X-Git-Url: https://git.sommitrealweird.co.uk/rss2maildir.git/blobdiff_plain/47c98c8b7067c9146f49746be76ad23a4b877806..84f14a811430b6a49cd2d9adac6d4bcaa34c3037:/rss2maildir.py

diff --git a/rss2maildir.py b/rss2maildir.py
index 04f20ce..f6078ff 100755
--- a/rss2maildir.py
+++ b/rss2maildir.py
@@ -93,6 +93,7 @@ class HTML2Text(HTMLParser):
         self.opentags = []
         self.indentlevel = 0
         self.listcount = []
+        self.urls = []
         HTMLParser.__init__(self)
 
     def handle_starttag(self, tag, attrs):
@@ -145,15 +146,22 @@ class HTML2Text(HTMLParser):
                 and self.opentags[-1] == u'dd':
                 self.handle_curdata()
                 self.opentags.pop()
+            elif tag_name == u'a':
+                for attr in attrs:
+                    if attr[0].lower() == u'href':
+                        self.urls.append(attr[1])
+                self.curdata = self.curdata + u'`'
+                self.opentags.append(tag_name)
+                return
 
             self.handle_curdata()
             self.opentags.append(tag_name)
 
     def handle_startendtag(self, tag, attrs):
         if tag.lower() == u'br':
-            self.tags.append(u'br')
+            self.opentags.append(u'br')
             self.handle_curdata() # just handle the data, don't do anything else
-            self.tags.pop()
+            self.opentags.pop()
 
     def handle_curdata(self):
         if len(self.opentags) == 0:
@@ -179,7 +187,8 @@ class HTML2Text(HTMLParser):
         if tag_thats_done in ["h1", "h2", "h3", "h4", "h5", "h6"]:
             underline = u''
             underlinechar = u'='
-            headingtext = self.curdata.encode("utf-8").strip()
+            headingtext = unicode( \
+                self.curdata.encode("utf-8").strip(), "utf-8")
             seperator = u'\n' + u' '*self.indentlevel
             headingtext = seperator.join( \
                 textwrap.wrap( \
@@ -203,15 +212,20 @@ class HTML2Text(HTMLParser):
                 + headingtext.encode("utf-8") + u'\n' \
                 + underline
         elif tag_thats_done == u'p':
-            paragraph = self.curdata.encode("utf-8").strip()
+            paragraph = unicode( \
+                self.curdata.strip().encode("utf-8"), "utf-8")
             seperator = u'\n' + u' ' * self.indentlevel
             self.text = self.text \
                 + u' ' * self.indentlevel \
-                + seperator.join(textwrap.wrap(paragraph, self.textwidth - self.indentlevel))
+                + seperator.join( \
+                    textwrap.wrap( \
+                        paragraph, self.textwidth - self.indentlevel))
         elif tag_thats_done == "pre":
-            self.text = self.text + self.curdata
+            self.text = self.text + unicode( \
+                self.curdata.encode("utf-8"), "utf-8")
         elif tag_thats_done == "blockquote":
-            quote = self.curdata.encode("utf-8").strip()
+            quote = unicode( \
+                self.curdata.encode("utf-8").strip(), "utf-8")
             seperator = u'\n' + u' ' * self.indentlevel + u'> '
             self.text = self.text \
                 + u'> ' \
@@ -222,13 +236,13 @@ class HTML2Text(HTMLParser):
                     )
                 )
         elif tag_thats_done == "li":
-            item = self.curdata.encode("utf-8").strip()
+            item = unicode(self.curdata.encode("utf-8").strip(), "utf-8")
             if len(self.text) > 0 and self.text[-1] != u'\n':
                 self.text = self.text + u'\n'
             # work out if we're in an ol rather than a ul
             latesttags = self.opentags[-4:]
             latesttags.reverse()
-            isul = False
+            isul = None
             for thing in latesttags:
                 if thing == 'ul':
                     isul = True
@@ -242,7 +256,7 @@ class HTML2Text(HTMLParser):
                 listindent = 4
 
             listmarker = u' * '
-            if not isul:
+            if isul == False:
                 listmarker = u' %2d. ' %(self.listcount[-1])
                 self.listcount[-1] = self.listcount[-1] + 1
 
@@ -260,7 +274,7 @@ class HTML2Text(HTMLParser):
                 )
             self.curdata = u''
         elif tag_thats_done == u'dt':
-            definition = self.curdata.encode("utf-8").strip()
+            definition = unicode(self.curdata.encode("utf-8").strip(), "utf-8")
             if len(self.text) > 0 and self.text[-1] != u'\n':
                 self.text = self.text + u'\n\n'
             elif len(self.text) > 1 and self.text[-2] != u'\n':
@@ -273,7 +287,7 @@ class HTML2Text(HTMLParser):
                         self.textwidth - self.indentlevel - 1))
             self.curdata = u''
         elif tag_thats_done == u'dd':
-            definition = self.curdata.encode("utf-8").strip()
+            definition = unicode(self.curdata.encode("utf-8").strip(), "utf-8")
             if len(definition) > 0:
                 if len(self.text) > 0 and self.text[-1] != u'\n':
                     self.text = self.text + u'\n'
@@ -287,6 +301,9 @@ class HTML2Text(HTMLParser):
                             ) \
                         )
                 self.curdata = u''
+        elif tag_thats_done == u'a':
+            self.curdata = self.curdata + u'`__'
+            pass
         elif tag_thats_done in self.liststarttags:
             pass
         else:
@@ -296,7 +313,10 @@ class HTML2Text(HTMLParser):
                 self.text = self.text \
                     + u' ... ' \
                     + u'\n ... '.join( \
-                        textwrap.wrap(self.curdata, self.textwidth - 5))
+                        textwrap.wrap( \
+                            unicode( \
+                                self.curdata.encode("utf-8").strip(), \
+                                "utf-8"), self.textwidth - 5))
             self.curdata = u''
 
         if tag_thats_done in self.blockleveltags:
@@ -369,6 +389,9 @@ class HTML2Text(HTMLParser):
             while len(self.text) > 1 and self.text[-1] == u'\n':
                 self.text = self.text[:-1]
             self.text = self.text + u'\n'
+        if len(self.urls) > 0:
+            self.text = self.text + u'\n__ ' + u'\n__ '.join(self.urls) + u'\n'
+            self.urls = []
         return self.text
 
 def open_url(method, url):
@@ -574,7 +597,8 @@ def parse_and_deliver(maildir, url, statedir):
     if headers:
         data = []
         for header in headers:
-            if header[0] in ["content-md5", "etag", "last-modified", "content-length"]:
+            if header[0] in \
+                ["content-md5", "etag", "last-modified", "content-length"]:
                 data.append((header[0], header[1]))
         if len(data) > 0:
             data = urllib.urlencode(data)