X-Git-Url: https://git.sommitrealweird.co.uk/rss2maildir.git/blobdiff_plain/729c797149e6048e3f48f700e1e4bc2533c3a99d..2408a39553e5f6d8de18325a16f67b70595f6dac:/rss2maildir.py?ds=sidebyside

diff --git a/rss2maildir.py b/rss2maildir.py
index d721d0e..fd14826 100755
--- a/rss2maildir.py
+++ b/rss2maildir.py
@@ -64,10 +64,13 @@ class HTML2Text(HTMLParser):
         self.inheadingtwo = False
         self.inotherheading = False
         self.inparagraph = True
+        self.inblockquote = False
         self.inlink = False
         self.text = ""
         self.currentparagraph = ""
         self.headingtext = ""
+        self.blockquote = ""
+        self.inpre = False
         HTMLParser.__init__(self)
 
     def handle_starttag(self, tag, attrs):
@@ -83,41 +86,75 @@ class HTML2Text(HTMLParser):
         elif tag.lower() == "a":
             self.inlink = True
         elif tag.lower() == "br":
+            if self.inparagraph:
+                self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70)) + "\n"
+                self.currentparagraph = ""
+            elif self.inblockquote:
+                self.text = self.text + "\n> " + "\n> ".join([a.strip() for a in textwrap.wrap(self.blockquote, 68)]) + "\n"
+                self.blockquote = ""
+            else:
+                self.text = self.text + "\n"
+        elif tag.lower() == "blockquote":
+            self.inblockquote = True
             self.text = self.text + "\n"
         elif tag.lower() == "p":
             if self.text != "":
                 self.text = self.text + "\n\n"
-                self.currentparagraph = ""
-                self.inparagraph = True
+            if self.inparagraph:
+                self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70))
+            self.currentparagraph = ""
+            self.inparagraph = True
+        elif tag.lower() == "pre":
+            self.text = self.text + "\n"
+            self.inpre = True
+            self.inparagraph = False
+            self.inblockquote = False
 
     def handle_startendtag(self, tag, attrs):
         if tag.lower() == "br":
-            self.text = self.text + "\n"
+            if self.inparagraph:
+                self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70)) + "\n"
+                self.currentparagraph = ""
+            elif self.inblockquote:
+                self.text = self.text + "\n> " + "\n> ".join([a.strip() for a in textwrap.wrap(self.blockquote, 68)]) + "\n"
+                self.blockquote = ""
+            else:
+                self.text = self.text + "\n"
 
     def handle_endtag(self, tag):
         if tag.lower() == "h1":
             self.inheadingone = False
-            self.text = self.text + self.headingtext + "\n" + "=" * len(self.headingtext)
+            self.text = self.text + "\n\n" + self.headingtext + "\n" + "=" * len(self.headingtext.strip())
             self.headingtext = ""
         elif tag.lower() == "h2":
             self.inheadingtwo = False
-            self.text = self.text + self.headingtext + "\n" + "-" * len(self.headingtext)
+            self.text = self.text + "\n\n" + self.headingtext + "\n" + "-" * len(self.headingtext.strip())
             self.headingtext = ""
         elif tag.lower() in ["h3", "h4", "h5", "h6"]:
             self.inotherheading = False
-            self.text = self.text + self.headingtext + "\n" + "~" * len(self.headingtext)
+            self.text = self.text + "\n\n" + self.headingtext + "\n" + "~" * len(self.headingtext.strip())
             self.headingtext = ""
         elif tag.lower() == "p":
             self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70))
             self.inparagraph = False
+        elif tag.lower() == "blockquote":
+            self.text = self.text + "\n> " + "\n> ".join([a.strip() for a in textwrap.wrap(self.blockquote, 68)]) + "\n"
+            self.inblockquote = False
+            self.blockquote = ""
+        elif tag.lower() == "pre":
+            self.inpre = False
 
     def handle_data(self, data):
-        if not self.inheadingone and not self.inheadingtwo and not self.inotherheading and not self.inparagraph:
-            self.text = self.text + data.strip() + " "
+        if self.inheadingone or self.inheadingtwo or self.inotherheading:
+            self.headingtext = self.headingtext + data.strip() + " "
+        elif self.inblockquote:
+            self.blockquote = self.blockquote + data.strip() + " "
         elif self.inparagraph:
             self.currentparagraph = self.currentparagraph + data.strip() + " "
+        elif self.inpre:
+            self.text = self.text + data
         else:
-            self.headingtext = self.headingtext + data.strip() + " "
+            self.text = self.text + data.strip() + " "
 
     def handle_entityref(self, name):
         if entities.has_key(name.lower()):