[vimeo] Fix pro videos and player.vimeo.com urls

The old process can still be used for those videos.
Added RegexNotFoundError, which is raised by _search_regex if it can't extract the info.
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-10-23 14:38:03 +02:00
parent 365bcf6d97
commit 55b3e45bba
3 changed files with 14 additions and 2 deletions

View file

@ -14,6 +14,7 @@
clean_html,
compiled_regex_type,
ExtractorError,
RegexNotFoundError,
unescapeHTML,
)
@ -231,7 +232,7 @@ def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0
Perform a regex search on the given string, using a single or a list of
patterns returning the first matching group.
In case of failure return a default value or raise a WARNING or a
ExtractorError, depending on fatal, specifying the field name.
RegexNotFoundError, depending on fatal, specifying the field name.
"""
if isinstance(pattern, (str, compat_str, compiled_regex_type)):
mobj = re.search(pattern, string, flags)
@ -251,7 +252,7 @@ def _search_regex(self, pattern, string, name, default=None, fatal=True, flags=0
elif default is not None:
return default
elif fatal:
raise ExtractorError(u'Unable to extract %s' % _name)
raise RegexNotFoundError(u'Unable to extract %s' % _name)
else:
self._downloader.report_warning(u'unable to extract %s; '
u'please report this issue on http://yt-dl.org/bug' % _name)

View file

@ -10,6 +10,7 @@
clean_html,
get_element_by_attribute,
ExtractorError,
RegexNotFoundError,
std_headers,
unsmuggle_url,
)
@ -133,6 +134,11 @@ def _real_extract(self, url, new_video=True):
r' data-config-url="(.+?)"', webpage, u'config URL')
config_json = self._download_webpage(config_url, video_id)
config = json.loads(config_json)
except RegexNotFoundError:
# For pro videos or player.vimeo.com urls
config = self._search_regex([r' = {config:({.+?}),assets:', r'c=({.+?);'],
webpage, u'info section', flags=re.DOTALL)
config = json.loads(config)
except Exception as e:
if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
raise ExtractorError(u'The author has restricted the access to this video, try with the "--referer" option')

View file

@ -572,6 +572,11 @@ def format_traceback(self):
return u''.join(traceback.format_tb(self.traceback))
class RegexNotFoundError(ExtractorError):
"""Error when a regex didn't match"""
pass
class DownloadError(Exception):
"""Download Error exception.