From 2415e66f889f38503b73e8ebc5f43ca342390e5c Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Mon, 15 Apr 2024 18:49:24 +0200 Subject: Adding upstream version 2024.03.10. Signed-off-by: Daniel Baumann --- yt_dlp/extractor/lemonde.py | 56 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 yt_dlp/extractor/lemonde.py (limited to 'yt_dlp/extractor/lemonde.py') diff --git a/yt_dlp/extractor/lemonde.py b/yt_dlp/extractor/lemonde.py new file mode 100644 index 0000000..c916791 --- /dev/null +++ b/yt_dlp/extractor/lemonde.py @@ -0,0 +1,56 @@ +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': 'da120c8722d8632eec6ced937536cc98', + 'info_dict': { + 'id': 'lqm3kl', + 'ext': 'mp4', + 'title': "Comprendre l'affaire Bygmalion en 5 minutes", + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 309, + 'upload_date': '20160119', + 'timestamp': 1453194778, + 'uploader_id': '3pmkp', + }, + }, { + # standard iframe embed + 'url': 'http://www.lemonde.fr/les-decodeurs/article/2016/10/18/tout-comprendre-du-ceta-le-petit-cousin-du-traite-transatlantique_5015920_4355770.html', + 'info_dict': { + 'id': 'uzsxms', + 'ext': 'mp4', + 'title': "CETA : quelles suites pour l'accord commercial entre l'Europe et le Canada ?", + 'thumbnail': r're:^https?://.*\.jpg', + 'duration': 325, + 'upload_date': '20161021', + 'timestamp': 1477044540, + 'uploader_id': '3pmkp', + }, + 'params': { + 'skip_download': True, + }, + }, { + '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, + }, { + # YouTube embeds + 'url': 'http://www.lemonde.fr/pixels/article/2016/12/09/pourquoi-pewdiepie-superstar-de-youtube-a-menace-de-fermer-sa-chaine_5046649_4408996.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', default=None)) + + if digiteka_url: + return self.url_result(digiteka_url, 'Digiteka') + + return self.url_result(url, 'Generic') -- cgit v1.2.3