X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ffranceculture.py;h=e2ca962838932f682f0ac833bd64169ccaba8fc5;hb=f745403b5b448c170710256a61b8505e09e77674;hp=2ac6157cdecd2a0ea565f6d9528d8552aca22164;hpb=7447661e9b433d8871d0a898c9af271d5a49ec82;p=youtube-dl diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index 2ac6157cd..e2ca96283 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -8,6 +8,7 @@ from ..compat import ( from ..utils import ( determine_ext, int_or_none, + ExtractorError, ) @@ -28,8 +29,7 @@ class FranceCultureIE(InfoExtractor): } } - def _real_extract(self, url): - video_id = self._match_id(url) + def _extract_from_player(self, url, video_id): webpage = self._download_webpage(url, video_id) video_path = self._search_regex( @@ -42,6 +42,9 @@ class FranceCultureIE(InfoExtractor): r'\s+emission-(.*?)', webpage, 'display_id') + title = self._html_search_regex( r'(.*?)', webpage, 'title') alt_title = self._html_search_regex( @@ -66,4 +69,37 @@ class FranceCultureIE(InfoExtractor): 'alt_title': alt_title, 'thumbnail': thumbnail, 'description': description, + 'display_id': display_id, } + + def _real_extract(self, url): + video_id = self._match_id(url) + return self._extract_from_player(url, video_id) + + +class FranceCultureEmissionIE(FranceCultureIE): + _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P[^?#]+)' + _TEST = { + 'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13', + 'info_dict': { + 'title': 'Jean-Gabriel Périot, cinéaste', + 'alt_title': 'Les Carnets de la création', + 'id': '5093239', + 'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13', + 'ext': 'mp3', + 'timestamp': 1444762500, + 'upload_date': '20151013', + 'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + video_path = self._html_search_regex( + r'[0-9]+)', video_path, 'new_id', group='id') + video_url = compat_urlparse.urljoin(url, video_path) + return self._extract_from_player(video_url, new_id)