kumi/yt-dlp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[rmcdecouverte] Generalize _VALID_URL

Browse source 
Closes #291
This commit is contained in:
pukkandan 2021-05-11 18:23:38 +05:30
parent 4171221823
commit d8ec40b39f
No known key found for this signature in database
GPG key ID: 0F00D95A001F4698
1 changed files with 9 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
yt_dlp/extractor/rmcdecouverte.py
View file

@ -13,7 +13,7 @@ from ..utils import smuggle_url
class RMCDecouverteIE(InfoExtractor): class RMCDecouverteIE(InfoExtractor):
_VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/(?:[^/]+/(?P<id>[^?#/]+)|(?P<live_id>mediaplayer-direct))' _VALID_URL = r'https?://rmcdecouverte\.bfmtv\.com/(?:[^?#]*_(?P<id>\d+)|mediaplayer-direct)/?(?:[#?]|$)'
_TESTS = [{ _TESTS = [{
'url': 'https://rmcdecouverte.bfmtv.com/vestiges-de-guerre_22240/les-bunkers-secrets-domaha-beach_25303/', 'url': 'https://rmcdecouverte.bfmtv.com/vestiges-de-guerre_22240/les-bunkers-secrets-domaha-beach_25303/',
@ -45,6 +45,13 @@ class RMCDecouverteIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
'skip': 'only available for a week', 'skip': 'only available for a week',
}, {
'url': 'https://rmcdecouverte.bfmtv.com/avions-furtifs-la-technologie-de-lextreme_10598',
'only_matching': True,
},{
# The website accepts any URL as long as it has _\d+ at the end
'url': 'https://rmcdecouverte.bfmtv.com/any/thing/can/go/here/_10598',
'only_matching': True,
}, { }, {
# live, geo restricted, bypassable # live, geo restricted, bypassable
'url': 'https://rmcdecouverte.bfmtv.com/mediaplayer-direct/', 'url': 'https://rmcdecouverte.bfmtv.com/mediaplayer-direct/',
@ -54,7 +61,7 @@ class RMCDecouverteIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id') or mobj.group('live_id') display_id = mobj.group('id') or 'direct'
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
if brightcove_legacy_url: if brightcove_legacy_url: