Python\u3067mecab\u3092\u4f7f\u3044\u305f\u304b\u3063\u305f\u306e\u3067\u3059\u304c\u3001\u9762\u5012\u306a\u3053\u3068\u304c\u591a\u3059\u304e\u3066\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u306b\u632b\u6298\u3057\u307e\u3057\u305f\u3002<\/p>\n
\u3068\u3044\u3046\u3053\u3068\u3067\u3001\u79c1\u307f\u305f\u3044\u306a\u300cmecab-python\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u306b\u632b\u6298\u3057\u305f\u4eba\u5411\u3051\u300d\u306e\u30af\u30e9\u30b9\u3092\u66f8\u304d\u307e\u3057\u305f\u306e\u3067\u3001\u4f7f\u3044\u305f\u3044\u4eba\u306f\u4f7f\u3063\u3066\u307f\u3066\u304f\u3060\u3055\u3044\u3002
\n\u6700\u4f4e\u9650\u306e\u6a5f\u80fd\u3057\u304b\u306a\u3044\u3067\u3059\u304c\u3001\u4e00\u5fdc\u3084\u308a\u305f\u3044\u3053\u3068\u306f\u3067\u304d\u308b\u306e\u3067\u306f\u306a\u3044\u3067\u3057\u3087\u3046\u304b\u3002<\/p>\n
<\/p>\n
\u3053\u306e\u8a18\u4e8b\u672b\u5c3e\u306e\u30b3\u30fc\u30c9\u3092\u30b3\u30d4\u30da\u3057\u3066\u300cmecab.py\u300d\u3068\u304b\u540d\u524d\u3092\u4ed8\u3051\u3066\u4fdd\u5b58\u3057\u3066\u3001\u30e2\u30b8\u30e5\u30fc\u30eb\u3068\u3057\u3066\u8aad\u307f\u8fbc\u3093\u3067\u3082\u3089\u3046\u3068\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u4f7f\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n
[python]
\nimport mecab
\nstring = "\u56fd\u5883\u306e\u9577\u3044\u30c8\u30f3\u30cd\u30eb\u3092\u629c\u3051\u308b\u3068\u305d\u3053\u306f\u96ea\u56fd\u3060\u3063\u305f\u3002"
\nm = mecab.Mecab(string)<\/p>\n
# \u305f\u3060\u306e\u5206\u304b\u3061\u66f8\u304d\u306e\u30ea\u30b9\u30c8\u3092\u8fd4\u3059
\nm.wakachi()
\n#=> [‘\u56fd\u5883’, ‘\u306e’, ‘\u9577\u3044’, ‘\u30c8\u30f3\u30cd\u30eb’, ‘\u3092’, ‘\u629c\u3051\u308b’, ‘\u3068’, ‘\u305d\u3053’, ‘\u306f’, ‘\u96ea\u56fd’, ‘\u3060\u3063’, ‘\u305f’, ‘\u3002’]<\/p>\n
# \u666e\u901a\u8868\u8a18\u306e\u30ea\u30b9\u30c8\u3092\u8fd4\u3059
\nm.futsu_hyouki()
\n#=> [‘\u56fd\u5883’, ‘\u306e’, ‘\u9577\u3044’, ‘\u30c8\u30f3\u30cd\u30eb’, ‘\u3092’, ‘\u629c\u3051\u308b’, ‘\u3068’, ‘\u305d\u3053’, ‘\u306f’, ‘\u96ea\u56fd’, ‘\u3060’, ‘\u305f’, ‘\u3002’]
\n[\/python]<\/p>\n
\u3068\u3044\u3046\u611f\u3058\u3067\u3059\u3002
\n\u4eca\u5f8c\u6539\u826f\u3057\u3066\u3044\u3053\u3046\u3068\u601d\u3044\u307e\u3059\u3002<\/p>\n
[python]
\n# -*- coding: utf-8 -*-<\/p>\n
class Mecab:
\n """mecab-python\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u306b\u632b\u6298\u3057\u305f\u4eba\u7528
\n """<\/p>\n
def __init__(self, string=""):
\n self.ma_list = self.cmd_mecab(string)<\/p>\n
def wakachi(self):
\n """\u5206\u304b\u3061\u66f8\u304d\u306e\u7d50\u679c\u3092\u8fd4\u3059(list)
\n """
\n wakachi_list = []
\n for word_ma in self.ma_list:
\n wakachi_list.append(word_ma.split(‘\\t’)[0])
\n return wakachi_list<\/p>\n
def futsu_hyouki(self):
\n """\u666e\u901a\u8868\u8a18\u306e\u7d50\u679c\u3092\u8fd4\u3059(list)
\n """
\n futsu_hyouki_list = []
\n for word_ma in self.ma_list:
\n word, ma_info = word_ma.split(‘\\t’)
\n futsu_hyouki_info = ma_info.split(‘,’)[6]
\n word_futsu = ”
\n if futsu_hyouki_info == ‘*’:
\n word_futsu = word
\n else:
\n word_futsu = futsu_hyouki_info
\n futsu_hyouki_list.append(word_futsu)
\n return futsu_hyouki_list<\/p>\n
def cmd_mecab(self, string=”, opt=”):
\n """
\n Shell\u7d4c\u7531\u3067mecab\u3092\u5b9f\u884c\u3057\u3066\u7d50\u679c\u3092\u53d6\u5f97
\n (\u5f15\u304d\u6570)
\n string str\uff1a \u89e3\u6790\u3057\u305f\u3044\u6587\u5b57\u5217
\n opt str\uff1a mecab\u306e\u89e3\u6790\u30aa\u30d7\u30b7\u30e7\u30f3
\n (\u8fd4\u308a\u5024)
\n stdout str\uff1a \u89e3\u6790\u3057\u305f\u7d50\u679c\u305d\u306e\u307e\u307e
\n """
\n import subprocess
\n cmd = ‘echo %s | mecab’ % string.replace(‘\\n’, ”)
\n p = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
\n stdout_data, stderr_data = p.communicate()
\n stdout = str(stdout_data, encoding=’Shift-JIS’)
\n words_with_ma_info = stdout.split("\\r\\n")
\n words_with_ma_info.remove(‘EOS’)
\n words_with_ma_info.remove(”)
\n return words_with_ma_info
\n[\/python]<\/p>\n","protected":false},"excerpt":{"rendered":"
Python\u3067mecab\u3092\u4f7f\u3044\u305f\u304b\u3063\u305f\u306e\u3067\u3059\u304c\u3001\u9762\u5012\u306a\u3053\u3068\u304c\u591a\u3059\u304e\u3066\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u306b\u632b\u6298\u3057\u307e\u3057\u305f\u3002 \u3068\u3044\u3046\u3053\u3068\u3067\u3001\u79c1\u307f\u305f\u3044\u306a\u300cmecab-python\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb\u306b\u632b\u6298\u3057\u305f\u4eba\u5411\u3051\u300d\u306e\u30af\u30e9\u30b9\u3092\u66f8\u304d\u307e\u3057\u305f\u306e\u3067\u3001\u4f7f\u3044\u305f\u3044\u4eba\u306f\u4f7f […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[30,4,16],"tags":[38],"_links":{"self":[{"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/posts\/787"}],"collection":[{"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/comments?post=787"}],"version-history":[{"count":1,"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/posts\/787\/revisions"}],"predecessor-version":[{"id":788,"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/posts\/787\/revisions\/788"}],"wp:attachment":[{"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/media?parent=787"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/categories?post=787"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/frsw.net\/blog\/wp-json\/wp\/v2\/tags?post=787"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}