From 0e0508c8a24f5882fefea37e91ac03921fb967e9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Mon, 5 Feb 2018 23:55:18 +0700
Subject: [PATCH] [telebruxelles] Relax _VALID_URL and add support for live
streams
---
youtube_dl/extractor/telebruxelles.py | 22 +++++++++++++++++++---
1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/youtube_dl/extractor/telebruxelles.py b/youtube_dl/extractor/telebruxelles.py
index 8c7465d06..a0353fe3a 100644
--- a/youtube_dl/extractor/telebruxelles.py
+++ b/youtube_dl/extractor/telebruxelles.py
@@ -7,7 +7,7 @@ from .common import InfoExtractor
class TeleBruxellesIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt|emission)/?(?P<id>[^/#?]+)'
+ _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(?:[^/]+/)*(?P<id>[^/#?]+)'
_TESTS = [{
'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/',
'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9',
@@ -31,6 +31,16 @@ class TeleBruxellesIE(InfoExtractor):
}, {
'url': 'http://bx1.be/emission/bxenf1-gastronomie/',
'only_matching': True,
+ }, {
+ 'url': 'https://bx1.be/berchem-sainte-agathe/personnel-carrefour-de-berchem-sainte-agathe-inquiet/',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://bx1.be/dernier-jt/',
+ 'only_matching': True,
+ }, {
+ # live stream
+ 'url': 'https://bx1.be/lives/direct-tv/',
+ 'only_matching': True,
}]
def _real_extract(self, url):
@@ -45,16 +55,22 @@ class TeleBruxellesIE(InfoExtractor):
description = self._og_search_description(webpage, default=None)
rtmp_url = self._html_search_regex(
- r'file\s*:\s*"(rtmps?://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"',
+ r'file["\']?\s*:\s*"(r(?:tm|mt)ps?://[^/]+/(?:vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*"\.mp4|stream/live))"',
webpage, 'RTMP url')
+ # Yes, they have a typo in scheme name for live stream URLs (e.g.
+ # https://bx1.be/lives/direct-tv/)
+ rtmp_url = re.sub(r'^rmtp', 'rtmp', rtmp_url)
rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url)
formats = self._extract_wowza_formats(rtmp_url, article_id or display_id)
self._sort_formats(formats)
+ is_live = 'stream/live' in rtmp_url
+
return {
'id': article_id or display_id,
'display_id': display_id,
- 'title': title,
+ 'title': self._live_title(title) if is_live else title,
'description': description,
'formats': formats,
+ 'is_live': is_live,
}