X-Git-Url: https://git.sommitrealweird.co.uk/rss2maildir.git/blobdiff_plain/2408a39553e5f6d8de18325a16f67b70595f6dac..e3114c366ffcca31fedc33388dd887043e7e0af7:/rss2maildir.py

diff --git a/rss2maildir.py b/rss2maildir.py
index fd14826..268d192 100755
--- a/rss2maildir.py
+++ b/rss2maildir.py
@@ -1,5 +1,5 @@
 #!/usr/bin/python
-# coding=utf8
+# coding=utf-8
 
 # rss2maildir.py - RSS feeds to Maildir 1 email per item
 # Copyright (C) 2007  Brett Parker <iDunno@sommitrealweird.co.uk>
@@ -17,7 +17,6 @@
 # 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 os
 import stat
@@ -66,11 +65,14 @@ class HTML2Text(HTMLParser):
         self.inparagraph = True
         self.inblockquote = False
         self.inlink = False
-        self.text = ""
-        self.currentparagraph = ""
-        self.headingtext = ""
-        self.blockquote = ""
+        self.text = u''
+        self.currentparagraph = u''
+        self.headingtext = u''
+        self.blockquote = u''
         self.inpre = False
+        self.inul = False
+        self.initem = False
+        self.item = u''
         HTMLParser.__init__(self)
 
     def handle_starttag(self, tag, attrs):
@@ -87,80 +89,174 @@ class HTML2Text(HTMLParser):
             self.inlink = True
         elif tag.lower() == "br":
             if self.inparagraph:
-                self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70)) + "\n"
+                self.text = self.text \
+                    + u'\n'.join( \
+                        textwrap.wrap(self.currentparagraph, 70)) \
+                    + u'\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 = ""
+                self.text = self.text \
+                    + u'\n> ' \
+                    + u'\n> '.join( \
+                        [a.strip() \
+                            for a in textwrap.wrap(self.blockquote, 68) \
+                        ]) \
+                    + u'\n'
+                self.blockquote = u''
             else:
-                self.text = self.text + "\n"
+                self.text = self.text + u'\n'
         elif tag.lower() == "blockquote":
             self.inblockquote = True
-            self.text = self.text + "\n"
+            self.text = self.text + u'\n'
         elif tag.lower() == "p":
             if self.text != "":
-                self.text = self.text + "\n\n"
+                self.text = self.text + u'\n\n'
             if self.inparagraph:
-                self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70))
-            self.currentparagraph = ""
+                self.text = self.text \
+                    + u'\n'.join(textwrap.wrap(self.currentparagraph, 70))
+            self.currentparagraph = u''
             self.inparagraph = True
         elif tag.lower() == "pre":
             self.text = self.text + "\n"
             self.inpre = True
             self.inparagraph = False
             self.inblockquote = False
+        elif tag.lower() == "ul":
+            self.item = u''
+            self.inul = True
+            self.text = self.text + "\n"
+        elif tag.lower() == "li" and self.inul:
+            if not self.initem:
+                self.initem = True
+                self.item = u''
+            else:
+                self.text = self.text \
+                    + u' * ' \
+                    + u'\n   '.join([a.strip() for a in \
+                        textwrap.wrap(self.item, 67)]) \
+                    + u'\n'
+                self.item = u''
 
     def handle_startendtag(self, tag, attrs):
         if tag.lower() == "br":
             if self.inparagraph:
-                self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70)) + "\n"
-                self.currentparagraph = ""
+                self.text = self.text \
+                + u'\n'.join( \
+                    [a \
+                        for a in textwrap.wrap( \
+                            self.currentparagraph, 70) \
+                    ] \
+                ) \
+                + u'\n'
+                self.currentparagraph = u''
             elif self.inblockquote:
-                self.text = self.text + "\n> " + "\n> ".join([a.strip() for a in textwrap.wrap(self.blockquote, 68)]) + "\n"
-                self.blockquote = ""
+                self.text = self.text \
+                    + u'\n> ' \
+                    + u'\n> '.join( \
+                        [a \
+                            for a in textwrap.wrap( \
+                                self.blockquote.encode("utf-8") \
+                                , 68) \
+                        ] \
+                    ) \
+                    + u'\n'
+                self.blockquote = u''
             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 = ""
+            self.text = self.text \
+                + u'\n\n' \
+                + self.headingtext.encode("utf-8") \
+                + u'\n' \
+                + u'=' * len(self.headingtext.encode("utf-8").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 = ""
+            self.text = self.text \
+                + u'\n\n' \
+                + self.headingtext.encode("utf-8") \
+                + u'\n' \
+                + u'-' * len(self.headingtext.encode("utf-8").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 = ""
+            self.text = self.text \
+                + u'\n\n' \
+                + self.headingtext.encode("utf-8") \
+                + u'\n' \
+                + u'~' * len(self.headingtext.encode("utf-8").strip())
+            self.headingtext = u''
         elif tag.lower() == "p":
-            self.text = self.text + "\n".join(textwrap.wrap(self.currentparagraph, 70))
+            self.text = self.text \
+                + u'\n'.join(textwrap.wrap( \
+                    self.currentparagraph, 70) \
+                )
             self.inparagraph = False
+            self.currentparagraph = u''
         elif tag.lower() == "blockquote":
-            self.text = self.text + "\n> " + "\n> ".join([a.strip() for a in textwrap.wrap(self.blockquote, 68)]) + "\n"
+            self.text = self.text \
+                + u'\n> ' \
+                + u'\n> '.join( \
+                    [a.strip() \
+                        for a in textwrap.wrap( \
+                            self.blockquote, 68)] \
+                    ) \
+                + u'\n'
             self.inblockquote = False
-            self.blockquote = ""
+            self.blockquote = u''
         elif tag.lower() == "pre":
             self.inpre = False
+        elif tag.lower() == "li":
+            self.initem = False
+            if self.item != "":
+                self.text = self.text \
+                    + u' * ' \
+                    + u'\n   '.join( \
+                        [a.strip() for a in textwrap.wrap(self.item, 67)]) \
+                    + u'\n'
+            self.item = u''
+        elif tag.lower() == "ul":
+            self.inul = False
 
     def handle_data(self, data):
         if self.inheadingone or self.inheadingtwo or self.inotherheading:
-            self.headingtext = self.headingtext + data.strip() + " "
+            self.headingtext = self.headingtext \
+                + unicode(data, "utf-8").strip() \
+                + u' '
         elif self.inblockquote:
-            self.blockquote = self.blockquote + data.strip() + " "
+            self.blockquote = self.blockquote \
+                + unicode(data, "utf-8").strip() \
+                + u' '
         elif self.inparagraph:
-            self.currentparagraph = self.currentparagraph + data.strip() + " "
+            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 + data
+            self.text = self.text + unicode(data, "utf-8")
         else:
-            self.text = self.text + data.strip() + " "
+            self.text = self.text + unicode(data, "utf-8").strip() + u' '
 
     def handle_entityref(self, name):
+        entity = name
         if entities.has_key(name.lower()):
-            self.text = self.text + entities[name.lower()]
+            entity = entities[name.lower()]
+        elif name[0] == "#":
+            entity = unichr(int(name[1:]))
+        else:
+            entity = "&" + name + ";"
+
+        if self.inparagraph:
+            self.currentparagraph = self.currentparagraph \
+                + unicode(entity, "utf-8")
+        elif self.inblockquote:
+            self.blockquote = self.blockquote + unicode(entity, "utf-8")
         else:
-            self.text = self.text + "&" + name + ";"
+            self.text = self.text + unicode(entity, "utf-8")
 
     def gettext(self):
         data = self.text
@@ -169,7 +265,6 @@ class HTML2Text(HTMLParser):
         return data
 
 def parse_and_deliver(maildir, url, statedir):
-    md = mailbox.Maildir(maildir)
     fp = feedparser.parse(url)
     db = dbm.open(os.path.join(statedir, "seen"), "c")
     for item in fp["items"]:
@@ -181,7 +276,7 @@ def parse_and_deliver(maildir, url, statedir):
         else:
             content = item["summary"]
 
-        md5sum = md5.md5(content.encode("utf8")).hexdigest()
+        md5sum = md5.md5(content.encode("utf-8")).hexdigest()
 
         if db.has_key(url + "|" + item["link"]):
             data = db[url + "|" + item["link"]]
@@ -196,27 +291,42 @@ def parse_and_deliver(maildir, url, statedir):
 
         # create a basic email message
         msg = MIMEMultipart("alternative")
-        messageid = "<" + datetime.datetime.now().strftime("%Y%m%d%H%M") + "." + "".join([random.choice(string.ascii_letters + string.digits) for a in range(0,6)]) + "@" + socket.gethostname() + ">"
+        messageid = "<" \
+            + datetime.datetime.now().strftime("%Y%m%d%H%M") \
+            + "." \
+            + "".join( \
+                [random.choice( \
+                    string.ascii_letters + string.digits \
+                    ) for a in range(0,6) \
+                ]) + "@" + socket.gethostname() + ">"
         msg.add_header("Message-ID", messageid)
         msg.set_unixfrom("\"%s\" <rss2maildir@localhost>" %(url))
         msg.add_header("From", "\"%s\" <rss2maildir@localhost>" %(author))
         msg.add_header("To", "\"%s\" <rss2maildir@localhost>" %(url))
-        createddate = datetime.datetime(*item["updated_parsed"][0:6]).strftime("%a, %e %b %Y %T -0000")
+        createddate = datetime.datetime(*item["updated_parsed"][0:6]) \
+            .strftime("%a, %e %b %Y %T -0000")
         msg.add_header("Date", createddate)
         msg.add_header("Subject", item["title"])
         msg.set_default_type("text/plain")
 
