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

feeds: various small cleanup/fixes

Browse Source
This commit is contained in:
pictuga
2018-11-18 15:14:38 +01:00
parent 24c8a0ecd0
commit e606c5eefb
2 changed files with 18 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
morss/feeds.py
View File

@@ -44,18 +44,6 @@ except NameError:
basestring = unicode = str basestring = unicode = str
Element = etree.Element
NSMAP = {'atom': 'http://www.w3.org/2005/Atom',
'atom03': 'http://purl.org/atom/ns#',
'media': 'http://search.yahoo.com/mrss/',
'rdf': 'http://www.w3.org/1999/02/22-rdf-syntax-ns#',
'slash': 'http://purl.org/rss/1.0/modules/slash/',
'dc': 'http://purl.org/dc/elements/1.1/',
'content': 'http://purl.org/rss/1.0/modules/content/',
'rssfake': 'http://purl.org/rss/1.0/'}
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')
@@ -224,6 +212,15 @@ class ParserBase(object):
class ParserXML(ParserBase): class ParserXML(ParserBase):
NSMAP = {'atom': 'http://www.w3.org/2005/Atom',
'atom03': 'http://purl.org/atom/ns#',
'media': 'http://search.yahoo.com/mrss/',
'rdf': 'http://www.w3.org/1999/02/22-rdf-syntax-ns#',
'slash': 'http://purl.org/rss/1.0/modules/slash/',
'dc': 'http://purl.org/dc/elements/1.1/',
'content': 'http://purl.org/rss/1.0/modules/content/',
'rssfake': 'http://purl.org/rss/1.0/'}
def parse(self, raw): def parse(self, raw):
parser = etree.XMLParser(recover=True) parser = etree.XMLParser(recover=True)
return etree.fromstring(raw, parser) return etree.fromstring(raw, parser)
@@ -242,8 +239,8 @@ class ParserXML(ParserBase):
match = re.search(r'^([^:]+):([^:]+)$', rule) # to match fakerss:content match = re.search(r'^([^:]+):([^:]+)$', rule) # to match fakerss:content
if match: if match:
match = match.groups() match = match.groups()
if match[0] in NSMAP: if match[0] in self.NSMAP:
return "{%s}%s" % (NSMAP[match[0]], match[1].lower()) return "{%s}%s" % (self.NSMAP[match[0]], match[1].lower())
return rule return rule
@@ -257,7 +254,7 @@ class ParserXML(ParserBase):
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=self.NSMAP)
except etree.XPathEvalError: except etree.XPathEvalError:
return [] return []
@@ -405,17 +402,18 @@ class Uniq(object):
_id = None _id = None
def __new__(cls, *args, **kwargs): def __new__(cls, *args, **kwargs):
# check if an item was already created for it # check if a wrapper was already created for it
# if so, reuse it # if so, reuse it
# if not, create a new one # if not, create a new one
# note that the item itself (the tree node) is created beforehands
tmp_id = cls._gen_id(*args, **kwargs) tmp_id = cls._gen_id(*args, **kwargs)
if tmp_id is not None and tmp_id in cls._map: if tmp_id in cls._map:
return cls._map[tmp_id] return cls._map[tmp_id]
else: else:
obj = object.__new__(cls, *args, **kwargs) obj = object.__new__(cls, *args, **kwargs)
cls._map[obj._id] = obj cls._map[tmp_id] = obj
return obj return obj

4
morss/morss.py
View File

@@ -164,8 +164,8 @@ def ItemFix(item, feedurl='/'):
item.link = parse_qs(urlparse(item.link).query)['u'][0] item.link = parse_qs(urlparse(item.link).query)['u'][0]
log(item.link) log(item.link)
# feedburner # feedburner FIXME only works if RSS...
feeds.NSMAP['feedburner'] = 'http://rssnamespace.org/feedburner/ext/1.0' item.NSMAP['feedburner'] = 'http://rssnamespace.org/feedburner/ext/1.0'
match = item.rule_str('feedburner:origLink') match = item.rule_str('feedburner:origLink')
if match: if match:
item.link = match item.link = match