[ie/mitele] Remove extractor (#14348)

Closes #13535
Authored by: bashonly

yt_dlp/extractor/_extractors.py

@@ -1136,7 +1136,6 @@ from .mit import (
     OCWMITIE,
     TechTVMITIE,
 )
-from .mitele import MiTeleIE
 from .mixch import (
     MixchArchiveIE,
     MixchIE,

yt_dlp/extractor/mitele.py

@@ -1,102 +0,0 @@
-from .telecinco import TelecincoBaseIE
-from ..utils import (
-    int_or_none,
-    parse_iso8601,
-)
-
-
-class MiTeleIE(TelecincoBaseIE):
-    IE_DESC = 'mitele.es'
-    _VALID_URL = r'https?://(?:www\.)?mitele\.es/(?:[^/]+/)+(?P<id>[^/]+)/player'
-    _TESTS = [{
-        'url': 'http://www.mitele.es/programas-tv/diario-de/57b0dfb9c715da65618b4afa/player',
-        'info_dict': {
-            'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg',
-            'ext': 'mp4',
-            'title': 'Diario de La redacción Programa 144',
-            'description': 'md5:07c35a7b11abb05876a6a79185b58d27',
-            'series': 'Diario de',
-            'season': 'Season 14',
-            'season_number': 14,
-            'episode': 'Tor, la web invisible',
-            'episode_number': 3,
-            'thumbnail': r're:(?i)^https?://.*\.jpg$',
-            'duration': 2913,
-            'age_limit': 16,
-            'timestamp': 1471209401,
-            'upload_date': '20160814',
-        },
-        'skip': 'HTTP Error 404 Not Found',
-    }, {
-        # no explicit title
-        'url': 'http://www.mitele.es/programas-tv/cuarto-milenio/57b0de3dc915da14058b4876/player',
-        'info_dict': {
-            'id': 'oyNG1iNTE6TAPP-JmCjbwfwJqqMMX3Vq',
-            'ext': 'mp4',
-            'title': 'Cuarto Milenio Temporada 6 Programa 226',
-            'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
-            'series': 'Cuarto Milenio',
-            'season': 'Season 6',
-            'season_number': 6,
-            'episode': 'Episode 24',
-            'episode_number': 24,
-            'thumbnail': r're:(?i)^https?://.*\.jpg$',
-            'duration': 7313,
-            'age_limit': 12,
-            'timestamp': 1471209021,
-            'upload_date': '20160814',
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'skip': 'HTTP Error 404 Not Found',
-    }, {
-        'url': 'https://www.mitele.es/programas-tv/horizonte/temporada-5/programa-171-40_013480051/player/',
-        'info_dict': {
-            'id': '7adbe22e-cd41-4787-afa4-36f3da7c2c6f',
-            'ext': 'mp4',
-            'title': 'Horizonte Temporada 5 Programa 171',
-            'description': 'md5:97f1fb712c5ac27e5693a8b3c5c0c6e3',
-            'episode': 'Las Zonas de Bajas Emisiones, a debate',
-            'episode_number': 171,
-            'season': 'Season 5',
-            'season_number': 5,
-            'series': 'Horizonte',
-            'duration': 7012,
-            'upload_date': '20240927',
-            'timestamp': 1727416450,
-            'thumbnail': 'https://album.mediaset.es/eimg/2024/09/27/horizonte-171_9f02.jpg',
-            'age_limit': 12,
-        },
-        'params': {'geo_bypass_country': 'ES'},
-    }, {
-        '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)
-        webpage = self._download_webpage(url, display_id)
-        pre_player = self._search_json(
-            r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=',
-            webpage, 'Pre Player', display_id)['prePlayer']
-        title = pre_player['title']
-        video_info = self._parse_content(pre_player['video'], url)
-        content = pre_player.get('content') or {}
-        info = content.get('info') or {}
-
-        video_info.update({
-            'title': title,
-            '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')),
-            'age_limit': int_or_none(info.get('rating')),
-            'timestamp': parse_iso8601(pre_player.get('publishedTime')),
-        })
-        return video_info

yt_dlp/extractor/unsupported.py

@@ -65,6 +65,7 @@ class KnownDRMIE(UnsupportedInfoExtractor):
         r'play\.rtl\.hr',
         r'rtlmost\.hu',
         r'plus\.rtl\.de(?!/podcast/)',
+        r'mediasetinfinity\.es',
     )
 
     _TESTS = [{
@@ -222,6 +223,9 @@ class KnownDRMIE(UnsupportedInfoExtractor):
     }, {
         'url': 'https://plus.rtl.de/video-tv/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.mediasetinfinity.es/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/vk.py

