파이썬 크롤링 - 빅데이터 시각화

구글 확장 프로그램 quick javascript switcher

pip install pygame 

pip install simplejson

pip install pytagcloud

한국어 형태소 분석

pip install konlpy

https://www.lfd.uci.edu/~gohlke/pythonlibs

# pip install JPype1-0.6.2-cp36-cp36m-win_amd64.whl # pip install pygame # pip install simplejson # pip install konlpy # pip install jpype """ https://www.lfd.uci.edu/~gohlke/pythonlibs/#jpype 여기서 다운받아 설치하자 """ from collections import Counter from konlpy.tag import Twitter import pytagcloud f = open('blog_data.txt') data = f.read() nlp = Twitter() nouns = nlp.nouns(data) count = Counter(nouns) tags2 = count.most_common(40) taglist = pytagcloud.make_tags(tags2, maxsize=80) pytagcloud.create_tag_image(taglist, 'wordcloud.jpg', size=(900, 600), fontname='Korean', rectangular=False) f.close()

#-*- coding:utf-8 -*-

"""

pip install lxml

pip install wordcloud

pip install pytagcloud

pip install pygame

pip install simplejson

"""

from collections import Counter

import pytagcloud

import webbrowser

"""

Counter - list타입 단어 많이넣어놓으면

Couter 로 객체를 만들면

korea 5

america 12

dic 형태로 전환

pytagcloud - 워드클라우드 차트 생성 라이브러리

webbrowser - 웹 브라우저 여는 프로그램

"""

words = list()

words.extend(['korea' for t in range(8)])

words.extend(['beautiful' for t in range(3)])

words.extend(['flower' for t in range(7)])

words.extend(['cloud' for t in range(23)])

words.extend(['rose' for t in range(8)])

words.extend(['lily' for t in range(4)])

words.extend(['apple' for t in range(5)])

words.extend(['orange' for t in range(9)])

words.extend(['rainbow' for t in range(45)])

words.extend(['rain' for t in range(14)])

words.extend(['snow' for t in range(27)])

words.extend(['puppy' for t in range(5)])

words.extend(['one' for t in range(5)])

words.extend(['lion' for t in range(5)])

words.extend(['cat' for t in range(52)])

words.extend(['tree' for t in range(51)])

words.extend(['pink' for t in range(45)])

words.extend(['brown' for t in range(35)])

words.extend(['gold' for t in range(25)])

words.extend(['silver' for t in range(15)])

words.extend(['green' for t in range(15)])

words.extend(['president' for t in range(5)])

words.extend(['moon' for t in range(25)])

words.extend(['river' for t in range(15)])

words.extend(['sun' for t in range(5)])

words.extend(['sunflower' for t in range(5)])

words.extend(['two' for t in range(19)])

words.extend(['three' for t in range(21)])

words.extend(['four' for t in range(17)])

words.extend(['five' for t in range(16)])

words.extend(['six' for t in range(9)])

words.extend(['seven' for t in range(8)])

words.extend(['nine' for t in range(54)])

words.extend(['ten' for t in range(45)])

words.extend(['june' for t in range(56)])

words.extend(['july' for t in range(57)])

print(words)

count = Counter(words)

print(count)

#위의 단어들 중에서 상위 20개만 가져다

#차트 그리겠다

tag = count.most_common(100)

taglist = pytagcloud.make_tags(tag,

maxsize=100)

print(taglist)

#차트 그리기

pytagcloud.create_tag_image(taglist,

"image1.jpg", size=(900,600),

fontname='Nobile',

rectangular=False)

webbrowser.open("image1.jpg")

WordCloud

http://pinkwink.kr/1029