From b605ebb609dc208a814ab44fff84463bf0c5369a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 19 Jan 2016 22:09:55 +0600 Subject: [PATCH] [lemonde] Add extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/lemonde.py | 34 ++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) create mode 100644 youtube_dl/extractor/lemonde.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 1d838cdd0..0cc339a37 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -333,6 +333,7 @@ from .la7 import LA7IE from .laola1tv import Laola1TvIE from .lecture2go import Lecture2GoIE +from .lemonde import LemondeIE from .letv import ( LetvIE, LetvTvIE, diff --git a/youtube_dl/extractor/lemonde.py b/youtube_dl/extractor/lemonde.py new file mode 100644 index 000000000..be66fff03 --- /dev/null +++ b/youtube_dl/extractor/lemonde.py @@ -0,0 +1,34 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class LemondeIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?lemonde\.fr/(?:[^/]+/)*(?P[^/]+)\.html' + _TESTS = [{ + 'url': 'http://www.lemonde.fr/police-justice/video/2016/01/19/comprendre-l-affaire-bygmalion-en-cinq-minutes_4849702_1653578.html', + 'md5': '01fb3c92de4c12c573343d63e163d302', + 'info_dict': { + 'id': 'lqm3kl', + 'ext': 'mp4', + 'title': "Comprendre l'affaire Bygmalion en 5 minutes", + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 320, + 'upload_date': '20160119', + 'timestamp': 1453194778, + 'uploader_id': '3pmkp', + }, + }, { + 'url': 'http://redaction.actu.lemonde.fr/societe/video/2016/01/18/calais-debut-des-travaux-de-defrichement-dans-la-jungle_4849233_3224.html', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + digiteka_url = self._proto_relative_url(self._search_regex( + r'url\s*:\s*(["\'])(?P(?:https?://)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/.+?)\1', + webpage, 'digiteka url', group='url')) + return self.url_result(digiteka_url, 'Digiteka')