html_unescape.py

#!/usr/bin/env python
# -*- coding: ascii -*-

### Sample Usage: for f in `ls *.md`; do html_unescape.py $f > ok && mv ok $f; done

import sys
import codecs
import HTMLParser
h = HTMLParser.HTMLParser()

def convert_html(filename):
    f = open(filename, "r")
    text = h.unescape( codecs.open(filename, "r", "utf-8").read() )
#    text = h.unescape( f.read() )
    return text.encode('utf-8')

if __name__ == "__main__":
    print convert_html( sys.argv[1] )

Used this to convert the Wordpress export to jekyll / Markdown

Use via base with something to the effect of;
for f in *.md; do html_unescape.py $f > ok && mv ok $f done