[텍스트기반 데이터 분석]워드 클라우드 과제 제출

[이민규]

# 잡코리아 크롤링

from urllib.request import urlopen
from bs4 import BeautifulSoup
import openpyxl

def search():
    url = f'https://www.jobkorea.co.kr/Search/?stext=it' 
    src1 = urlopen(url).read() 
    src2 =  BeautifulSoup(src1,'html.parser')
    src3 = src2.select('p.etc')
    
    with open('it','a',encoding="utf-8") as f:
        for i in src3:
            print(i.text)

if __name__ == '__main__':
    search()

* 결과물 *

# 모델 시각화

from wordcloud import WordCloud
import matplotlib.pyplot as plt


def word():
    text = open('C:/Users/pc346/Desktop/xxxx2.txt',encoding='UTF8').read()
    wordcloud = WordCloud(font_path='C:/Users/pc346/Desktop/nanum-gothic/NanumGothic.ttf', background_color='white').generate(text)
    wordcloud.to_file('it.png')

    plt.figure(figsize=(22,22)) #이미지 사이즈 지정
    plt.imshow(wordcloud, interpolation='lanczos') #이미지의 부드럽기 정도
    plt.axis('off') #x y 축 숫자 제거
    plt.show()
    
if __name__ == '__main__':
    word()

* 결과물 *