금융감독원 공시에서 첨부파일 스크래핑

금융감독원-공시-첨부파일.py

import requests
from bs4 import BeautifulSoup
import time

for page in range(1, 6):
    url = f"https://www.fss.or.kr/fss/kr/bbs/list.jsp?url=/fss/kr/1207404857348&bbsid=1207404857348&page={page}"
    resp = requests.get(url)

    soup = BeautifulSoup(resp.text, 'html5lib')
    sel = "#contents_area > div.contents > table > tbody > tr > td.tit > a"
    titles = soup.select(sel)
    for tag in titles:
        sub_url = "https://www.fss.or.kr/fss/kr/bbs" + tag['href'][1:]
        resp = requests.get(sub_url)
        soup = BeautifulSoup(resp.text, 'html5lib')

        sel = "#contents_area > div.contents > table:nth-child(1) > tbody > tr:nth-child(3) > td > a"
        links = soup.select(sel)
        for item in links:
            print(item.text.strip())
            file_url = "https://www.fss.or.kr" + item['href']
            print(file_url)

            resp = requests.get(file_url)
            
            with open(item.text.strip(), "wb") as f:
                f.write(resp.content)

        time.sleep(1)