summary |
shortlog |
log |
commit | commitdiff |
tree
raw |
patch |
inline | side by side (from parent 1:
58e7d46)
These are attribute values, so we don't need the more complex and whitespace-destroying cleanHTML - we just need to unescape quotes, that's it.
clean_html,
compiled_regex_type,
ExtractorError,
clean_html,
compiled_regex_type,
ExtractorError,
)
class InfoExtractor(object):
)
class InfoExtractor(object):
def _og_search_property(self, prop, html, name=None, **kargs):
if name is None:
name = 'OpenGraph %s' % prop
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)
def _og_search_thumbnail(self, html, **kargs):
return self._og_search_property('image', html, u'thumbnail url', fatal=False, **kargs)