
         },
         },
         'params': {
             'skip_download': True,
         },
+        'add_ie': ['Ooyala'],
+    }, {
+        'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144-40_1006364575251/player/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
     }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-
         webpage = self._download_webpage(url, display_id)
         webpage = self._download_webpage(url, display_id)
+        pre_player = self._parse_json(self._search_regex(
+            r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=\s*({.+})',
+            webpage, 'Pre Player'), display_id)['prePlayer']
+        title = pre_player['title']
+        video = pre_player['video']
+        video_id = video['dataMediaId']
+        content = pre_player.get('content') or {}
+        info = content.get('info') or {}
 
 
-        info = self._get_player_info(url, webpage)
-
-        title = self._search_regex(
-            r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>',
-            webpage, 'title', default=None)
-
-        mobj = re.search(r'''(?sx)
-                            class="Destacado-text"[^>]*>.*?<h1>\s*
-                            <span>(?P<series>[^<]+)</span>\s*
-                            <span>(?P<season>[^<]+)</span>\s*
-                            <span>(?P<episode>[^<]+)</span>''', webpage)
-        series, season, episode = mobj.groups() if mobj else [None] * 3
-
-        if not title:
-            if mobj:
-                title = '%s - %s - %s' % (series, season, episode)
-            else:
-                title = remove_start(self._search_regex(
-                    r'<title>([^<]+)</title>', webpage, 'title'), 'Ver online ')
-
-        info.update({
-            'display_id': display_id,
+        return {
+            '_type': 'url_transparent',
+            # for some reason only HLS is supported
+            'url': smuggle_url('ooyala:' + video_id, {'supportedformats': 'm3u8,dash'}),
+            'id': video_id,
             'title': title,
             'title': title,
-            'description': get_element_by_attribute('class', 'text', webpage),
-            'series': series,
-            'season': season,
-            'episode': episode,
-        })
-        return info
+            'description': info.get('synopsis'),
+            'series': content.get('title'),
+            'season_number': int_or_none(info.get('season_number')),
+            'episode': content.get('subtitle'),
+            'episode_number': int_or_none(info.get('episode_number')),
+            'duration': int_or_none(info.get('duration')),
+            'thumbnail': video.get('dataPoster'),
+            'age_limit': int_or_none(info.get('rating')),
+            'timestamp': parse_iso8601(pre_player.get('publishedTime')),
+        }
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...