diff options
Diffstat (limited to 'src/lxml/html/clean.py')
| -rw-r--r-- | src/lxml/html/clean.py | 17 |
1 files changed, 15 insertions, 2 deletions
diff --git a/src/lxml/html/clean.py b/src/lxml/html/clean.py index aa9fc57f..da1f8706 100644 --- a/src/lxml/html/clean.py +++ b/src/lxml/html/clean.py @@ -432,6 +432,12 @@ class Cleaner(object): return False def allow_element(self, el): + """ + Decide whether an element is configured to be accepted or rejected. + + :param el: an element. + :return: true to accept the element or false to reject/discard it. + """ if el.tag not in self._tag_link_attrs: return False attr = self._tag_link_attrs[el.tag] @@ -450,8 +456,15 @@ class Cleaner(object): return self.allow_embedded_url(el, url) def allow_embedded_url(self, el, url): - if (self.whitelist_tags is not None - and el.tag not in self.whitelist_tags): + """ + Decide whether a URL that was found in an element's attributes or text + if configured to be accepted or rejected. + + :param el: an element. + :param url: a URL found on the element. + :return: true to accept the URL and false to reject it. + """ + if self.whitelist_tags is not None and el.tag not in self.whitelist_tags: return False scheme, netloc, path, query, fragment = urlsplit(url) netloc = netloc.lower().split(':', 1)[0] |