X-Git-Url: https://git.sommitrealweird.co.uk/rss2maildir.git/blobdiff_plain/629cdfb564c31d54236ba24cd6d891cba1c2308a..e6e6c337ac79ea307329843153e477f5f4f784c8:/rss2maildir.py?ds=inline diff --git a/rss2maildir.py b/rss2maildir.py index 910b8a9..2af32bc 100755 --- a/rss2maildir.py +++ b/rss2maildir.py @@ -70,6 +70,9 @@ class HTML2Text(HTMLParser): u'ul', u'ol', u'dl', + u'li', + u'dt', + u'dd', u'div', #u'blockquote', ] @@ -148,7 +151,7 @@ class HTML2Text(HTMLParser): elif tag_name == u'a': for attr in attrs: if attr[0].lower() == u'href': - self.urls.append(attr[1]) + self.urls.append(attr[1].decode('utf-8')) self.curdata = self.curdata + u'`' self.opentags.append(tag_name) return @@ -180,21 +183,17 @@ class HTML2Text(HTMLParser): url = u'' for attr in attrs: if attr[0] == 'alt': - alt = attr[1] + alt = attr[1].decode('utf-8') elif attr[0] == 'src': - url = attr[1] + url = attr[1].decode('utf-8') if url: self.curdata = self.curdata \ + u' [img:' \ - + unicode( \ - url.encode('utf-8'), \ - 'utf-8') + + url if alt: self.curdata = self.curdata \ + u'(' \ - + unicode( \ - alt.encode('utf-8'), \ - 'utf-8') \ + + alt \ + u')' self.curdata = self.curdata \ + u']' @@ -223,17 +222,20 @@ class HTML2Text(HTMLParser): if self.ignorenodata: newlinerequired = False self.ignorenodata = False - if newlinerequired \ - and len(self.text) > 2 \ - and self.text[-1] != u'\n' \ - and self.text[-2] != u'\n': + if newlinerequired: + if tag_thats_done in [u'dt', u'dd', u'li'] \ + and len(self.text) > 1 \ + and self.text[-1] != u'\n': + self.text = self.text + u'\n' + elif len(self.text) > 2 \ + and self.text[-1] != u'\n' \ + and self.text[-2] != u'\n': self.text = self.text + u'\n\n' if tag_thats_done in ["h1", "h2", "h3", "h4", "h5", "h6"]: underline = u'' underlinechar = u'=' - headingtext = unicode( \ - self.curdata.encode("utf-8").strip(), "utf-8") + headingtext = self.curdata seperator = u'\n' + u' '*self.indentlevel headingtext = seperator.join( \ textwrap.wrap( \ @@ -254,7 +256,7 @@ class HTML2Text(HTMLParser): underline = u' ' * self.indentlevel \ + underlinechar * len(headingtext) self.text = self.text \ - + headingtext.encode("utf-8") + u'\n' \ + + headingtext + u'\n' \ + underline elif tag_thats_done in [u'p', u'div']: paragraph = unicode( \ @@ -411,7 +413,7 @@ class HTML2Text(HTMLParser): def handle_data(self, data): if len(self.opentags) == 0: self.opentags.append(u'p') - self.curdata = self.curdata + unicode(data, "utf-8") + self.curdata = self.curdata + data.decode("utf-8") def handle_entityref(self, name): entity = name @@ -721,11 +723,13 @@ if __name__ == "__main__": elif scp.has_option("general", "state_dir"): new_state_dir = scp.get("general", "state_dir") try: - mode = os.stat(state_dir)[stat.ST_MODE] + mode = os.stat(new_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.exit(1) + else: + state_dir = new_state_dir except: # try to create it try: