From 69b2f838d3d3e37dc17367ef64d978db1bea45cf Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 23 Mar 2023 11:19:37 -0500 Subject: [PATCH] [extractor/telecaribe] Expand livestream support (#6601) Closes #6598 Authored by: bashonly --- yt_dlp/extractor/telecaribe.py | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/yt_dlp/extractor/telecaribe.py b/yt_dlp/extractor/telecaribe.py index b6d88a8090..91118a1a4a 100644 --- a/yt_dlp/extractor/telecaribe.py +++ b/yt_dlp/extractor/telecaribe.py @@ -38,11 +38,23 @@ class TelecaribePlayIE(InfoExtractor): 'params': { 'skip_download': 'Livestream', } + }, { + 'url': 'https://www.play.telecaribe.co/liveplus', + 'info_dict': { + 'id': 'liveplus', + 'title': r're:^SeƱal en vivo Plus', + 'live_status': 'is_live', + 'ext': 'mp4', + }, + 'params': { + 'skip_download': 'Livestream', + }, + 'skip': 'Geo-restricted to Colombia', }] def _download_player_webpage(self, webpage, display_id): page_id = self._search_regex( - (r'window.firstPageId\s*=\s*["\']([^"\']+)', r']+id\s*=\s*"pageBackground_([^"]+)'), + (r'window\.firstPageId\s*=\s*["\']([^"\']+)', r']+id\s*=\s*"pageBackground_([^"]+)'), webpage, 'page_id') props = self._download_json(self._search_regex( @@ -59,14 +71,16 @@ class TelecaribePlayIE(InfoExtractor): webpage = self._download_webpage(url, display_id) player = self._download_player_webpage(webpage, display_id) - if display_id != 'live': + livestream_url = self._search_regex( + r'(?:let|const|var)\s+source\s*=\s*["\']([^"\']+)', player, 'm3u8 url', default=None) + + if not livestream_url: return self.playlist_from_matches( re.findall(r']+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') + livestream_url, display_id, 'mp4', live=True) return { 'id': display_id,