From 04988b55b54bd7bd803d43a56f87e4728158890a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 17 Mar 2019 15:34:21 +0700 Subject: [PATCH] [openload] Improve embed detection --- youtube_dl/extractor/openload.py | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index bae7c7ee71..cc323e5e21 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -243,18 +243,16 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): + _DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space))' _VALID_URL = r'''(?x) https?:// (?P (?:www\.)? - (?: - openload\.(?:co|io|link|pw)| - oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live|space) - ) + %s )/ (?:f|embed)/ (?P[a-zA-Z0-9-_]+) - ''' + ''' % _DOMAINS _TESTS = [{ 'url': 'https://openload.co/f/kUEfGclsU9o', @@ -359,8 +357,8 @@ class OpenloadIE(InfoExtractor): @staticmethod def _extract_urls(webpage): return re.findall( - r']+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)', - webpage) + r']+src=["\']((?:https?://)?%s/embed/[a-zA-Z0-9-_]+)' + % OpenloadIE._DOMAINS, webpage) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url)