From da0a5d2d6eb4ed3f511e69d3d6c8814f6aab6535 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 4 Oct 2013 00:31:10 +0200 Subject: [PATCH] [france2] Add support for URLs without video IDs (Fixes #1547) --- youtube_dl/extractor/francetv.py | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index b1530e549..461dac8ef 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -70,7 +70,11 @@ def _real_extract(self, url): class France2IE(FranceTVBaseInfoExtractor): IE_NAME = u'france2.fr' - _VALID_URL = r'https?://www\.france2\.fr/emissions/.*?/videos/(?P\d+)' + _VALID_URL = r'''(?x)https?://www\.france2\.fr/ + (?: + emissions/.*?/videos/(?P\d+) + | emission/(?P[^/?]+) + )''' _TEST = { u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', @@ -86,7 +90,15 @@ class France2IE(FranceTVBaseInfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + if mobj.group('key'): + webpage = self._download_webpage(url, mobj.group('key')) + video_id = self._html_search_regex( + r'''(?x)\s* + ''', + webpage, u'video ID') + else: + video_id = mobj.group('id') return self._extract_video(video_id)