}],
},
},
+ 'skip': 'Gone. Maybe https://www.safaribooksonline.com/library/tutorials/introduction-to-python-anon/3469/',
'params': {
'skip_download': True,
},
@staticmethod
def _extract_url(webpage):
+ # Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
mobj = (
re.search(
r"""(?xs)
kWidget\.(?:thumb)?[Ee]mbed\(
\{.*?
- (?P<q1>['\"])wid(?P=q1)\s*:\s*
- (?P<q2>['\"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
- (?P<q3>['\"])entry_?[Ii]d(?P=q3)\s*:\s*
- (?P<q4>['\"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
+ (?P<q1>['"])wid(?P=q1)\s*:\s*
+ (?P<q2>['"])_?(?P<partner_id>(?:(?!(?P=q2)).)+)(?P=q2),.*?
+ (?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
+ (?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
""", webpage) or
re.search(
r'''(?xs)
- (?P<q1>["\'])
+ (?P<q1>["'])
(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
(?P=q1).*?
(?:
- entry_?[Ii]d|
- (?P<q2>["\'])entry_?[Ii]d(?P=q2)
- )\s*:\s*
- (?P<q3>["\'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
- ''', webpage))
+ (?:
+ entry_?[Ii]d|
+ (?P<q2>["'])entry_?[Ii]d(?P=q2)
+ )\s*:\s*|
+ \[\s*(?P<q2_1>["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s*
+ )
+ (?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
+ ''', webpage) or
+ re.search(
+ r'''(?xs)
+ <(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
+ (?:https?:)?//(?:(?:www|cdnapi)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
+ (?:(?!(?P=q1)).)*
+ [?&;]entry_id=(?P<id>(?:(?!(?P=q1))[^&])+)
+ (?P=q1)
+ ''', webpage)
+ )
if mobj:
embed_info = mobj.groupdict()
url = 'kaltura:%(partner_id)s:%(id)s' % embed_info
# skip for now.
if f.get('fileExt') == 'chun':
continue
+ # DRM-protected video, cannot be decrypted
+ if f.get('fileExt') == 'wvm':
+ continue
if not f.get('fileExt'):
# QT indicates QuickTime; some videos have broken fileExt
if f.get('containerFormat') == 'qt':
if captions:
for caption in captions.get('objects', []):
# Continue if caption is not ready
- if f.get('status') != 2:
+ if caption.get('status') != 2:
continue
if not caption.get('id'):
continue