파이썬기초88 : 네이버의 특정뉴스를 docx문서로 저장하기

# pip install python-docx 설치

import requests

from bs4 import BeautifulSoup

import docx

#crawling

response = requests.get('http://news.naver.com/main/read.nhn?mode=LSD&mid=shm&sid1=105&oid=277&aid=0003675857')

response.raise_for_status()

soup = BeautifulSoup(response.text, 'html.parser')

title = soup.select('#articleTitle')[0].get_text()

#print(title)

content = soup.select('#articleBodyContents')[0].get_text()

#print(content)

#doc writing

doc = docx.Document()

doc.add_heading(title, 0)

doc.add_paragraph(content)

doc.add_page_break()

doc.save('article.docx')