From 9941ceb33146e4552cf7a1008c36e5858660605d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Fri, 5 Jul 2013 12:56:41 +0200 Subject: [PATCH] ArteTVIE: support emission urls that don't contain the video id Like http://www.arte.tv/guide/fr/emissions/AJT/arte-journal --- youtube_dl/extractor/arte.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 14725276d..f52672490 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -77,7 +77,12 @@ class ArteTvIE(InfoExtractor): def _extract_emission(self, url, video_id, lang): """Extract from www.arte.tv/guide""" - json_url = 'http://org-www.arte.tv/papi/tvguide/videos/stream/player/F/%s_PLUS7-F/ALL/ALL.json' % video_id + if video_id.replace('-','').isdigit(): + json_url = 'http://org-www.arte.tv/papi/tvguide/videos/stream/player/F/%s_PLUS7-F/ALL/ALL.json' % video_id + else: + # We don't know the real id of the video, we have to search in the webpage + webpage = self._download_webpage(url, video_id) + json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url') json_info = self._download_webpage(json_url, video_id, 'Downloading info json') self.report_extraction(video_id)