feedify: support any type (json, xml, html)

morss/feeds.py

@@ -88,16 +88,21 @@ def parse_rules(filename=None):
     return rules
 
 
-def parse(data, url=None, encoding=None):
+def parse(data, url=None, encoding=None, ruleset=None):
     " Determine which ruleset to use "
 
-    rulesets = parse_rules()
+    if ruleset is not None:
+        rulesets = [ruleset]
+
+    else:
+        rulesets = parse_rules().values()
+
     parsers = [FeedXML, FeedHTML, FeedJSON]
 
     # 1) Look for a ruleset based on path
 
     if url is not None:
-        for ruleset in rulesets.values():
+        for ruleset in rulesets:
             if 'path' in ruleset:
                 for path in ruleset['path']:
                     if fnmatch(url, path):
@@ -111,9 +116,6 @@ def parse(data, url=None, encoding=None):
         # 3b) See if .items matches anything
 
     for parser in parsers:
-        ruleset_candidates = [x for x in rulesets.values() if x['mode'] == parser.mode and 'path' not in x]
-            # 'path' as they should have been caught beforehands
-
         try:
             feed = parser(data, encoding=encoding)
 
@@ -124,13 +126,17 @@ def parse(data, url=None, encoding=None):
         else:
             # parsing worked, now we try the rulesets
 
+            ruleset_candidates = [x for x in rulesets if x.get('mode', None) in (parser.mode, None) and 'path' not in x]
+                # 'path' as they should have been caught beforehands
+                # try anyway if no 'mode' specified
+
             for ruleset in ruleset_candidates:
                 feed.rules = ruleset
 
                 try:
                     feed.items[0]
 
-                except (AttributeError, IndexError):
+                except (AttributeError, IndexError, TypeError):
                     # parsing and or item picking did not work out
                     pass
 

morss/morss.py

@@ -104,6 +104,13 @@ class Options:
     def __contains__(self, key):
         return key in self.options
 
+    def get(self, key, default=None):
+        if key in self.options:
+            return self.options[key]
+
+        else:
+            return default
+
 
 def ItemFix(item, options, feedurl='/'):
     """ Improves feed items (absolute links, resolve feedburner links, etc) """
@@ -276,22 +283,23 @@ def FeedFetch(url, options):
 
     if options.items:
         # using custom rules
-        rss = feeds.FeedHTML(req['data'], encoding=req['encoding'])
+        ruleset = {}
 
-        rss.rules['title'] = options.title              if options.title        else '//head/title'
+        ruleset['items'] = options.items
-        rss.rules['desc'] = options.desc                if options.desc         else '//head/meta[@name="description"]/@content'
 
-        rss.rules['items'] = options.items
+        ruleset['title'] = options.get('title', '//head/title')
+        ruleset['desc'] = options.get('desc', '//head/meta[@name="description"]/@content')
 
-        rss.rules['item_title'] = options.item_title    if options.item_title   else '.'
+        ruleset['item_title'] = options.get('item_title', '.')
-        rss.rules['item_link'] = options.item_link      if options.item_link    else './@href|.//a/@href|ancestor::a/@href'
+        ruleset['item_link'] = options.get('item_link', './@href|.//a/@href|ancestor::a/@href')
 
         if options.item_content:
-            rss.rules['item_content'] = options.item_content
+            ruleset['item_content'] = options.item_content
 
         if options.item_time:
-            rss.rules['item_time'] = options.item_time
+            ruleset['item_time'] = options.item_time
 
+        rss = feeds.parse(req['data'], encoding=req['encoding'], ruleset=ruleset)
         rss = rss.convert(feeds.FeedXML)
 
     else: