K-디지털트레이닝(빅데이터) 32일차

오늘은 네이버 기사 검색을 했다.

1. 패키지 불러오기

import requests
from bs4 import BeautifulSoup
import urllib
import re

2. 키워드 입력받기

keyword = input('검색하실 키워드를 입력하세요(ex:커피,코로나...) : ')
keyword1 = urllib.parse.quote(keyword)

3. 10페이지 검색 만들기

for temp in range(1,101,10):
    
    
    url = 'https://search.naver.com/search.naver?where=news&sm=tab_pge&query={0}&start={1}'.format(keyword,temp)
    
    page = requests.get(url)
    html = page.text
    soup = BeautifulSoup(html,'lxml')
    data1 = soup.find('div',{'id':'main_pack'})
    data2 = data1.find_all('div',{'class':'news_area'})
    import re

    result_title = []

    for temp in data2:
        titletemp = temp.find('a',{'class':'news_tit'})
        result_title.append( re.sub('[^A-Za-z0-9가-힣]',' ',titletemp.attrs['title']) )  

    data3 = data1.find_all('a',{'class':'api_txt_lines dsc_txt_wrap'})

    result_desc = []

    for temp in data3:
        result_desc.append(re.sub('[^A-Za-z0-9가-힣]',' ',temp.text))
    
    
    result = []


    for temp in range(0,10):
        temp1 = []
        temp1.append(result_title[temp])
        temp1.append(result_desc[temp])

        result.append(temp1)

f = open('{0}뉴스기사검색.csv'.format(keyword) , 'w')
f.write('제목' +',' + '내용' + '\n')
for temp in result:    
        f.write(temp[0] + ',' + temp[1] + '\n')
f.close()