get_element_by_attribute,
ExtractorError,
std_headers,
+ unsmuggle_url,
)
class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
- _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)(?:[?].*)?$'
+ _VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)/?(?:[?].*)?$'
_NETRC_MACHINE = 'vimeo'
IE_NAME = u'vimeo'
_TESTS = [
u'title': u'Kathy Sierra: Building the minimum Badass User, Business of Software',
u'uploader': u'The BLN & Business of Software',
},
- },
+ }
]
def _login(self):
self._login()
def _real_extract(self, url, new_video=True):
+ url, data = unsmuggle_url(url)
+ headers = std_headers
+ if data is not None:
+ headers = headers.copy()
+ headers.update(data)
+
# Extract ID from URL
mobj = re.match(self._VALID_URL, url)
if mobj is None:
url = 'https://vimeo.com/' + video_id
# Retrieve video webpage to extract further information
- request = compat_urllib_request.Request(url, None, std_headers)
+ request = compat_urllib_request.Request(url, None, headers)
webpage = self._download_webpage(request, video_id)
# Now we begin extracting as much information as we can from what we
_, video_thumbnail = sorted((int(width), t_url) for (width, t_url) in config["video"]["thumbs"].items())[-1]
# Extract video description
- video_description = get_element_by_attribute("itemprop", "description", webpage)
- if video_description: video_description = clean_html(video_description)
- else: video_description = u''
+ video_description = None
+ try:
+ video_description = get_element_by_attribute("itemprop", "description", webpage)
+ if video_description: video_description = clean_html(video_description)
+ except AssertionError as err:
+ # On some pages like (http://player.vimeo.com/video/54469442) the
+ # html tags are not closed, python 2.6 cannot handle it
+ if err.args[0] == 'we should not get here!':
+ pass
+ else:
+ raise
# Extract upload date
video_upload_date = None