konlpy

src/main/python/kr/co/swh/lecture/opensource/konlpy/konlpy-ex2.py

@@ -1,9 +0,0 @@
-from konlpy.tag import Kkma
-kkma = Kkma()
-
-def tokenize(doc):
-    # norm은 정규화, stem은 근어로 표시하기를 나타냄
-    return ['/'.join(t) for t in kkma.pos(doc)]
-
-tweet = 'RT @marcobonzanini: just an example! :D http://example.com #NLP'
-print(tokenize(tweet))

src/main/python/kr/co/swh/lecture/opensource/konlpy/konlpy-hannanum.py

@@ -0,0 +1,13 @@
+# import os
+# os.environ['_JAVA_OPTIONS'] = '-Xmx1024M'
+# from konlpy import init_jvm
+# init_jvm("<JAVA_HOME>")
+
+from konlpy.tag import Hannanum
+hannanum = Hannanum()
+noun = hannanum.nouns('안녕하세요 SWH코딩학원입니다.')
+print(noun)
+pos = hannanum.pos('안녕하세요 SWH코딩학원입니다.')
+print(pos)
+morph = hannanum.morphs('안녕하세요 SWH코딩학원입니다.')
+print(morph)

src/main/python/kr/co/swh/lecture/opensource/konlpy/konlpy-quiz1.py

@@ -0,0 +1,8 @@
+from konlpy.tag import Kkma
+kkma = Kkma()
+
+def tokenize(doc):
+    return ['/'.join(t) for t in kkma.pos(doc)]
+
+tweet = '초등학생부터 대학생까지 인공지능 교육이 필수화된다. 전 국민의 AI 기본소양을 함양한다는 취지다.'
+print(tokenize(tweet))

src/main/python/kr/co/swh/lecture/opensource/konlpy/user_dic.txt

@@ -1 +0,0 @@
-SWH코딩학원	NNP

src/main/python/kr/co/swh/lecture/opensource/naver/blog.py

@@ -0,0 +1,18 @@
+import os
+import sys
+import urllib.request
+client_id = "OJgN42xxZiJXpnZtCH1j"
+client_secret = "crXggqJhhW"
+encText = urllib.parse.quote("코딩")
+url = "https://openapi.naver.com/v1/search/blog?query=" + encText # json 결과
+# url = "https://openapi.naver.com/v1/search/blog.xml?query=" + encText # xml 결과
+request = urllib.request.Request(url)
+request.add_header("X-Naver-Client-Id",client_id)
+request.add_header("X-Naver-Client-Secret",client_secret)
+response = urllib.request.urlopen(request)
+rescode = response.getcode()
+if(rescode==200):
+    response_body = response.read()
+    print(response_body.decode('utf-8'))
+else:
+    print("Error Code:" + rescode)

src/main/python/kr/co/swh/lecture/opensource/project/naver-blog-nlp-ranking.py

@@ -0,0 +1,42 @@
+from konlpy.tag import Kkma
+import os
+import sys
+import urllib.request
+import json
+import re
+
+def naver_blog_search(client_id, client_secret, text):
+    encText = urllib.parse.quote(text)
+    url = "https://openapi.naver.com/v1/search/blog?query=" + encText # json 결과
+    # url = "https://openapi.naver.com/v1/search/blog.xml?query=" + encText # xml 결과
+    request = urllib.request.Request(url)
+    request.add_header("X-Naver-Client-Id",client_id)
+    request.add_header("X-Naver-Client-Secret",client_secret)
+    response = urllib.request.urlopen(request)
+    rescode = response.getcode()
+    if(rescode==200):
+        response_body = response.read()
+        return response_body.decode('utf-8')
+    else:
+        print("Error Code:" + rescode)
+    
+def striphtml(data):
+    p = re.compile(r'<.*?>')
+    return p.sub('', data)
+
+result = []
+kkma = Kkma()
+naver_result = naver_blog_search('OJgN42xxZiJXpnZtCH1j', 'crXggqJhhW', '코딩')
+y = json.loads(naver_result)
+for b in y['items']:
+    for word, pos in kkma.pos(striphtml(b['description'])):
+        if pos == 'NNG' or pos == 'NNP':
+            result.append(word)
+            
+words = set(result)
+loofWords = list(words)
+countList = []
+for b in loofWords:
+    if result.count(b) > 1:
+        countList.append([b, result.count(b)])
+print(countList)