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

feeds: fix atom xhtml handling

master
pictuga 2018-11-11 15:21:06 +01:00
parent 8aceda4957
commit 401dfbc1ff
1 changed files with 21 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
morss/feeds.py
View File

@ -77,14 +77,6 @@ def tag_NS(tag, nsmap=NSMAP):
return tag return tag
def inner_html(xml):
return (xml.text or '') + ''.join([etree.tostring(child) for child in xml])
def clean_node(xml):
[xml.remove(child) for child in xml]
def parse_rules(filename=None): def parse_rules(filename=None):
if not filename: if not filename:
filename = os.path.join(os.path.dirname(__file__), 'feedify.ini') filename = os.path.join(os.path.dirname(__file__), 'feedify.ini')
@ -266,6 +258,14 @@ class ParserXML(ParserBase):
return rule return rule
@staticmethod
def _inner_html(xml):
return (xml.text or '') + ''.join([etree.tostring(child) for child in xml])
@staticmethod
def _clean_node(xml):
[xml.remove(child) for child in xml]
def rule_search_all(self, rule): def rule_search_all(self, rule):
try: try:
return self.root.xpath(rule, namespaces=NSMAP) return self.root.xpath(rule, namespaces=NSMAP)
@ -333,13 +333,25 @@ class ParserXML(ParserBase):
match.attrib[key] = value match.attrib[key] = value
else: else:
if len(match):
# atom stuff
self._clean_node(match)
if match.attrib.get('type', '') == 'xhtml':
match.attrib['type'] = 'html'
match.text = value match.text = value
def rule_str(self, rule): def rule_str(self, rule):
match = self.rule_search(rule) match = self.rule_search(rule)
if isinstance(match, etree._Element): if isinstance(match, etree._Element):
return match.text or "" if len(match):
# atom stuff
return self._inner_html(match)
else:
return match.text or ""
else: else:
return match or "" return match or ""