# -*- coding: utf-8 -*- """전북(14)+제주(2) 공공누리(O열) 권위 재판정 — 충청도 _recheck_kogl_all.py 방식. _jeonbuk_phase234_all 의 검출 로직(get_body/detect_form/extract_detail_urls/KOGL_LINK_PAT)을 그대로 재사용. 각 부착 행을 재크롤링하여: 1) O열 = 이미지명(img_opentype/opencode) 유형 우선 권위 재판정 2) 이미지 존재 & 이미지≠링크 → S열 비고 '링크주소 오기' 3) 링크만 있고 1·2·3·4 전부 → 범례페이지로 미부착 규칙: feedback_kogl_image_rule. 상세추적은 같은 기관 도메인만. 사용: python -X utf8 _recheck_kogl_jeonbuk.py [기관명 ...] """ import sys, os, re, shutil, warnings, openpyxl from concurrent.futures import ThreadPoolExecutor from urllib.parse import urlparse sys.path.insert(0, r'D:\01.프로젝트\DB수집\_스크립트') sys.stdout.reconfigure(encoding='utf-8') warnings.filterwarnings('ignore') import _jeonbuk_phase234_all as JB O_COL, K_COL, S_COL = 15, 11, 19 WORKERS = 12 DETAIL_TIMEOUT = 5 DETAIL_LIMIT = 3 # (기관명, weak_ssl) — xlsx/body_sel 은 JB.SITES 에서 가져옴 TARGETS = [(name, JB.SITES[name].get('weak_ssl', False)) for name in JB.SITES] BROAD_IMG_PAT = re.compile(r'(?:new_)?img_open(?:type|code)(\d{1,2})\.(?:png|jpe?g|gif)', re.I) def _valid(n): return 1 <= n <= 4 def detect_split(body, LINK_PAT): img_t, link_t = set(), set() for a in body.find_all('a', href=True): m = LINK_PAT.search(a['href']) if m and _valid(int(m.group(1))): link_t.add(int(m.group(1))) blob = ' '.join(filter(None, (img.get('src', '') for img in body.find_all('img')))) blob += ' ' + ' '.join(el.get('style', '') for el in body.find_all(style=True)) blob += ' ' + str(body) for m in BROAD_IMG_PAT.finditer(blob): n = int(m.group(1)) if _valid(n): img_t.add(n) return img_t, link_t def decide_O(img_t, link_t): if img_t: newO = ','.join(f'{n}유형' for n in sorted(img_t)) return newO, bool(link_t) and (link_t != img_t) if link_t: if {1, 2, 3, 4}.issubset(link_t): return '미부착', False return ','.join(f'{n}유형' for n in sorted(link_t)), False return '미부착', False def make_fetch(weak_ssl): sess = JB.make_session(weak_ssl) return lambda url, timeout=DETAIL_TIMEOUT: JB.fetch(sess, url, timeout) def _domain(host): labels = (host or '').split('.') return '.'.join(labels[-3:]) if len(labels) >= 3 else host def same_site(base_url, target_url): return _domain(urlparse(base_url).hostname) == _domain(urlparse(target_url).hostname) def detect_row(url, body_sel, fetch_fn): soup = fetch_fn(url) if soup is None: return None, None, 'fetch_fail' body = JB.get_body(soup, body_sel) form, _ = JB.detect_form(body) img_t, link_t = detect_split(body, JB.KOGL_LINK_PAT) if form == '게시판': for du in JB.extract_detail_urls(body, url, limit=DETAIL_LIMIT): if not same_site(url, du): continue ds = fetch_fn(du, DETAIL_TIMEOUT) if ds is None: continue db = JB.get_body(ds, body_sel) di, dl = detect_split(db, JB.KOGL_LINK_PAT) img_t |= di link_t |= dl return img_t, link_t, 'ok' def process_site(name, weak_ssl): cfg = JB.SITES[name] xlsx, body_sel = cfg['xlsx'], cfg['body_sel'] print(f'\n{"="*70}\n■ {name} ({os.path.relpath(xlsx)})') wb = openpyxl.load_workbook(xlsx) ws = wb.active targets = [] for r in range(3, ws.max_row + 1): o = ws.cell(r, O_COL).value if not o or str(o).strip() == '미부착': continue url = ws.cell(r, K_COL).value if url: targets.append((r, str(url).strip(), o, ws.cell(r, S_COL).value)) if not targets: print(' 부착 행 없음 → 변경 없음') return dict(name=name, total=0, o_changed=0, to_none=0, mismatch=0, fetch_fail=0) print(f' 부착 행 {len(targets)}건 재크롤링 (workers={WORKERS}, weak_ssl={weak_ssl})') fetch_fn = make_fetch(weak_ssl) def work(t): r, url, oldO, oldS = t img_t, link_t, status = detect_row(url, body_sel, fetch_fn) return (r, url, oldO, oldS, img_t, link_t, status) results = [] with ThreadPoolExecutor(max_workers=WORKERS) as ex: for res in ex.map(work, targets): results.append(res) o_changed = to_none = mismatch = fetch_fail = 0 for r, url, oldO, oldS, img_t, link_t, status in sorted(results): if status != 'ok': fetch_fail += 1 continue newO, do_flag = decide_O(img_t, link_t) if newO != str(oldO).strip(): o_changed += 1 if newO == '미부착': to_none += 1 ws.cell(r, O_COL).value = newO if do_flag: mismatch += 1 cur = (oldS or '').strip() if '링크주소 오기' not in cur: ws.cell(r, S_COL).value = '링크주소 오기' if not cur else cur + ' / 링크주소 오기' backup = os.path.join(os.path.dirname(xlsx), f'{name}_backup_kogl재판정전.xlsx') if not os.path.exists(backup): shutil.copy2(xlsx, backup) wb.save(xlsx) print(f' ▶ {name} 완료: O변경 {o_changed} (미부착化 {to_none}) | 불일치비고 {mismatch} | fetch실패 {fetch_fail}') return dict(name=name, total=len(targets), o_changed=o_changed, to_none=to_none, mismatch=mismatch, fetch_fail=fetch_fail) def main(): sel = [a for a in sys.argv[1:] if not a.startswith('-')] sites = [t for t in TARGETS if (not sel or t[0] in sel)] print(f'대상 {len(sites)}개: {[s[0] for s in sites]}') summary = [] for name, weak in sites: try: summary.append(process_site(name, weak)) except Exception as e: import traceback; traceback.print_exc() summary.append(dict(name=name, total=-1, o_changed=0, to_none=0, mismatch=0, fetch_fail=0)) print('\n' + '=' * 70 + '\n[전체 요약]') print(f'{"기관":<8}{"부착":>6}{"O변경":>7}{"미부착化":>8}{"불일치":>7}{"실패":>6}') for s in summary: print(f'{s["name"]:<8}{s["total"]:>6}{s["o_changed"]:>7}{s["to_none"]:>8}{s["mismatch"]:>7}{s["fetch_fail"]:>6}') tot = lambda k: sum(x[k] for x in summary if x[k] >= 0) print(f'\n합계: 부착 {tot("total")} | O변경 {tot("o_changed")} | 미부착化 {tot("to_none")} | 불일치비고 {tot("mismatch")} | fetch실패 {tot("fetch_fail")}') if __name__ == '__main__': main()