[extractor/telecaribe] Add extractor (#6311)

Authored by: elyse0
Closes #6001

yt_dlp/extractor/_extractors.py

@@ -1854,6 +1854,7 @@ from .ted import (
 from .tele5 import Tele5IE
 from .tele13 import Tele13IE
 from .telebruxelles import TeleBruxellesIE
+from .telecaribe import TelecaribePlayIE
 from .telecinco import TelecincoIE
 from .telegraaf import TelegraafIE
 from .telegram import TelegramEmbedIE

yt_dlp/extractor/telecaribe.py

@@ -0,0 +1,77 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import traverse_obj
+
+
+class TelecaribePlayIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?play\.telecaribe\.co/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.play.telecaribe.co/breicok',
+        'info_dict': {
+            'id': 'breicok',
+            'title': 'Breicok',
+        },
+        'playlist_count': 7,
+    }, {
+        'url': 'https://www.play.telecaribe.co/si-fue-gol-de-yepes',
+        'info_dict': {
+            'id': 'si-fue-gol-de-yepes',
+            'title': 'Sí Fue Gol de Yepes',
+        },
+        'playlist_count': 6,
+    }, {
+        'url': 'https://www.play.telecaribe.co/ciudad-futura',
+        'info_dict': {
+            'id': 'ciudad-futura',
+            'title': 'Ciudad Futura',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.play.telecaribe.co/live',
+        'info_dict': {
+            'id': 'live',
+            'title': r're:^Señal en vivo',
+            'live_status': 'is_live',
+            'ext': 'mp4',
+        },
+        'params': {
+            'skip_download': 'Livestream',
+        }
+    }]
+
+    def _download_player_webpage(self, webpage, display_id):
+        page_id = self._search_regex(
+            (r'window.firstPageId\s*=\s*["\']([^"\']+)', r'<div[^>]+id\s*=\s*"pageBackground_([^"]+)'),
+            webpage, 'page_id')
+
+        props = self._download_json(self._search_regex(
+            rf'<link[^>]+href\s*=\s*"([^"]+)"[^>]+id\s*=\s*"features_{page_id}"',
+            webpage, 'json_props_url'), display_id)['props']['render']['compProps']
+
+        return self._download_webpage(traverse_obj(props, (..., 'url'))[-1], display_id)
+
+    def _get_clean_title(self, title):
+        return re.sub(r'\s*\|\s*Telecaribe\s*VOD', '', title or '').strip() or None
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        player = self._download_player_webpage(webpage, display_id)
+
+        if display_id != 'live':
+            return self.playlist_from_matches(
+                re.findall(r'<a[^>]+href\s*=\s*"([^"]+\.mp4)', player), display_id,
+                self._get_clean_title(self._og_search_title(webpage)))
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            self._search_regex(r'(?:let|const|var)\s+source\s*=\s*["\']([^"\']+)', player, 'm3u8 url'),
+            display_id, 'mp4')
+
+        return {
+            'id': display_id,
+            'title': self._get_clean_title(self._og_search_title(webpage)),
+            'formats': formats,
+            'subtitles': subtitles,
+            'is_live': True,
+        }