@@ -96,12 +96,12 @@ class VKIE(VKBaseIE):
                     https?://
                         (?:
                             (?:
-                                (?:(?:m|new)\.)?vk(?:(?:video)?\.ru|\.com)/video_|
+                                (?:(?:m|new|vksport)\.)?vk(?:(?:video)?\.ru|\.com)/video_|
                                 (?:www\.)?daxab\.com/
                             )
                             ext\.php\?(?P<embed_query>.*?\boid=(?P<oid>-?\d+).*?\bid=(?P<id>\d+).*)|
                             (?:
-                                (?:(?:m|new)\.)?vk(?:(?:video)?\.ru|\.com)/(?:.+?\?.*?z=)?(?:video|clip)|
+                                (?:(?:m|new|vksport)\.)?vk(?:(?:video)?\.ru|\.com)/(?:.+?\?.*?z=)?(?:video|clip)|
                                 (?:www\.)?daxab\.com/embed/
                             )
                             (?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
@@ -359,6 +359,10 @@ class VKIE(VKBaseIE):
             'url': 'https://vk.ru/video-220754053_456242564',
             'only_matching': True,
         },
+        {
+            'url': 'https://vksport.vkvideo.ru/video-124096712_456240773',
+            'only_matching': True,
+        },
     ]
 
     def _real_extract(self, url):

yt_dlp/extractor/xhamster.py

@@ -1,4 +1,5 @@
 import base64
+import codecs
 import itertools
 import re
 
@@ -11,13 +12,13 @@ from ..utils import (
     extract_attributes,
     float_or_none,
     int_or_none,
+    join_nonempty,
     parse_duration,
     str_or_none,
     try_call,
     try_get,
     unified_strdate,
     url_or_none,
-    urljoin,
 )
 
 
@@ -142,6 +143,27 @@ class XHamsterIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    _XOR_KEY = b'xh7999'
+
+    def _decipher_format_url(self, format_url, format_id):
+        cipher_type, _, ciphertext = try_call(
+            lambda: base64.b64decode(format_url).decode().partition('_')) or [None] * 3
+
+        if not cipher_type or not ciphertext:
+            self.report_warning(f'Skipping format "{format_id}": failed to decipher URL')
+            return None
+
+        if cipher_type == 'xor':
+            return bytes(
+                a ^ b for a, b in
+                zip(ciphertext.encode(), itertools.cycle(self._XOR_KEY))).decode()
+
+        if cipher_type == 'rot13':
+            return codecs.decode(ciphertext, cipher_type)
+
+        self.report_warning(f'Skipping format "{format_id}": unsupported cipher type "{cipher_type}"')
+        return None
+
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id') or mobj.group('id_2')
@@ -212,7 +234,7 @@ class XHamsterIE(InfoExtractor):
                         hls_url = hls_sources.get(hls_format_key)
                         if not hls_url:
                             continue
-                        hls_url = urljoin(url, hls_url)
+                        hls_url = self._decipher_format_url(hls_url, f'hls-{hls_format_key}')
                         if not hls_url or hls_url in format_urls:
                             continue
                         format_urls.add(hls_url)
@@ -221,7 +243,7 @@ class XHamsterIE(InfoExtractor):
                             m3u8_id='hls', fatal=False))
                 standard_sources = xplayer_sources.get('standard')
                 if isinstance(standard_sources, dict):
-                    for format_id, formats_list in standard_sources.items():
+                    for identifier, formats_list in standard_sources.items():
                         if not isinstance(formats_list, list):
                             continue
                         for standard_format in formats_list:
@@ -231,12 +253,11 @@ class XHamsterIE(InfoExtractor):
                                 standard_url = standard_format.get(standard_format_key)
                                 if not standard_url:
                                     continue
-                                decoded = try_call(lambda: base64.b64decode(standard_url))
-                                if decoded and decoded[:4] == b'xor_':
-                                    standard_url = bytes(
-                                        a ^ b for a, b in
-                                        zip(decoded[4:], itertools.cycle(b'xh7999'))).decode()
-                                standard_url = urljoin(url, standard_url)
+                                quality = (str_or_none(standard_format.get('quality'))
+                                           or str_or_none(standard_format.get('label'))
+                                           or '')
+                                format_id = join_nonempty(identifier, quality)
+                                standard_url = self._decipher_format_url(standard_url, format_id)
                                 if not standard_url or standard_url in format_urls:
                                     continue
                                 format_urls.add(standard_url)
@@ -246,11 +267,9 @@ class XHamsterIE(InfoExtractor):
                                         standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
                                         m3u8_id='hls', fatal=False))
                                     continue
-                                quality = (str_or_none(standard_format.get('quality'))
-                                           or str_or_none(standard_format.get('label'))
-                                           or '')
+
                                 formats.append({
-                                    'format_id': f'{format_id}-{quality}',
+                                    'format_id': format_id,
                                     'url': standard_url,
                                     'ext': ext,
                                     'height': get_height(quality),