* fix README to have a more complete config example

[rss2maildir.git] / rss2maildir.py

diff --git a/rss2maildir.py b/rss2maildir.py
index 80f22d57d6f6852ed9efbf1289b03590f9845f8f..322dc5751d2f77efe51f301b5dba9a4b2799381b 100755 (executable)
--- a/rss2maildir.py
+++ b/rss2maildir.py
@@ -58,7 +58,7 @@ class HTML2Text(HTMLParser):
         "nbsp": " ",
         }
 
         "nbsp": " ",
         }
 

-    def __init__(self):
+    def __init__(self,textwidth=70):

         self.inheadingone = False
         self.inheadingtwo = False
         self.inotherheading = False
         self.inheadingone = False
         self.inheadingtwo = False
         self.inotherheading = False


@@ -73,6 +73,7 @@ class HTML2Text(HTMLParser):
         self.inul = False
         self.initem = False
         self.item = u''
         self.inul = False
         self.initem = False
         self.item = u''

+        self.textwidth = textwidth

         HTMLParser.__init__(self)
 
     def handle_starttag(self, tag, attrs):
         HTMLParser.__init__(self)
 
     def handle_starttag(self, tag, attrs):


@@ -97,7 +98,7 @@ class HTML2Text(HTMLParser):
                 self.text = self.text + u'\n\n'
             if self.inparagraph:
                 self.text = self.text \
                 self.text = self.text + u'\n\n'
             if self.inparagraph:
                 self.text = self.text \

-                    + u'\n'.join(textwrap.wrap(self.currentparagraph, 70))
+                    + u'\n'.join(textwrap.wrap(self.currentparagraph, self.textwidth))

             self.currentparagraph = u''
             self.inparagraph = True
         elif tag.lower() == "pre":
             self.currentparagraph = u''
             self.inparagraph = True
         elif tag.lower() == "pre":


@@ -109,7 +110,7 @@ class HTML2Text(HTMLParser):
             self.item = u''
             self.inul = True
             self.text = self.text + "\n"
             self.item = u''
             self.inul = True
             self.text = self.text + "\n"

-        elif tag.lower() == "li" and self.inul:
+        elif tag.lower() == "li":

             if not self.initem:
                 self.initem = True
                 self.item = u''
             if not self.initem:
                 self.initem = True
                 self.item = u''


@@ -117,9 +118,10 @@ class HTML2Text(HTMLParser):
                 self.text = self.text \
                     + u' * ' \
                     + u'\n   '.join([a.strip() for a in \
                 self.text = self.text \
                     + u' * ' \
                     + u'\n   '.join([a.strip() for a in \

-                        textwrap.wrap(self.item, 67)]) \
+                        textwrap.wrap(self.item, self.textwidth - 3)]) \

                     + u'\n'
                 self.item = u''
                     + u'\n'
                 self.item = u''

+                self.initem = True

 
     def handle_startendtag(self, tag, attrs):
         if tag.lower() == "br":
 
     def handle_startendtag(self, tag, attrs):
         if tag.lower() == "br":


@@ -131,7 +133,7 @@ class HTML2Text(HTMLParser):
                 + u'\n'.join( \
                     [a \
                         for a in textwrap.wrap( \
                 + u'\n'.join( \
                     [a \
                         for a in textwrap.wrap( \

-                            self.currentparagraph, 70) \
+                            self.currentparagraph, self.textwidth) \

                     ] \
                 ) \
                 + u'\n'
                     ] \
                 ) \
                 + u'\n'


@@ -179,7 +181,7 @@ class HTML2Text(HTMLParser):
         elif tag.lower() == "p":
             self.text = self.text \
                 + u'\n'.join(textwrap.wrap( \
         elif tag.lower() == "p":
             self.text = self.text \
                 + u'\n'.join(textwrap.wrap( \

-                    self.currentparagraph, 70) \
+                    self.currentparagraph, self.textwidth) \

                 )
             self.inparagraph = False
             self.currentparagraph = u''
                 )
             self.inparagraph = False
             self.currentparagraph = u''


@@ -189,7 +191,7 @@ class HTML2Text(HTMLParser):
                 + u'\n> '.join( \
                     [a.strip() \
                         for a in textwrap.wrap( \
                 + u'\n> '.join( \
                     [a.strip() \
                         for a in textwrap.wrap( \

-                            self.blockquote, 68)] \
+                            self.blockquote, self.textwidth - 2)] \

                     ) \
                 + u'\n'
             self.inblockquote = False
                     ) \
                 + u'\n'
             self.inblockquote = False


@@ -198,11 +200,11 @@ class HTML2Text(HTMLParser):
             self.inpre = False
         elif tag.lower() == "li":
             self.initem = False
             self.inpre = False
         elif tag.lower() == "li":
             self.initem = False

-            if self.item != "":
+            if self.item != u'':

                 self.text = self.text \
                     + u' * ' \
                     + u'\n   '.join( \
                 self.text = self.text \
                     + u' * ' \
                     + u'\n   '.join( \

-                        [a.strip() for a in textwrap.wrap(self.item, 67)]) \
+                        [a.strip() for a in textwrap.wrap(self.item, self.textwidth - 3)]) \

                     + u'\n'
             self.item = u''
         elif tag.lower() == "ul":
                     + u'\n'
             self.item = u''
         elif tag.lower() == "ul":


@@ -217,16 +219,18 @@ class HTML2Text(HTMLParser):
             self.blockquote = self.blockquote \
                 + unicode(data, "utf-8").strip() \
                 + u' '
             self.blockquote = self.blockquote \
                 + unicode(data, "utf-8").strip() \
                 + u' '

+        elif self.initem:
+            self.item = self.item + unicode(data, "utf-8")

         elif self.inparagraph:
             self.currentparagraph = self.currentparagraph \
                 + unicode(data, "utf-8").strip() \
                 + u' '
         elif self.inparagraph:
             self.currentparagraph = self.currentparagraph \
                 + unicode(data, "utf-8").strip() \
                 + u' '

-        elif self.inul and self.initem:
-            self.item = self.item + unicode(data, "utf-8")

         elif self.inpre:
             self.text = self.text + unicode(data, "utf-8")
         else:
         elif self.inpre:
             self.text = self.text + unicode(data, "utf-8")
         else:

-            self.text = self.text + unicode(data, "utf-8").strip() + u' '
+            isallwhitespace = data.strip() == ""
+            if not isallwhitespace:
+                self.text = self.text + unicode(data, "utf-8").strip() + u' ' 

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


@@ -248,7 +252,7 @@ class HTML2Text(HTMLParser):
     def gettext(self):
         data = self.text
         if self.inparagraph:
     def gettext(self):
         data = self.text
         if self.inparagraph:

-            data = data + "\n".join(textwrap.wrap(self.currentparagraph, 70))
+            data = data + "\n".join(textwrap.wrap(self.currentparagraph, self.textwidth))

         if data[-1] != '\n':
             data = data + '\n'
         return data
         if data[-1] != '\n':
             data = data + '\n'
         return data