性癖リストを同義語辞書用JSONにする https://dl.dropboxusercontent.com/u/49326509/Propensity.txt

propensity.py

# -*- coding: utf-8 -*-
import json
import fileinput
import re
import codecs


'''
性癖リストを同義語辞書用JSONにする
https://dl.dropboxusercontent.com/u/49326509/Propensity.txt
'''
re_items = re.compile(u'(?P<representative>[^:]+):（(?P<words>[^）]+)）')

if __name__ == '__main__':
    result = {}
    for line in fileinput.input():
        line = line.decode('utf8').strip()
        if not u'（' in line:
            continue
        m = re_items.search(line)
        if m:
            representative = m.group('representative')
            for word in m.group('words').split(', '):
                result[word] = representative
    with codecs.open('propensity.json', 'w', 'utf-8') as fd:
        json.dump(result, fd, indent=4, sort_keys=True, ensure_ascii=False)