[PYTHON] 크롤링 Parsing (BeautifulSoup)

 

 

 

- 네이버 웹툰 제목 가져오기

 

result = get_html('https://comic.naver.com/webtooon/list.nhn?titleld=557672')
table = parse.select_one('table.viewList')
trs= table.select('tr')
for tr in trs:
	title = tr.select_one('td.title>a')
    if title:
    	print(title.get('href'))
        print(title.getText().replace('\n',''), end=' // ')
    num = tr.select_one('.num')
    if num:
    	print(num.getText())

 

 

- 네이버TV 검색결과 가져오기

import requests
from bs4 import BeautifulSoup as bs

address = 'https://tv.naver.com/search?query=낚시&page=1'
res = requests.get(address)
res.encoding = 'utf-8' 			#인코딩 처리 필수

result = res.text
parse = bs(result, 'html.parser')
a_list = parse.select('#clip_list .inner a')
for a in a_list:
    print(a.text)

print()

import requests

address = 'https://movie.naver.com/movie/sdb/rank/rmovie.nhn'
res = requests.get(address)
res.encoding = None

parse = bs(res.text, 'html.parser')
a_list = parse.select('.title > .tit3 > a')	  #'.'->class를 선택자로 지정시 사용, '#'-> ID
for a in a_list:
    print(a.getText())

print()