from playwright.sync_api import sync_playwright import re targets={ '사회공헌위원회(B8,200106)':"https://www.kdhc.co.kr/kdhc/bbs/B0000008/list.do?menuNo=200106", '시민열냉방시설기준(200276)':"https://www.kdhc.co.kr/kdhc/cstmrCnter/arclngFclty/list.do?fcltyParntsSe=02&menuNo=200276", '안전경영방침(B30,200091)':"https://www.kdhc.co.kr/kdhc/bbs/B0000030/list.do?menuNo=200091", '한난사보20-23(200127)':"https://www.kdhc.co.kr/kdhc/prCnter/cyclb/list.do?prTargetSe=2&menuNo=200127", '한난사보-19(200427)':"https://www.kdhc.co.kr/kdhc/prCnter/cyclb/list.do?prTargetSe=3&menuNo=200427", 'FAQ(B10,200271)':"https://www.kdhc.co.kr/kdhc/bbs/B0000010/list.do?menuNo=200271", } with sync_playwright() as p: b=p.chromium.launch() pg=b.new_page() for nm,u in targets.items(): try: pg.goto(u,wait_until='networkidle',timeout=30000) except Exception as e: print(nm,'GOTO ERR',str(e)[:50]); continue body=pg.inner_text('body') pgind=re.search(r'(\d+)\s*/\s*(\d+)\s*페이지',body) tot=re.search(r'전체게시물\s*([\d,]+)',body) # count rows / gallery rows=pg.eval_on_selector_all('table tbody tr','els=>els.length') gal=pg.eval_on_selector_all('.gallery li, [class*=gallery] li, .photo li, [class*=thumb] li','els=>els.length') faq=pg.eval_on_selector_all('dl.faq dt, [class*=faq] dt, [class*=faq] li','els=>els.length') print(f'{nm}: pageind={pgind.groups() if pgind else None} 전체={tot.group(1) if tot else None} rows={rows} gal={gal} faq={faq}') b.close()