pictuga
/
morss
1
1
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

feeds: clean up html code handling

master
pictuga 2020-03-19 11:35:51 +01:00
parent 9cf933723f
commit b47e40246c
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
morss/feeds.py
View File

@ -320,8 +320,10 @@ class ParserXML(ParserBase):
@staticmethod @staticmethod
def _clean_node(xml): def _clean_node(xml):
if xml is not None and len(xml): if xml is not None:
if len(xml):
[xml.remove(child) for child in xml] [xml.remove(child) for child in xml]
xml.text = None xml.text = None
def rule_search_all(self, rule): def rule_search_all(self, rule):
@ -401,9 +403,12 @@ class ParserXML(ParserBase):
else: else:
if html_rich: if html_rich:
# atom stuff # atom stuff
self._clean_node(match) if 'atom' in rule:
match.attrib['type'] = 'xhtml' match.attrib['type'] = 'xhtml'
self._clean_node(match)
match.append(lxml.html.fragment_fromstring(value, create_parent='div')) match.append(lxml.html.fragment_fromstring(value, create_parent='div'))
match.find('div').drop_tag()
else: else:
if match is not None and len(match): if match is not None and len(match):