Unicode handling of URLs fix

[rss2maildir.git] / rss2maildir.py

diff --git a/rss2maildir.py b/rss2maildir.py
index 5d991e72363e254fe6d8604e38321b301aa19bfd..2af32bc9105a49201e2bbba49d87b5e2cbcda1da 100755 (executable)
--- a/rss2maildir.py
+++ b/rss2maildir.py
@@ -151,7 +151,7 @@ class HTML2Text(HTMLParser):
             elif tag_name == u'a':
                 for attr in attrs:
                     if attr[0].lower() == u'href':
             elif tag_name == u'a':
                 for attr in attrs:
                     if attr[0].lower() == u'href':

-                        self.urls.append(attr[1])
+                        self.urls.append(attr[1].decode('utf-8'))

                 self.curdata = self.curdata + u'`'
                 self.opentags.append(tag_name)
                 return
                 self.curdata = self.curdata + u'`'
                 self.opentags.append(tag_name)
                 return


@@ -235,8 +235,7 @@ class HTML2Text(HTMLParser):
         if tag_thats_done in ["h1", "h2", "h3", "h4", "h5", "h6"]:
             underline = u''
             underlinechar = u'='
         if tag_thats_done in ["h1", "h2", "h3", "h4", "h5", "h6"]:
             underline = u''
             underlinechar = u'='

-            headingtext = unicode( \
-                self.curdata.encode("utf-8").strip(), "utf-8")
+            headingtext = self.curdata

             seperator = u'\n' + u' '*self.indentlevel
             headingtext = seperator.join( \
                 textwrap.wrap( \
             seperator = u'\n' + u' '*self.indentlevel
             headingtext = seperator.join( \
                 textwrap.wrap( \


@@ -257,7 +256,7 @@ class HTML2Text(HTMLParser):
                 underline = u' ' * self.indentlevel \
                     + underlinechar * len(headingtext)
             self.text = self.text \
                 underline = u' ' * self.indentlevel \
                     + underlinechar * len(headingtext)
             self.text = self.text \

-                + headingtext.encode("utf-8") + u'\n' \
+                + headingtext + u'\n' \

                 + underline
         elif tag_thats_done in [u'p', u'div']:
             paragraph = unicode( \
                 + underline
         elif tag_thats_done in [u'p', u'div']:
             paragraph = unicode( \


@@ -414,7 +413,7 @@ class HTML2Text(HTMLParser):
     def handle_data(self, data):
         if len(self.opentags) == 0:
             self.opentags.append(u'p')
     def handle_data(self, data):
         if len(self.opentags) == 0:
             self.opentags.append(u'p')

-        self.curdata = self.curdata + unicode(data, "utf-8")
+        self.curdata = self.curdata + data.decode("utf-8")

 
     def handle_entityref(self, name):
         entity = name
 
     def handle_entityref(self, name):
         entity = name