[telewebion] Fix extraction (#32634)

* [telewebion] fix extraction

Resolves https://github.com/ytdl-org/youtube-dl/issues/5135#issuecomment-932952119

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>

diff --git a/youtube_dl/extractor/telewebion.py b/youtube_dl/extractor/telewebion.py
index 1207b1a1b8cdcc5fc5b3d1c71b51c54ba1c300e4..30192d74e1709327e130975d2fe183239842fd79 100644 (file)
--- a/youtube_dl/extractor/telewebion.py
+++ b/youtube_dl/extractor/telewebion.py
@@ -3,17 +3,23 @@ from __future__ import unicode_literals
 
 from .common import InfoExtractor
 
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    url_or_none,
+)
+
 
 class TelewebionIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?telewebion\.com/#!/episode/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?telewebion\.com/(episode|clip)/(?P<id>[a-zA-Z0-9]+)'
 
     _TEST = {
-        'url': 'http://www.telewebion.com/#!/episode/1263668/',
+        'url': 'http://www.telewebion.com/episode/0x1b3139c/',
         'info_dict': {
-            'id': '1263668',
+            'id': '0x1b3139c',
             'ext': 'mp4',
             'title': 'قرعه\u200cکشی لیگ قهرمانان اروپا',
-            'thumbnail': r're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://static\.telewebion\.com/episodeImages/.*/default',
             'view_count': int,
         },
         'params': {
@@ -25,31 +31,24 @@ class TelewebionIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        secure_token = self._download_webpage(
-            'http://m.s2.telewebion.com/op/op?action=getSecurityToken', video_id)
-        episode_details = self._download_json(
-            'http://m.s2.telewebion.com/op/op', video_id,
-            query={'action': 'getEpisodeDetails', 'episode_id': video_id})
-
-        m3u8_url = 'http://m.s1.telewebion.com/smil/%s.m3u8?filepath=%s&m3u8=1&secure_token=%s' % (
-            video_id, episode_details['file_path'], secure_token)
-        formats = self._extract_m3u8_formats(
-            m3u8_url, video_id, ext='mp4', m3u8_id='hls')
+        episode_details = self._download_json('https://gateway.telewebion.ir/kandoo/episode/getEpisodeDetail/?EpisodeId={0}'.format(video_id), video_id)
+        episode_details = episode_details['body']['queryEpisode'][0]
 
-        picture_paths = [
-            episode_details.get('picture_path'),
-            episode_details.get('large_picture_path'),
-        ]
+        channel_id = episode_details['channel']['descriptor']
+        episode_image_id = episode_details.get('image')
+        episode_image = 'https://static.telewebion.com/episodeImages/{0}/default'.format(episode_image_id) if episode_image_id else None
 
-        thumbnails = [{
-            'url': picture_path,
-            'preference': idx,
-        } for idx, picture_path in enumerate(picture_paths) if picture_path is not None]
+        m3u8_url = 'https://cdna.telewebion.com/{0}/episode/{1}/playlist.m3u8'.format(channel_id, video_id)
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, ext='mp4', m3u8_id='hls',
+            entry_protocol='m3u8_native')
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': episode_details['title'],
             'formats': formats,
-            'thumbnails': thumbnails,
-            'view_count': episode_details.get('view_count'),
+            'thumbnail': url_or_none(episode_image),
+            'view_count': int_or_none(episode_details.get('view_count')),
+            'duration': float_or_none(episode_details.get('duration')),
         }