clean_html,
compiled_regex_type,
ExtractorError,
+ unescapeHTML,
)
class InfoExtractor(object):
@classmethod
def suitable(cls, url):
"""Receives a URL and returns True if suitable for this IE."""
- return re.match(cls._VALID_URL, url) is not None
+
+ # This does not use has/getattr intentionally - we want to know whether
+ # we have cached the regexp for *this* class, whereas getattr would also
+ # match the superclass
+ if '_VALID_URL_RE' not in cls.__dict__:
+ cls._VALID_URL_RE = re.compile(cls._VALID_URL)
+ return cls._VALID_URL_RE.match(url) is not None
@classmethod
def working(cls):
def _og_search_property(self, prop, html, name=None, **kargs):
if name is None:
name = 'OpenGraph %s' % prop
- return self._html_search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+ escaped = self._search_regex(self._og_regex(prop), html, name, flags=re.DOTALL, **kargs)
+ return unescapeHTML(escaped)
def _og_search_thumbnail(self, html, **kargs):
return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)