From f8514f618607a23d7307d5faa287299b6c907030 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 4 Apr 2014 23:13:52 +0200 Subject: [PATCH] [rts] Use visible id in file names Maybe the internal ID is more precise, but it's totally confusing, and the obvious ID still allows a google search. --- youtube_dl/extractor/rts.py | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py index 40224d761..0f85b2320 100644 --- a/youtube_dl/extractor/rts.py +++ b/youtube_dl/extractor/rts.py @@ -37,7 +37,7 @@ class RTSIE(InfoExtractor): 'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html', 'md5': 'c197f0b2421995c63a64cc73d800f42e', 'info_dict': { - 'id': '5738317', + 'id': '5624067', 'ext': 'mp4', 'duration': 55, 'title': 'Bande de lancement de Passe-moi les jumelles', @@ -98,17 +98,20 @@ def _real_extract(self, url): m = re.match(self._VALID_URL, url) video_id = m.group('id') - def download_json(video_id): + def download_json(internal_id): return self._download_json( - 'http://www.rts.ch/a/%s.html?f=json/article' % video_id, video_id) + 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id, + video_id) all_info = download_json(video_id) # video_id extracted out of URL is not always a real id if 'video' not in all_info and 'audio' not in all_info: page = self._download_webpage(url, video_id) - video_id = self._html_search_regex(r'<(?:video|audio) data-id="(\d+)"', page, 'video id') - all_info = download_json(video_id) + internal_id = self._html_search_regex( + r'<(?:video|audio) data-id="([0-9]+)"', page, + 'internal video id') + all_info = download_json(internal_id) info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']