[kovidgoyal]

from calibre import walk

for path in walk('.'):
   if os.path.splitext(path)[1:].lower() in ('html', 'htm'):
       with open(path, 'r+b') as f:
           raw = f.read()
           raw = raw.decode('utf-8')
           for pat, func in self.preprocess_regexps:
                 raw = pat.sub(func, raw)
           f.seek(0)
           f.truncate()
           f.write(raw.encode('utf-8'))

This will need some adjustments, of course.