質問編集履歴
2
ご回答いただいたコードを完成させ実行した結果の追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -118,6 +118,96 @@
|
|
|
118
118
|
|
|
119
119
|
|
|
120
120
|
|
|
121
|
+
###ご回答いただいたコードを完成させ実行した結果
|
|
122
|
+
|
|
123
|
+
ご回答いただいたコード
|
|
124
|
+
|
|
125
|
+
```python
|
|
126
|
+
|
|
127
|
+
import sys
|
|
128
|
+
|
|
129
|
+
import MeCab
|
|
130
|
+
|
|
131
|
+
import mojimoji
|
|
132
|
+
|
|
133
|
+
|
|
134
|
+
|
|
135
|
+
STOP_POS = {
|
|
136
|
+
|
|
137
|
+
('名詞', '副詞可能', '*'),
|
|
138
|
+
|
|
139
|
+
('名詞', '非自立', '副詞可能'),
|
|
140
|
+
|
|
141
|
+
('名詞', '非自立', '一般'),
|
|
142
|
+
|
|
143
|
+
('名詞', '接尾', '副詞可能'),
|
|
144
|
+
|
|
145
|
+
('名詞', '接尾', '助数詞'),
|
|
146
|
+
|
|
147
|
+
('名詞', '数', '*'),
|
|
148
|
+
|
|
149
|
+
}
|
|
150
|
+
|
|
151
|
+
|
|
152
|
+
|
|
153
|
+
def han2zen(text):
|
|
154
|
+
|
|
155
|
+
text = mojimoji.han_to_zen(text)
|
|
156
|
+
|
|
157
|
+
return text
|
|
158
|
+
|
|
159
|
+
|
|
160
|
+
|
|
161
|
+
def extractKeyword(text):
|
|
162
|
+
|
|
163
|
+
tagger = MeCab.Tagger('-Ochasen')
|
|
164
|
+
|
|
165
|
+
tagger.parse('')
|
|
166
|
+
|
|
167
|
+
node = tagger.parseToNode(han2zen(text))
|
|
168
|
+
|
|
169
|
+
keywords = []
|
|
170
|
+
|
|
171
|
+
while node:
|
|
172
|
+
|
|
173
|
+
features = tuple(node.feature.split(","))
|
|
174
|
+
|
|
175
|
+
if features[0] == u"名詞" and features[:3] not in STOP_POS:
|
|
176
|
+
|
|
177
|
+
keywords.append(node.surface)
|
|
178
|
+
|
|
179
|
+
elif features[0] == u"形容詞" and features[1] == u"自立":
|
|
180
|
+
|
|
181
|
+
keywords.append(node.surface)
|
|
182
|
+
|
|
183
|
+
elif features[0] == u"動詞" and features[1] == u"自立":
|
|
184
|
+
|
|
185
|
+
keywords.append(node.surface)
|
|
186
|
+
|
|
187
|
+
node = node.next
|
|
188
|
+
|
|
189
|
+
return keywords
|
|
190
|
+
|
|
191
|
+
|
|
192
|
+
|
|
193
|
+
text = "ドライ・アムネシア・バラ（切り花）"
|
|
194
|
+
|
|
195
|
+
extractKeyword(text)
|
|
196
|
+
|
|
197
|
+
```
|
|
198
|
+
|
|
199
|
+
|
|
200
|
+
|
|
201
|
+
結果
|
|
202
|
+
|
|
203
|
+
```
|
|
204
|
+
|
|
205
|
+
['ドライ・アムネシア・バラ', '切り花']
|
|
206
|
+
|
|
207
|
+
````
|
|
208
|
+
|
|
209
|
+
|
|
210
|
+
|
|
121
211
|
### 補足情報（FW/ツールのバージョンなど）
|
|
122
212
|
|
|
123
213
|
Python3.6
|
1
誤字脱字
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -17,8 +17,6 @@
|
|
|
17
17
|
text = "ドライ・アムネシア・バラ(切花)"
|
|
18
18
|
|
|
19
19
|
['ドライ', 'アムネシア', 'バラ', '切花']
|
|
20
|
-
|
|
21
|
-
```
|
|
22
20
|
|
|
23
21
|
```
|
|
24
22
|
|