Convert numeric entities (`{`) to unicode

numeric_entities_to_utf8.py

#!/usr/bin/python3

# Caution: this will convert everywhere, including inside <script>...</script> or CDATA sections.

import re, os

def numeric_entities_to_utf8(fname):
    s = open(fname, encoding='utf8', newline='').read()
    s = re.sub(r'&#([0-9]+);', lambda m: chr(int(m.group(1))), s)
    with open(fname, 'w', encoding='utf8', newline='') as f:
        f.write(s)

for path, dirs, files in os.walk('.'):
    for fname in files:
        if fname.endswith('.html'):
            numeric_entities_to_utf8(os.path.join(path, fname))