[PYTHON] 웹크롤러

from urllib.request import urlopen
from bs4 import BeautifulSoup
 
html = urlopen('http://news.naver.com/main/read.nhn?mode=LSD&mid=shm&sid1=103&sid2=245&oid=020&aid=0003113573')
# html = urlopen('file:///C:/Users/USER/Desktop/songsong.html')
#html = urlopen('https://dak.gg/profile/DeadDE/2017-pre6/krjp')
soup = BeautifulSoup(html, 'lxml')
 
#nameList = soup.find_all('span', {'class': 'red'})
nameList = soup.find_all('h3' ,{'id':'articleTitle'})
nameList_1 = soup.find_all('div' ,{'id':'articleBodyContents'})
#nameList_1 = soup.find_all('span',{'class':'top'})
'''
for name in nameList_1:
    print(name.get_text())
'''
 
 
f = open("저장할 경로 /새파일.txt", 'w')
for name in nameList:
    f.write("기사제목 : " + name.get_text())
 
for name_1 in nameList_1:
    f.write(name_1.get_text())
f.close()