X-Git-Url: https://git.sommitrealweird.co.uk/rss2maildir.git/blobdiff_plain/fcaedcaf414720ca8aac9fff2d12c45edd929a43..30903dc148a14cd0f59fb1e40132092e389aec4b:/rss2maildir.py diff --git a/rss2maildir.py b/rss2maildir.py index 59e9361..d36b489 100755 --- a/rss2maildir.py +++ b/rss2maildir.py @@ -137,6 +137,39 @@ class HTML2Text(HTMLParser): u'THORN': u'Þ', u'eth': u'ð', u'ETH': u'Ð', + u'mdash': u'—', + u'ndash': u'–', + u'sect': u'§', + u'para': u'¶', + u'uarr': u'↑', + u'darr': u'↓', + u'larr': u'←', + u'rarr': u'→', + u'dagger': u'†', + u'Dagger': u'‡', + u'permil': u'‰', + u'prod': u'∏', + u'infin': u'∞', + u'radic': u'√', + u'there4': u'∴', + u'int': u'∫', + u'asymp': u'≈', + u'ne': u'≠', + u'equiv': '≡', + u'le': u'≤', + u'ge': u'≥', + u'loz': u'⋄', + u'sum': u'∑', + u'part': u'∂', + u'prime': u'′', + u'Prime': u'″', + u'harr': u'↔', + u'micro': u'µ', + u'not': u'¬', + u'plusmn': u'±', + u'divide': u'÷', + u'cent': u'¢', + u'euro': u'€', } blockleveltags = [ @@ -197,6 +230,9 @@ class HTML2Text(HTMLParser): self.listcount.append(1) self.listlevel = len(self.listcount) - 1 + if tag_name == u'dl': + self.indentlevel = self.indentlevel + 4 + if tag_name in self.liststarttags: smallist = self.opentags[-3:-1] smallist.reverse() @@ -430,12 +466,12 @@ class HTML2Text(HTMLParser): self.text = self.text + u'\n\n' elif len(self.text) > 1 and self.text[-2] != u'\n': self.text = self.text + u'\n' - definition = u' ' * self.indentlevel + definition + "::" - indentstring = u'\n' + u' ' * (self.indentlevel + 1) + definition = u' ' * (self.indentlevel - 4) + definition + "::" + indentstring = u'\n' + u' ' * (self.indentlevel - 3) self.text = self.text \ + indentstring.join( textwrap.wrap(definition, \ - self.textwidth - self.indentlevel - 1)) + self.textwidth - self.indentlevel - 4)) self.curdata = u'' elif tag_thats_done == u'dd': definition = unicode(" ".join( \ @@ -444,13 +480,13 @@ class HTML2Text(HTMLParser): if len(definition) > 0: if len(self.text) > 0 and self.text[-1] != u'\n': self.text = self.text + u'\n' - indentstring = u'\n' + u' ' * (self.indentlevel + 4) + indentstring = u'\n' + u' ' * self.indentlevel self.text = self.text \ - + u' ' * (self.indentlevel + 4) \ + + indentstring \ + indentstring.join( \ textwrap.wrap( \ definition, \ - self.textwidth - self.indentlevel - 4 \ + self.textwidth - self.indentlevel \ ) \ ) self.curdata = u'' @@ -479,8 +515,11 @@ class HTML2Text(HTMLParser): if tag in [u'br', u'img']: return + if tag == u'dl': + self.indentlevel = self.indentlevel - 4 + if tag in self.liststarttags: - if tag in [u'ol', u'dl', u'ul']: + if tag in [u'ol', u'dl', u'ul', u'dd']: self.handle_curdata() # find if there was a previous list level smalllist = self.opentags[:-1] @@ -544,7 +583,7 @@ class HTML2Text(HTMLParser): self.urls = [] if len(self.images.keys()) > 0: self.text = self.text + u'\n.. ' \ - + u'.. '.join( \ + + u'\n.. '.join( \ ["|%s| image:: %s" %(a, self.images[a]["url"]) \ for a in self.images.keys()]) + u'\n' self.images = {}