[teachable] Improve embed detection (closes #26923)

Co-authored-by: sofutru <54445344+sofutru@users.noreply.github.com>

youtube_dl/extractor/mitele.py

@@ -1,15 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+from .telecinco import TelecincoIE
 from ..utils import (
     int_or_none,
     parse_iso8601,
-    smuggle_url,
 )
 
 
-class MiTeleIE(InfoExtractor):
+class MiTeleIE(TelecincoIE):
     IE_DESC = 'mitele.es'
     _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
 
@@ -31,7 +30,6 @@ class MiTeleIE(InfoExtractor):
             'timestamp': 1471209401,
             'upload_date': '20160814',
         },
-        'add_ie': ['Ooyala'],
     }, {
         # no explicit title
         'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
@@ -54,7 +52,6 @@ class MiTeleIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
-        'add_ie': ['Ooyala'],
     }, {
         'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
         'only_matching': True,
@@ -70,16 +67,11 @@ class MiTeleIE(InfoExtractor):
             r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=\s*({.+})',
             webpage, 'Pre Player'), display_id)['prePlayer']
         title = pre_player['title']
-        video = pre_player['video']
+        video_info = self._parse_content(pre_player['video'], url)
-        video_id = video['dataMediaId']
         content = pre_player.get('content') or {}
         info = content.get('info') or {}
 
-        return {
+        video_info.update({
-            '_type': 'url_transparent',
-            # for some reason only HLS is supported
-            'url': smuggle_url('ooyala:' + video_id, {'supportedformats': 'm3u8,dash'}),
-            'id': video_id,
             'title': title,
             'description': info.get('synopsis'),
             'series': content.get('title'),
@@ -87,7 +79,7 @@ class MiTeleIE(InfoExtractor):
             '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')),
-        }
+        })
+        return video_info

youtube_dl/extractor/teachable.py

@@ -140,7 +140,7 @@ class TeachableIE(TeachableBaseIE):
     @staticmethod
     def _is_teachable(webpage):
         return 'teachableTracker.linker:autoLink' in webpage and re.search(
-            r'<link[^>]+href=["\']https?://process\.fs\.teachablecdn\.com',
+            r'<link[^>]+href=["\']https?://(?:process\.fs|assets)\.teachablecdn\.com',
             webpage)
 
     @staticmethod

youtube_dl/extractor/telecinco.py

@@ -5,14 +5,11 @@ import json
 import re
 
 from .common import InfoExtractor
-from .ooyala import OoyalaIE
 from ..utils import (
     clean_html,
-    determine_ext,
     int_or_none,
     str_or_none,
     try_get,
-    urljoin,
 )
 
 
@@ -28,7 +25,7 @@ class TelecincoIE(InfoExtractor):
             'description': 'md5:716caf5601e25c3c5ab6605b1ae71529',
         },
         'playlist': [{
-            'md5': 'adb28c37238b675dad0f042292f209a7',
+            'md5': '7ee56d665cfd241c0e6d80fd175068b0',
             'info_dict': {
                 'id': 'JEA5ijCnF6p5W08A1rNKn7',
                 'ext': 'mp4',
@@ -38,7 +35,7 @@ class TelecincoIE(InfoExtractor):
         }]
     }, {
         'url': 'http://www.cuatro.com/deportes/futbol/barcelona/Leo_Messi-Champions-Roma_2_2052780128.html',
-        'md5': '9468140ebc300fbb8b9d65dc6e5c4b43',
+        'md5': 'c86fe0d99e3bdb46b7950d38bf6ef12a',
         'info_dict': {
             'id': 'jn24Od1zGLG4XUZcnUnZB6',
             'ext': 'mp4',
@@ -48,7 +45,7 @@ class TelecincoIE(InfoExtractor):
         },
     }, {
         'url': 'http://www.mediaset.es/12meses/campanas/doylacara/conlatratanohaytrato/Ayudame-dar-cara-trata-trato_2_1986630220.html',
-        'md5': 'ae2dc6b7b50b2392076a51c0f70e01f6',
+        'md5': 'eddb50291df704ce23c74821b995bcac',
         'info_dict': {
             'id': 'aywerkD2Sv1vGNqq9b85Q2',
             'ext': 'mp4',
@@ -90,58 +87,24 @@ class TelecincoIE(InfoExtractor):
 
     def _parse_content(self, content, url):
         video_id = content['dataMediaId']
-        if content.get('dataCmsId') == 'ooyala':
-            return self.url_result(
-                'ooyala:%s' % video_id, OoyalaIE.ie_key(), video_id)
-        config_url = urljoin(url, content['dataConfig'])
         config = self._download_json(
-            config_url, video_id, 'Downloading config JSON')
+            content['dataConfig'], video_id, 'Downloading config JSON')
         title = config['info']['title']
-
+        services = config['services']
-        def mmc_url(mmc_type):
+        caronte = self._download_json(services['caronte'], video_id)
-            return re.sub(
+        stream = caronte['dls'][0]['stream']
-                r'/(?:flash|html5)\.json', '/%s.json' % mmc_type,
+        headers = self.geo_verification_headers()
-                config['services']['mmc'])
+        headers.update({
-
+            'Content-Type': 'application/json;charset=UTF-8',
-        duration = None
+            'Origin': re.match(r'https?://[^/]+', url).group(0),
-        formats = []
+        })
-        for mmc_type in ('flash', 'html5'):
+        cdn = self._download_json(
-            mmc = self._download_json(
+            caronte['cerbero'], video_id, data=json.dumps({
-                mmc_url(mmc_type), video_id,
+                'bbx': caronte['bbx'],
-                'Downloading %s mmc JSON' % mmc_type, fatal=False)
+                'gbx': self._download_json(services['gbx'], video_id)['gbx'],
-            if not mmc:
+            }).encode(), headers=headers)['tokens']['1']['cdn']
-                continue
+        formats = self._extract_m3u8_formats(
-            if not duration:
+            stream + '?' + cdn, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
-                duration = int_or_none(mmc.get('duration'))
-            for location in mmc['locations']:
-                gat = self._proto_relative_url(location.get('gat'), 'http:')
-                gcp = location.get('gcp')
-                ogn = location.get('ogn')
-                if None in (gat, gcp, ogn):
-                    continue
-                token_data = {
-                    'gcp': gcp,
-                    'ogn': ogn,
-                    'sta': 0,
-                }
-                media = self._download_json(
-                    gat, video_id, data=json.dumps(token_data).encode('utf-8'),
-                    headers={
-                        'Content-Type': 'application/json;charset=utf-8',
-                        'Referer': url,
-                    }, fatal=False) or {}
-                stream = media.get('stream') or media.get('file')
-                if not stream:
-                    continue
-                ext = determine_ext(stream)
-                if ext == 'f4m':
-                    formats.extend(self._extract_f4m_formats(
-                        stream + '&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(
-                        stream, video_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls', fatal=False))
         self._sort_formats(formats)
 
         return {
@@ -149,7 +112,7 @@ class TelecincoIE(InfoExtractor):
             'title': title,
             'formats': formats,
             'thumbnail': content.get('dataPoster') or config.get('poster', {}).get('imageUrl'),
-            'duration': duration,
+            'duration': int_or_none(content.get('dataDuration')),
         }
 
     def _real_extract(self, url):

youtube_dl/extractor/youtube.py

@@ -321,7 +321,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
                             (?:(?:www|dev)\.)?invidio\.us/|
                             (?:(?:www|no)\.)?invidiou\.sh/|
-                            (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
+                            (?:(?:www|fi)\.)?invidious\.snopyta\.org/|
                             (?:www\.)?invidious\.kabi\.tk/|
                             (?:www\.)?invidious\.13ad\.de/|
                             (?:www\.)?invidious\.mastodon\.host/|