[lemonde] Fallback delegate extraction to generic extractor (closes #12115, closes #12116)

pull/12088/merge
Sergey M․ 2017-02-13 23:17:48 +07:00
parent 50fd3c2c69
commit 6e5956e6ba
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 28 additions and 4 deletions

View File

@ -7,20 +7,40 @@ class LemondeIE(InfoExtractor):
_VALID_URL = r'https?://(?:.+?\.)?lemonde\.fr/(?:[^/]+/)*(?P<id>[^/]+)\.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',
'md5': 'da120c8722d8632eec6ced937536cc98',
'info_dict': {
'id': 'lqm3kl',
'ext': 'mp4',
'title': "Comprendre l'affaire Bygmalion en 5 minutes",
'thumbnail': r're:^https?://.*\.jpg',
'duration': 320,
'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):
@ -30,5 +50,9 @@ class LemondeIE(InfoExtractor):
digiteka_url = self._proto_relative_url(self._search_regex(
r'url\s*:\s*(["\'])(?P<url>(?:https?://)?//(?:www\.)?(?:digiteka\.net|ultimedia\.com)/deliver/.+?)\1',
webpage, 'digiteka url', group='url'))
return self.url_result(digiteka_url, 'Digiteka')
webpage, 'digiteka url', group='url', default=None))
if digiteka_url:
return self.url_result(digiteka_url, 'Digiteka')
return self.url_result(url, 'Generic')