[ie/telecinco] Fix extractor (#13379)

Closes #13378
Authored by: bashonly

README.md

@@ -1797,7 +1797,7 @@ The following extractors use this feature:
 #### youtube
 * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
 * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
-* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
+* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv`, `tv_simply` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player), `initial_data` (skip initial data/next ep request). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause issues such as missing formats or metadata.  See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) and [#12826](https://github.com/yt-dlp/yt-dlp/issues/12826) for more details
 * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
 * `player_js_variant`: The player javascript variant to use for signature and nsig deciphering. The known variants are: `main`, `tce`, `tv`, `tv_es6`, `phone`, `tablet`. Only `main` is recommended as a possible workaround; the others are for debugging purposes. The default is to use what is prescribed by the site, and can be selected with `actual`

test/test_pot/test_pot_builtin_utils.py

@@ -11,7 +11,7 @@ class TestGetWebPoContentBinding:
 
     @pytest.mark.parametrize('client_name, context, is_authenticated, expected', [
         *[(client, context, is_authenticated, expected) for client in [
-            'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER']
+            'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', 'TVHTML5_SIMPLY']
           for context, is_authenticated, expected in [
             (PoTokenContext.GVS, False, ('example-visitor-data', ContentBindingType.VISITOR_DATA)),
             (PoTokenContext.PLAYER, False, ('example-video-id', ContentBindingType.VIDEO_ID)),

test/test_pot/test_pot_builtin_webpospec.py

@@ -49,7 +49,7 @@ class TestWebPoPCSP:
 
     @pytest.mark.parametrize('client_name, context, is_authenticated, remote_host, source_address, request_proxy, expected', [
         *[(client, context, is_authenticated, remote_host, source_address, request_proxy, expected) for client in [
-            'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER']
+            'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', 'TVHTML5_SIMPLY']
           for context, is_authenticated, remote_host, source_address, request_proxy, expected in [
             (PoTokenContext.GVS, False, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': '123abcXYZ_-', 'cbt': 'visitor_id'}),
             (PoTokenContext.PLAYER, False, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': '123abcXYZ_-', 'cbt': 'video_id'}),

yt_dlp/extractor/mitele.py

@@ -1,7 +1,5 @@
 from .telecinco import TelecincoBaseIE
-from ..networking.exceptions import HTTPError
 from ..utils import (
-    ExtractorError,
     int_or_none,
     parse_iso8601,
 )
@@ -81,17 +79,7 @@ class MiTeleIE(TelecincoBaseIE):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-
+        webpage = self._download_akamai_webpage(url, display_id)
-        try:  # yt-dlp's default user-agents are too old and blocked by akamai
-            webpage = self._download_webpage(url, display_id, headers={
-                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
-            })
-        except ExtractorError as e:
-            if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
-                raise
-            # Retry with impersonation if hardcoded UA is insufficient to bypass akamai
-            webpage = self._download_webpage(url, display_id, impersonate=True)
-
         pre_player = self._search_json(
             r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=',
             webpage, 'Pre Player', display_id)['prePlayer']

yt_dlp/extractor/stacommu.py

@@ -4,6 +4,7 @@ from .wrestleuniverse import WrestleUniverseBaseIE
 from ..utils import (
     int_or_none,
     traverse_obj,
+    url_basename,
     url_or_none,
 )
 
@@ -65,9 +66,19 @@ class StacommuBaseIE(WrestleUniverseBaseIE):
         hls_info, decrypt = self._call_encrypted_api(
             video_id, ':watchArchive', 'stream information', data={'method': 1})
 
+        formats = self._get_formats(hls_info, ('hls', 'urls', ..., {url_or_none}), video_id)
+        for f in formats:
+            # bitrates are exaggerated in PPV playlists, so avoid wrong/huge filesize_approx values
+            if f.get('tbr'):
+                f['tbr'] = int(f['tbr'] / 2.5)
+            # prefer variants with the same basename as the master playlist to avoid partial streams
+            f['format_id'] = url_basename(f['url']).partition('.')[0]
+            if not f['format_id'].startswith(url_basename(f['manifest_url']).partition('.')[0]):
+                f['preference'] = -10
+
         return {
             'id': video_id,
-            'formats': self._get_formats(hls_info, ('hls', 'urls', ..., {url_or_none}), video_id),
+            'formats': formats,
             'hls_aes': self._extract_hls_key(hls_info, 'hls', decrypt),
             **traverse_obj(video_info, {
                 'title': ('displayName', {str}),

yt_dlp/extractor/telecinco.py

@@ -63,6 +63,17 @@ class TelecincoBaseIE(InfoExtractor):
             'http_headers': headers,
         }
 
+    def _download_akamai_webpage(self, url, display_id):
+        try:  # yt-dlp's default user-agents are too old and blocked by akamai
+            return self._download_webpage(url, display_id, headers={
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
+            })
+        except ExtractorError as e:
+            if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
+                raise
+            # Retry with impersonation if hardcoded UA is insufficient to bypass akamai
+            return self._download_webpage(url, display_id, impersonate=True)
+
 
 class TelecincoIE(TelecincoBaseIE):
     IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
@@ -140,7 +151,7 @@ class TelecincoIE(TelecincoBaseIE):
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
+        webpage = self._download_akamai_webpage(url, display_id)
         article = self._search_json(
             r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=',
             webpage, 'article', display_id)['article']

yt_dlp/extractor/youtube/_base.py

@@ -175,6 +175,15 @@ INNERTUBE_CLIENTS = {
         'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
         'SUPPORTS_COOKIES': True,
     },
+    'tv_simply': {
+        'INNERTUBE_CONTEXT': {
+            'client': {
+                'clientName': 'TVHTML5_SIMPLY',
+                'clientVersion': '1.0',
+            },
+        },
+        'INNERTUBE_CONTEXT_CLIENT_NAME': 75,
+    },
     # This client now requires sign-in for every video
     # It was previously an age-gate workaround for videos that were `playable_in_embed`
     # It may still be useful if signed into an EU account that is not age-verified

yt_dlp/extractor/youtube/_video.py

@@ -250,7 +250,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
         '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
     }
-    _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
+    _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'srt', 'vtt')
     _DEFAULT_CLIENTS = ('tv', 'ios', 'web')
     _DEFAULT_AUTHED_CLIENTS = ('tv', 'web')
 

yt_dlp/extractor/youtube/pot/utils.py

@@ -20,6 +20,7 @@ WEBPO_CLIENTS = (
     'WEB_EMBEDDED_PLAYER',
     'WEB_CREATOR',
     'WEB_REMIX',
+    'TVHTML5_SIMPLY',
     'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
 )