From: Remita Amine Date: Sat, 25 Nov 2017 14:49:49 +0000 (+0100) Subject: [france2.fr:generation-what] fix extraction X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=6f5c598a28b2b400ffb4d2bc2d228c2802ab7fd7;p=youtube-dl [france2.fr:generation-what] fix extraction --- diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 037e538cc..5a3abeaff 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -3,7 +3,6 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..compat import compat_urlparse @@ -308,31 +307,32 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor): return self._extract_video(video_id, catalogue) -class GenerationQuoiIE(InfoExtractor): - IE_NAME = 'france2.fr:generation-quoi' - _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P[^/?#]+)' +class GenerationWhatIE(InfoExtractor): + IE_NAME = 'france2.fr:generation-what' + _VALID_URL = r'https?://generation-what\.francetv\.fr/[^/]+/video/(?P[^/?#]+)' - _TEST = { - 'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous', + _TESTS = [{ + 'url': 'http://generation-what.francetv.fr/portrait/video/present-arms', 'info_dict': { - 'id': 'k7FJX8VBcvvLmX4wA5Q', + 'id': 'wtvKYUG45iw', 'ext': 'mp4', - 'title': 'Génération Quoi - Garde à Vous', - 'uploader': 'Génération Quoi', - }, - 'params': { - # It uses Dailymotion - 'skip_download': True, + 'title': 'Generation What - Garde à vous - FRA', + 'uploader': 'Generation What', + 'uploader_id': 'UCHH9p1eetWCgt4kXBYCb3_w', + 'upload_date': '20160411', }, - } + }, { + 'url': 'http://generation-what.francetv.fr/europe/video/present-arms', + 'only_matching': True, + }] def _real_extract(self, url): display_id = self._match_id(url) - info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id) - info_json = self._download_webpage(info_url, display_id) - info = json.loads(info_json) - return self.url_result('http://www.dailymotion.com/video/%s' % info['id'], - ie='Dailymotion') + webpage = self._download_webpage(url, display_id) + youtube_id = self._search_regex( + r"window\.videoURL\s*=\s*'([0-9A-Za-z_-]{11})';", + webpage, 'youtube id') + return self.url_result(youtube_id, 'Youtube', youtube_id) class CultureboxIE(FranceTVBaseInfoExtractor):