Python etc2

1. 링크 넣고 제목 따오기

import requests
from bs4 import BeautifulSoup

html=requests.get('https://entertain.daum.net/ranking/popular').text

html=BeautifulSoup(html,"html.parser")

print(html.find('a',{'class':'link_txt'}).text)

 

2.링크 넣고 제목 다 따오기

import requests
from bs4 import BeautifulSoup

html=requests.get('https://entertain.daum.net/ranking/popular').text

html=BeautifulSoup(html,"html.parser")

news_tit=html.findAll('a',{'class':'link_txt'})

for x in news_tit:
    print(x.text)

 

3. 순위권 안에 제목 가져오기

import requests
from bs4 import BeautifulSoup

html=requests.get('https://entertain.daum.net/ranking/popular').text

html=BeautifulSoup(html,"html.parser")

news_tit=html.findAll('strong',{'class':'tit_thumb'})

for x in news_tit:
    print(x.text)

 

4. 순위권 안에 들어가 제목과 본문 가져오기

import requests
from bs4 import BeautifulSoup
html=requests.get('https://entertain.daum.net/ranking/popular').text
html=BeautifulSoup(html,"html.parser")
news_tit=html.findAll('strong',{'class':'tit_thumb'})
for x in news_tit:
    html=requests.get(x.find('a')['href']).text
    html=BeautifulSoup(html, "html.parser")
    news_tit=html.find('h3',{'class':'tit_view'})
    content=html.find('div',{'class':'article_view'})
    print(news_tit.text) #모니터에 출력
    print(content.text)

 

5. 순위권 안에 들어가 제목과 본문 파일에 저장하기

import requests
from bs4 import BeautifulSoup
html=requests.get('https://entertain.daum.net/ranking/popular').text
html=BeautifulSoup(html,"html.parser")
news_tit=html.findAll('strong',{'class':'tit_thumb'})
nember=1
for x in news_tit:
    file=open("news__"+str(nember)+'.txt','w',encoding='UTF-8')
    number+=1
    html=requests.get(x.find('a')['href']).text
    html=BeautifulSoup(html, "html.parser")
    news_tit=html.find('h3',{'class':'tit_view'})
    content=html.find('div',{'class':'article_view'})
		file.write(news_tit.text) #파일에 출력
    file.write(content.text)
    file.close()

 

6. 날짜마다

import requests
from bs4 import BeautifulSoup
for date in range(20211001,20211031,1):
		html=requests.get('https://entertain.daum.net/ranking/popular?date='+str(date)).text    
		html=BeautifulSoup(html,"html.parser")
    news_tit=html.findAll('div',{'class':'inner_cont2'})
    nember=1
    for x in news_tit:
        file=open(str(date)+'__'+str(nember)+'.txt','w',encoding='UTF-8')
        number+=1
        html=requests.get(x.find('a')['href']).text
        html = BeautifulSoup(html, "html.parser")
        news_tit=html.find('h3',{'class':'tit_view'})
        content=html.find('div',{'class':'article_view'})
        file.write(news_tit.text) #파일에 출력
        file.write(content.text)
        file.close()