better utf-8 handling (though, we currently don't take in to account what

[rss2maildir.git] / rss2maildir.py

diff --git a/rss2maildir.py b/rss2maildir.py
index 60bbe906ed562b1767d6c716d9ed4741891fe3ea..2d26217f9fb9d0df73f760926aea8946c10d421a 100755 (executable)
--- a/rss2maildir.py
+++ b/rss2maildir.py
@@ -1,4 +1,21 @@
 #!/usr/bin/python
 #!/usr/bin/python

+# coding=utf-8
+
+# rss2maildir.py - RSS feeds to Maildir 1 email per item
+# Copyright (C) 2007  Brett Parker <iDunno@sommitrealweird.co.uk>
+# 
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+# 
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.

 
 import mailbox
 import sys
 
 import mailbox
 import sys


@@ -14,6 +31,7 @@ from email.MIMEText import MIMEText
 import datetime
 import random
 import string
 import datetime
 import random
 import string

+import textwrap

 
 import socket
 
 
 import socket
 


@@ -26,6 +44,139 @@ import md5
 import cgi
 import dbm
 
 import cgi
 import dbm
 

+from HTMLParser import HTMLParser
+
+entities = {
+    "amp": "&",
+    "lt": "<",
+    "gt": ">",
+    "pound": "£",
+    "copy": "©",
+    "apos": "'",
+    "quote": "\"",
+    "nbsp": " ",
+    }
+
+class HTML2Text(HTMLParser):
+    
+    def __init__(self):
+        self.inheadingone = False
+        self.inheadingtwo = False
+        self.inotherheading = False
+        self.inparagraph = True
+        self.inblockquote = False
+        self.inlink = False
+        self.text = u''
+        self.currentparagraph = u''
+        self.headingtext = u''
+        self.blockquote = u''
+        self.inpre = False
+        HTMLParser.__init__(self)
+
+    def handle_starttag(self, tag, attrs):
+        if tag.lower() == "h1":
+            self.inheadingone = True
+            self.inparagraph = False
+        elif tag.lower() == "h2":
+            self.inheadingtwo = True
+            self.inparagraph = False
+        elif tag.lower() in ["h3", "h4", "h5", "h6"]:
+            self.inotherheading = True
+            self.inparagraph = False
+        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)).encode('utf-8') + "\n"
+                self.currentparagraph = ""
+            elif self.inblockquote:
+                self.text = self.text + "\n> " + "\n> ".join([a.strip() for a in textwrap.wrap(self.blockquote, 68)]).encode("utf-8") + "\n"
+                self.blockquote = u''
+            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"
+            if self.inparagraph:
+                self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70)).encode("utf-8")
+            self.currentparagraph = u''
+            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":
+            if self.inparagraph:
+                self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70)).encode("utf-8") + "\n"
+                self.currentparagraph = u''
+            elif self.inblockquote:
+                self.text = self.text + "\n> " + "\n> ".join([a.strip() for a in textwrap.wrap(self.blockquote, 68)]).encode("utf-8") + "\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 + "\n\n" + self.headingtext + "\n" + "=" * len(self.headingtext.strip())
+            self.headingtext = u''
+        elif tag.lower() == "h2":
+            self.inheadingtwo = False
+            self.text = self.text + "\n\n" + self.headingtext + "\n" + "-" * len(self.headingtext.strip())
+            self.headingtext = u''
+        elif tag.lower() in ["h3", "h4", "h5", "h6"]:
+            self.inotherheading = False
+            self.text = self.text + "\n\n" + self.headingtext + "\n" + "~" * len(self.headingtext.strip())
+            self.headingtext = u''
+        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)]).encode("utf-8") + "\n"
+            self.inblockquote = False
+            self.blockquote = u''
+        elif tag.lower() == "pre":
+            self.inpre = False
+
+    def handle_data(self, data):
+        if self.inheadingone or self.inheadingtwo or self.inotherheading:
+            self.headingtext = self.headingtext + unicode(data, "utf-8").strip() + u' '
+        elif self.inblockquote:
+            self.blockquote = self.blockquote + unicode(data, "utf-8").strip() + u' '
+        elif self.inparagraph:
+            self.currentparagraph = self.currentparagraph + unicode(data, "utf-8").strip() + u' '
+        elif self.inpre:
+            self.text = self.text + data.encode("utf-8")
+        else:
+            self.text = self.text + unicode(data, "utf-8").strip() + u' '
+
+    def handle_entityref(self, name):
+        entity = name
+        if entities.has_key(name.lower()):
+            entity = entities[name.lower()]
+        elif name[0] == "#":
+            entity = unichr(int(name[1:]))
+        else:
+            entity = "&" + name + ";"
+
+        if self.inparagraph:
+            self.currentparagraph = self.currentparagraph + entity
+        elif self.inblockquote:
+            self.blockquote = self.blockquote + entity
+        else:
+            self.text = self.text + entity
+
+    def gettext(self):
+        data = self.text
+        if self.inparagraph:
+            data = data + "\n".join(textwrap.wrap(self.currentparagraph, 70))
+        return data

 
 def parse_and_deliver(maildir, url, statedir):
     md = mailbox.Maildir(maildir)
 
 def parse_and_deliver(maildir, url, statedir):
     md = mailbox.Maildir(maildir)


@@ -40,10 +191,10 @@ def parse_and_deliver(maildir, url, statedir):
         else:
             content = item["summary"]
 
         else:
             content = item["summary"]
 

-        md5sum = md5.md5(content.encode("utf8")).hexdigest()
+        md5sum = md5.md5(content.encode("utf-8")).hexdigest()

 
 

-        if db.has_key(item["link"]):
-            data = db[item["link"]]
+        if db.has_key(url + "|" + item["link"]):
+            data = db[url + "|" + item["link"]]

             data = cgi.parse_qs(data)
             if data["contentmd5"][0] == md5sum:
                 continue
             data = cgi.parse_qs(data)
             if data["contentmd5"][0] == md5sum:
                 continue


@@ -65,9 +216,11 @@ def parse_and_deliver(maildir, url, statedir):
         msg.add_header("Subject", item["title"])
         msg.set_default_type("text/plain")
 
         msg.add_header("Subject", item["title"])
         msg.set_default_type("text/plain")
 

-        htmlpart = MIMEText(content.encode("utf8"), "html", "utf8")
-        textpart = MIMEText(content.encode("utf8"), "plain", "utf8")
-
+        htmlpart = MIMEText(content.encode("utf-8"), "html", "utf-8")
+        textparser = HTML2Text()
+        textparser.feed(content.encode("utf-8"))
+        textcontent = textparser.gettext()
+        textpart = MIMEText(textcontent.encode("utf-8"), "plain", "utf-8")

         msg.attach(textpart)
         msg.attach(htmlpart)
 
         msg.attach(textpart)
         msg.attach(htmlpart)
 


@@ -85,7 +238,7 @@ def parse_and_deliver(maildir, url, statedir):
 
         # now add to the database about the item
         data = urllib.urlencode((("message-id", messageid), ("created", createddate), ("contentmd5", md5sum)))
 
         # now add to the database about the item
         data = urllib.urlencode((("message-id", messageid), ("created", createddate), ("contentmd5", md5sum)))

-        db[item["link"]] = data
+        db[url + "|" + item["link"]] = data

 
     db.close()
 
 
     db.close()