Export all of the japan characters in the html file into a text file

import codecs

with codecs.open('kantai_collection.html', 'r', 'utf-8') as f:
    data = f.read()
    with codecs.open('kantai_collection.txt', 'w', 'utf-8') as f2:
        for x in data.split('<p>')[1:]:
            f2.write(x.split('</p>')[0] + '\n')