test/test_youtube_signature.py

@@ -90,10 +90,6 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/e06dea74/player_ias.vflset/en_US/base.js',
         'AiuodmaDDYw8d3y4bf', 'ankd8eza2T6Qmw',
     ),
-    (
-        'https://www.youtube.com/s/player/5dd88d1d/player-plasma-ias-phone-en_US.vflset/base.js',
-        'kSxKFLeqzv_ZyHSAt', 'n8gS8oRlHOxPFA',
-    ),
 ]
 
 

yt_dlp/extractor/rtvs.py

@@ -1,19 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
-from ..utils import (
-    parse_duration,
-    traverse_obj,
-    unified_timestamp,
-)
-
 
 class RTVSIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv(?:/\d+)?/(?P<id>\d+)/?(?:[#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv/\d+/(?P<id>\d+)'
     _TESTS = [{
         # radio archive
         'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
@@ -21,37 +13,23 @@ class RTVSIE(InfoExtractor):
         'info_dict': {
             'id': '414872',
             'ext': 'mp3',
-            'title': 'Ostrov pokladov 1 časť.mp3',
+            'title': 'Ostrov pokladov 1 časť.mp3'
-            'duration': 2854,
+        },
-            'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0000/b1R8.rtvs.jpg',
+        'params': {
-            'display_id': '135331',
+            'skip_download': True,
         }
     }, {
         # tv archive
         'url': 'http://www.rtvs.sk/televizia/archiv/8249/63118',
+        'md5': '85e2c55cf988403b70cac24f5c086dc6',
         'info_dict': {
             'id': '63118',
             'ext': 'mp4',
             'title': 'Amaro Džives - Náš deň',
-            'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.',
+            'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.'
-            'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0031/L7Qm.amaro_dzives_png.jpg',
+        },
-            'timestamp': 1428555900,
+        'params': {
-            'upload_date': '20150409',
+            'skip_download': True,
-            'duration': 4986,
-        }
-    }, {
-        # tv archive
-        'url': 'https://www.rtvs.sk/televizia/archiv/18083?utm_source=web&utm_medium=rozcestnik&utm_campaign=Robin',
-        'info_dict': {
-            'id': '18083',
-            'ext': 'mp4',
-            'title': 'Robin',
-            'description': 'md5:2f70505a7b8364491003d65ff7a0940a',
-            'timestamp': 1636652760,
-            'display_id': '307655',
-            'duration': 831,
-            'upload_date': '20211111',
-            'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0916/robin.jpg',
         }
     }]
 
@@ -59,31 +37,11 @@ class RTVSIE(InfoExtractor):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        iframe_id = self._search_regex(
-            r'<iframe[^>]+id\s*=\s*"player_[^_]+_([0-9]+)"', webpage, 'Iframe ID')
-        iframe_url = self._search_regex(
-            fr'<iframe[^>]+id\s*=\s*"player_[^_]+_{re.escape(iframe_id)}"[^>]+src\s*=\s*"([^"]+)"', webpage, 'Iframe URL')
 
-        webpage = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
+        playlist_url = self._search_regex(
-        json_url = self._search_regex(r'var\s+url\s*=\s*"([^"]+)"\s*\+\s*ruurl', webpage, 'json URL')
+            r'playlist["\']?\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
-        data = self._download_json(f'https:{json_url}b=mozilla&p=win&v=97&f=0&d=1', video_id)
+            'playlist url', group='url')
 
-        if data.get('clip'):
+        data = self._download_json(
-            data['playlist'] = [data['clip']]
+            playlist_url, video_id, 'Downloading playlist')[0]
-
+        return self._parse_jwplayer_data(data, video_id=video_id)
-        if traverse_obj(data, ('playlist', 0, 'sources', 0, 'type')) == 'audio/mp3':
-            formats = [{'url': traverse_obj(data, ('playlist', 0, 'sources', 0, 'src'))}]
-        else:
-            formats = self._extract_m3u8_formats(traverse_obj(data, ('playlist', 0, 'sources', 0, 'src')), video_id)
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'display_id': iframe_id,
-            'title': traverse_obj(data, ('playlist', 0, 'title')),
-            'description': traverse_obj(data, ('playlist', 0, 'description')),
-            'duration': parse_duration(traverse_obj(data, ('playlist', 0, 'length'))),
-            'thumbnail': traverse_obj(data, ('playlist', 0, 'image')),
-            'timestamp': unified_timestamp(traverse_obj(data, ('playlist', 0, 'datetime_create'))),
-            'formats': formats
-        }

yt_dlp/extractor/youtube.py

@@ -2413,7 +2413,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _extract_n_function_name(self, jscode):
         nfunc, idx = self._search_regex(
-            r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
+            r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]{3})(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
             jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
         if not idx:
             return nfunc