feeds: fix handling of html code
parent
13ea52ef80
commit
449bc3c695
|
@ -387,15 +387,22 @@ class ParserXML(ParserBase):
|
||||||
|
|
||||||
match = self.rule_search(rrule)
|
match = self.rule_search(rrule)
|
||||||
|
|
||||||
|
html_rich = ('atom' in rule or self.rules['mode'] == 'html') \
|
||||||
|
and rule in [self.rules.get('item_desc'), self.rules.get('item_content')]
|
||||||
|
|
||||||
if key is not None:
|
if key is not None:
|
||||||
match.attrib[key] = value
|
match.attrib[key] = value
|
||||||
|
|
||||||
else:
|
else:
|
||||||
if match is not None and len(match):
|
if html_rich:
|
||||||
# atom stuff
|
# atom stuff
|
||||||
self._clean_node(match)
|
self._clean_node(match)
|
||||||
|
match.attrib['type'] = 'xhtml'
|
||||||
|
match.append(lxml.html.fragment_fromstring(value, create_parent='div'))
|
||||||
|
|
||||||
if match.attrib.get('type', '') == 'xhtml':
|
else:
|
||||||
|
if match is not None and len(match):
|
||||||
|
self._clean_node(match)
|
||||||
match.attrib['type'] = 'html'
|
match.attrib['type'] = 'html'
|
||||||
|
|
||||||
match.text = value
|
match.text = value
|
||||||
|
@ -403,13 +410,16 @@ class ParserXML(ParserBase):
|
||||||
def rule_str(self, rule):
|
def rule_str(self, rule):
|
||||||
match = self.rule_search(rule)
|
match = self.rule_search(rule)
|
||||||
|
|
||||||
|
html_rich = ('atom' in rule or self.rules['mode'] == 'html') \
|
||||||
|
and rule in [self.rules.get('item_desc'), self.rules.get('item_content')]
|
||||||
|
|
||||||
if isinstance(match, etree._Element):
|
if isinstance(match, etree._Element):
|
||||||
if len(match):
|
if html_rich:
|
||||||
# atom stuff
|
# atom stuff
|
||||||
return self._inner_html(match)
|
return self._inner_html(match)
|
||||||
|
|
||||||
else:
|
else:
|
||||||
return match.text or ""
|
return etree.tostring(match, method='text', encoding='unicode').strip()
|
||||||
|
|
||||||
else:
|
else:
|
||||||
return match or ""
|
return match or ""
|
||||||
|
|
Loading…
Reference in New Issue