-        htmlpart = MIMEText(content.encode("utf8"), "html", "utf8")
+        htmlpart = MIMEText(content.encode("utf-8"), "html", "utf-8")
         textparser = HTML2Text()
-        textparser.feed(content.encode("utf8"))
+        textparser.feed(content.encode("utf-8"))
         textcontent = textparser.gettext()
-        textpart = MIMEText(textcontent, "plain", "utf8")
+        textpart = MIMEText(textcontent.encode("utf-8"), "plain", "utf-8")
         msg.attach(textpart)
         msg.attach(htmlpart)
 
         # start by working out the filename we should be writting to, we do
         # this following the normal maildir style rules
-        fname = str(os.getpid()) + "." + socket.gethostname() + "." + "".join([random.choice(string.ascii_letters + string.digits) for a in range(0,10)]) + "." + datetime.datetime.now().strftime('%s')
+        fname = str(os.getpid()) \
+            + "." + socket.gethostname() \
+            + "." + "".join( \
+                [random.choice( \
+                    string.ascii_letters + string.digits \
+                    ) for a in range(0,10) \
+                ]) + "." \
+            + datetime.datetime.now().strftime('%s')
         fn = os.path.join(maildir, "tmp", fname)
         fh = open(fn, "w")
         fh.write(msg.as_string())
@@ -227,7 +337,11 @@ def parse_and_deliver(maildir, url, statedir):
         os.unlink(fn)
 
         # now add to the database about the item
-        data = urllib.urlencode((("message-id", messageid), ("created", createddate), ("contentmd5", md5sum)))
+        data = urllib.urlencode((
+            ("message-id", messageid), \
+            ("created", createddate), \
+            ("contentmd5", md5sum) \
+            ))
         db[url + "|" + item["link"]] = data
 
     db.close()
@@ -257,7 +371,8 @@ if options.conf != None:
         configfile = options.conf
     except:
         # should exit here as the specified file doesn't exist
-        sys.stderr.write("Config file %s does not exist. Exiting.\n" %(options.conf,))
+        sys.stderr.write( \
+            "Config file %s does not exist. Exiting.\n" %(options.conf,))
         sys.exit(2)
 else:
     # check through the default locations
@@ -286,7 +401,8 @@ if options.statedir != None:
     try:
         mode = os.stat(state_dir)[stat.ST_MODE]
         if not stat.S_ISDIR(mode):
-            sys.stderr.write("State directory (%s) is not a directory\n" %(state_dir))
+            sys.stderr.write( \
+                "State directory (%s) is not a directory\n" %(state_dir))
             sys.exit(1)
     except:
         # try to make the directory
@@ -300,7 +416,8 @@ elif scp.has_option("general", "state_dir"):
     try:
         mode = os.stat(state_dir)[stat.ST_MODE]
         if not stat.S_ISDIR(mode):
-            sys.stderr.write("State directory (%s) is not a directory\n" %(state_dir))
+            sys.stderr.write( \
+                "State directory (%s) is not a directory\n" %(state_dir))
             sys.exit(1)
     except:
         # try to create it
@@ -308,19 +425,22 @@ elif scp.has_option("general", "state_dir"):
             os.mkdir(new_state_dir)
             state_dir = new_state_dir
         except:
-            sys.stderr.write("Couldn't create state directory %s\n" %(new_state_dir))
+            sys.stderr.write( \
+                "Couldn't create state directory %s\n" %(new_state_dir))
             sys.exit(1)
 else:
     try:
         mode = os.stat(state_dir)[stat.ST_MODE]
         if not stat.S_ISDIR(mode):
-            sys.stderr.write("State directory %s is not a directory\n" %(state_dir))
+            sys.stderr.write( \
+                "State directory %s is not a directory\n" %(state_dir))
             sys.exit(1)
     except:
         try:
             os.mkdir(state_dir)
         except:
-            sys.stderr.write("State directory %s could not be created\n" %(state_dir))
+            sys.stderr.write( \
+                "State directory %s could not be created\n" %(state_dir))
             sys.exit(1)
 
 if scp.has_option("general", "maildir_root"):
@@ -329,7 +449,9 @@ if scp.has_option("general", "maildir_root"):
 try:
     mode = os.stat(maildir_root)[stat.ST_MODE]
     if not stat.S_ISDIR(mode):
-        sys.stderr.write("Maildir Root %s is not a directory\n" %(maildir_root))
+        sys.stderr.write( \
+            "Maildir Root %s is not a directory\n" \
+            %(maildir_root))
         sys.exit(1)
 except:
     try:
@@ -390,7 +512,9 @@ for section in feeds:
             os.mkdir(os.path.join(maildir, "cur"))
             os.mkdir(os.path.join(maildir, "tmp"))
         except:
-            sys.stderr.write("Couldn't create required maildir directories for %s\n" %(section,))
+            sys.stderr.write( \
+                "Couldn't create required maildir directories for %s\n" \
+                %(section,))
             sys.exit(1)
 
     # right - we've got the directories, we've got the section, we know the