X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a6abd8dc822fb70852437ab5a77ced5f633739f8..2b4515201a54c38e34434ea2817d606be134a7c9:/youtube_dl/extractor/franceculture.py diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py index 1e83a4e..b98da69 100644 --- a/youtube_dl/extractor/franceculture.py +++ b/youtube_dl/extractor/franceculture.py @@ -2,68 +2,56 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import ( - compat_urlparse, -) from ..utils import ( determine_ext, - int_or_none, + unified_strdate, ) class FranceCultureIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P[^/?#&]+)' _TEST = { - 'url': 'http://www.franceculture.fr/player/reecouter?play=4795174', + 'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks', 'info_dict': { - 'id': '4795174', + 'id': 'rendez-vous-au-pays-des-geeks', + 'display_id': 'rendez-vous-au-pays-des-geeks', 'ext': 'mp3', 'title': 'Rendez-vous au pays des geeks', - 'alt_title': 'Carnet nomade | 13-14', - 'vcodec': 'none', + 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20140301', - 'thumbnail': r're:^http://www\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$', - 'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche des « geeks », une enquête menée aux Etats', - 'timestamp': 1393700400, + 'vcodec': 'none', } } def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_url = self._search_regex( + r'(?s)]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?]+data-asset-source="([^"]+)"', + webpage, 'video path') + + title = self._og_search_title(webpage) - video_path = self._search_regex( - r']+class="date"[^>]*>.*?]+class="inner"[^>]*>([^<]+)<', webpage, 'upload date', fatal=False)) thumbnail = self._search_regex( - r'\s+]+itemtype="https://schema.org/ImageObject"[^>]*>.*?]+data-dejavu-src="([^"]+)"', webpage, 'thumbnail', fatal=False) - - title = self._html_search_regex( - r'(.*?)', webpage, 'title') - alt_title = self._html_search_regex( - r'(.*?)', - webpage, 'alt_title', fatal=False) - description = self._html_search_regex( - r'(.*?)', - webpage, 'description', fatal=False) - uploader = self._html_search_regex( r'(?s)
(.*?)', webpage, 'uploader', default=None) vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None return { - 'id': video_id, + 'id': display_id, + 'display_id': display_id, 'url': video_url, - 'vcodec': vcodec, - 'uploader': uploader, - 'timestamp': timestamp, 'title': title, - 'alt_title': alt_title, 'thumbnail': thumbnail, - 'description': description, + 'vcodec': vcodec, + 'uploader': uploader, + 'upload_date': upload_date, }