From 651ad35ce0f0ee9d04db085c50c29441b47bc825 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Sun, 1 May 2016 06:57:19 +0600
Subject: [PATCH] [tagesschau] Relax _VALID_URL
---
youtube_dl/extractor/tagesschau.py | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/youtube_dl/extractor/tagesschau.py b/youtube_dl/extractor/tagesschau.py
index a71fbad7d..f6102c224 100644
--- a/youtube_dl/extractor/tagesschau.py
+++ b/youtube_dl/extractor/tagesschau.py
@@ -125,7 +125,7 @@ class TagesschauPlayerIE(InfoExtractor):
class TagesschauIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/[^/]+/(?:[^/]+/)*?[^/#?]+?(?P<id>-?[0-9]+)(?:~_?[^/#?]+?)?\.html'
+ _VALID_URL = r'https?://(?:www\.)?tagesschau\.de/(?P<path>[^/]+/(?:[^/]+/)*?[^/#?]+?(?P<id>-?[0-9]+)?)(?:~_?[^/#?]+?)?\.html'
_TESTS = [{
'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html',
@@ -197,6 +197,9 @@ class TagesschauIE(InfoExtractor):
}, {
'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html',
'only_matching': True,
+ }, {
+ 'url': 'http://www.tagesschau.de/100sekunden/index.html',
+ 'only_matching': True,
}]
@classmethod
@@ -256,7 +259,8 @@ class TagesschauIE(InfoExtractor):
return formats
def _real_extract(self, url):
- video_id = self._match_id(url)
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id') or mobj.group('path')
display_id = video_id.lstrip('-')
webpage = self._download_webpage(url, display_id)