import requests,re,io from bs4 import BeautifulSoup import urllib3; urllib3.disable_warnings() H={'User-Agent':'Mozilla/5.0'} u="https://www.kdhc.co.kr/kdhc/bbs/B0000020/list.do?menuNo=200124" r=requests.get(u,headers=H,timeout=25,verify=False) s=BeautifulSoup(r.content,'html.parser') # locate '전체게시물' import unicodedata for el in s.find_all(string=re.compile('전체게시물')): parent=el.parent print('전체게시물 parent html:', parent) print('parent text:', parent.get_text(' ',strip=True)) gp=parent.parent print('grandparent text:', gp.get_text(' ',strip=True)[:120]) break # page indicator full for el in s.find_all(string=re.compile(r'\d+\s*/\s*\d+\s*페이지')): print('pageind:',el.strip()) # pagination href pattern for a in s.select('.paging a, .pagination a, a[href*="pageIndex"]')[:5]: print('pag href:',a.get('href'),'txt:',a.get_text(strip=True))