"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?:http://)?vimeo\.com/([0-9]+)'
+ _VALID_URL = r'(?:http://)?(?:(?:www|player).)?vimeo\.com/(?:video/)?([0-9]+)'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err))
return
- # Extract uploader and title from webpage
+ # Now we begin extracting as much information as we can from what we
+ # retrieved. First we extract the information common to all extractors,
+ # and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
+
+ # Extract title
mobj = re.search(r'<caption>(.*?)</caption>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
video_title = mobj.group(1).decode('utf-8')
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+ # Extract uploader
mobj = re.search(r'<uploader_url>http://vimeo.com/(.*?)</uploader_url>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video uploader')
# if not video_description: video_description = 'No description available.'
video_description = 'Foo.'
- # Extract request signature
+ # Vimeo specific: extract request signature
mobj = re.search(r'<request_signature>(.*?)</request_signature>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract request signature')
return
sig = mobj.group(1).decode('utf-8')
- # Extract request signature expiration
+ # Vimeo specific: Extract request signature expiration
mobj = re.search(r'<request_signature_expires>(.*?)</request_signature_expires>', webpage)
if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract request signature expiration')