aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/youtube.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2017-03-25 01:17:17 +0700
committerSergey M․ <dstftw@gmail.com>2017-03-25 01:18:33 +0700
commitd0ba55871e6754fdc8a6a28543581989ba3c50fe (patch)
treecf540afff489a32a8c14a26c5465a5f29c969307 /youtube_dl/extractor/youtube.py
parent54b960f340ed5398136ef0206d17cafba2575678 (diff)
downloadyoutube-dl-d0ba55871e6754fdc8a6a28543581989ba3c50fe.tar.xz
[youtube] Improve _VALID_URLs (closes #12538)
Diffstat (limited to 'youtube_dl/extractor/youtube.py')
-rw-r--r--youtube_dl/extractor/youtube.py19
1 files changed, 15 insertions, 4 deletions
diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index caa048249..ca40de522 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -59,6 +59,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
# If True it will raise an error if no login info is provided
_LOGIN_REQUIRED = False
+ _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,}'
+
def _set_language(self):
self._set_cookie(
'.youtube.com', 'PREF', 'f1=50000000&hl=en',
@@ -265,9 +267,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
)
)? # all until now is optional -> you can pass the naked ID
([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
- (?!.*?\blist=) # combined list/video URLs are handled by the playlist IE
+ (?!.*?\blist=
+ (?:
+ %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
+ WL # WL are handled by the watch later IE
+ )
+ )
(?(1).+)? # if we found the ID, everything can follow
- $"""
+ $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
_NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
_formats = {
'5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
@@ -924,6 +931,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': 'sJL6WA-aGkQ',
'only_matching': True,
},
+ {
+ 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
+ 'only_matching': True,
+ },
]
def __init__(self, *args, **kwargs):
@@ -1864,8 +1875,8 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
)
.*
|
- ((?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,})
- )"""
+ (%(playlist_id)s)
+ )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
IE_NAME = 'youtube:playlist'