yahoo_hurigana.py

# coding: utf-8

import requests 
import xmltodict
import fileinput

def getAccess(url, **option):
    r = requests.get(url, params=option)
    return r.text

def addReplaceWord(replaceList,word,begin="$",sep="#",end="$"):
    if word['Surface'] != word['Furigana']:
        rubytext = "%s%s%s%s%s" % (begin,word['Surface'],sep,word['Furigana'],end)
        replaceList[word['Surface']] = rubytext
    return replaceList

def replace(sentence,begin="$",sep="#",end="$"):
    url = "http://jlp.yahooapis.jp/FuriganaService/V1/furigana"
    appid = "XXXXXXXXXXXXXXXXXXXXXXXXX"
    ret = getAccess(url,appid=appid,sentence=sentence,grade=1)
    tmp = xmltodict.parse(ret)
    replaceList = {}
    if 'ResultSet' in tmp:
        for val in (tmp['ResultSet']['Result']['WordList']['Word']):
            if 'SubWordList' in val:
                for subword in val['SubWordList']['SubWord']:
                    replaceList = addReplaceWord(replaceList,subword,begin,sep,end)
            elif 'Furigana' in val:
                replaceList = addReplaceWord(replaceList,val,begin,sep,end)
    text = sentence
    for k, v in replaceList.items():
        text = text.replace(k,v)
    return text

if __name__ == "__main__":
    for line in fileinput.input():
        line = replace(line)
        line = line.replace("，","、")
        line = line.replace("．","。")
        print(line, end="")