言語処理100本ノック

31. 動詞

動詞の表層形をすべて抽出せよ．

import re

sentences = []
with open("D:\\nlp100\\neko.txt.mecab",encoding="UTF-8") as fr:
    line = fr.readline()
    keitaiso = []
    while line:
        if "EOS" in line:
            if len(keitaiso)>0:
                sentences.append(keitaiso)
                keitaiso = []
        else:
            line = re.split(r'[\t,]',line)            
            keitaiso.append({"surface":line[0],"base":line[7],"pos":line[1],"pos1":line[2]})
        line =fr.readline()

for sentence in sentences:
    for word in sentence:
        if word["pos"] == "動詞":
            print(word["surface"])
<結果(一部)>

生れ
つか
し
泣い
し
いる
始め
見
聞く
捕え
煮
食う
思わ
載せ
られ
持ち上げ
られ