jcgruenhage/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[generic] Add support for jwPlayer YouTube videos

Browse source 
This makes nationalarchives.gov.uk work (Fixes #4907, fixes #4876)
This commit is contained in:
Philipp Hagemeister 2015-02-09 10:42:25 +01:00
parent dd8930684e
commit a0f7198544
1 changed files with 17 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
youtube_dl/extractor/generic.py
View file

@ -524,6 +524,19 @@ class GenericIE(InfoExtractor):
'upload_date': '20150126', 'upload_date': '20150126',
}, },
'add_ie': ['Viddler'], 'add_ie': ['Viddler'],
},
# jwplayer YouTube
{
'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
'info_dict': {
'id': 'Mrj4DVp2zeA',
'ext': 'mp4',
'upload_date': '20150204',
'uploader': 'The National Archives UK',
'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
'uploader_id': 'NationalArchives08',
'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
},
} }
] ]
@ -1065,6 +1078,8 @@ class GenericIE(InfoExtractor):
return self.url_result(mobj.group('url'), 'Livestream') return self.url_result(mobj.group('url'), 'Livestream')
def check_video(vurl): def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True
vpath = compat_urlparse.urlparse(vurl).path vpath = compat_urlparse.urlparse(vurl).path
vext = determine_ext(vpath) vext = determine_ext(vpath)
return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml') return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
@ -1082,7 +1097,8 @@ class GenericIE(InfoExtractor):
JWPlayerOptions| JWPlayerOptions|
jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
) )
.*?file\s*:\s*["\'](.*?)["\']''', webpage)) .*?
['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
if not found: if not found:
# Broaden the search a little bit # Broaden the search a little bit
found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)) found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))