WIP

feedpipe.py

@@ -10,6 +10,7 @@
 # https://pypi.python.org/pypi/defusedxml/#defusedxml-sax
 import xml.sax
 from xml.sax.saxutils import escape
+import HTMLParser
 
 
 class FeedPipe(object):
@@ -137,8 +138,9 @@ def __init__(self, content=''):
                                      .replace('’', '')
                         try:
                             try:
-                                xml.sax.parseString(("<div>{}</div>".format(nco)),
-                                                    xml.sax.ContentHandler())
+                                xml.sax.parseString(
+                                    ("<div>{}</div>".format(HTMLParser.HTMLParser().unescape(nco))),
+                                    xml.sax.ContentHandler())
                             except UnicodeEncodeError:
                                 # who the hell cares?
                                 pass
@@ -147,8 +149,7 @@ def __init__(self, content=''):
                                 xmlns='http://www.w3.org/1999/xhtml')
                             self.div.content = content
                             self.attrs["type"] = 'xhtml'
-                        except xml.sax.SAXParseException as e:
-                            print(nco)
+                        except xml.sax.SAXParseException:
                             self.attrs["type"] = 'html'
                             self.content = xe.XMLText(escape(content))
 

tests/test_basic.py

@@ -161,9 +161,11 @@ def test_grep(self):
         # )
         self.assertEqual(fp.count(), 5)
 
-    # def test_html_vs_xhtml(self):
-    #     fp = FeedPipe().cat(['./tests/lwn.xml'])
-    #     print([str(x.content) for x in fp.entries])
+    def test_html_vs_xhtml(self):
+        fp = FeedPipe().cat(['./tests/lwn.xml'])
+        for x in fp.entries:
+            if x.content.attrs['type'] == 'html':
+                print(x.content)
 
 if __name__ == '__main__':
     unittest.main()