# -*- coding: utf-8 -*-
"""장수 N 재판정 (r81~끝). 어문/어문,이미지/영상/오디오/없음. 본문+게시판 상세top10 이미지규칙.
사용: python -X utf8 _장수_N재판정.py [--write]
"""
import sys, os, re, shutil, importlib.util
from concurrent.futures import ThreadPoolExecutor, as_completed
import openpyxl
HERE=os.path.dirname(os.path.abspath(__file__))
s=importlib.util.spec_from_file_location('m',os.path.join(HERE,'_jeonbuk_phase234_all.py'))
M=importlib.util.module_from_spec(s); s.loader.exec_module(M)
XLSX=r'D:\01.프로젝트\DB수집\작업파일\광역_사이트맵\전북특별자치도\11.장수군\전북특별자치도_장수군.xlsx'
import sys as _s; START=int(next((a for a in _s.argv[1:] if a.isdigit()),81)); SESS=M.make_session()
DECO=re.compile(r'/common/|move\.png|no[-_]?img|blank|spacer|/ico|/btn|bullet|arrow|/bg|icon|see_btn|/sample|mimetype|/file_|filedown|btn_dir|/open\d|viewImg|/board/view|_link\d|governing_img|img_open(?:code|type)0[._]|/link\d',re.I)
EXCL=re.compile(r'한눈에|흐름도|절차도|로고(?!송)|logo(?!song)|아이콘|배너|banner|신문고|relation_item|tracer|headline|copyright|copy_logo|popup|wa_mk|웹접근성|품질인증|전용뷰어|뷰어로보기|바로가기|생활법령|전자관보|정보시스템',re.I)
AUDIO=re.compile(r'\.(?:mp3|wav|m4a|ogg|flac)\b',re.I)
MAPPDF=re.compile(r'pdf|viewer\.html|/map|kakao|daum.*map',re.I)
DETAIL=re.compile(r'view\.|/view\b|articleNo=|dataSid=|nttId=|not_ancmt|bbsView|seqRepeat=|mode=V|idx=|seq=',re.I)
EMPTY=re.compile(r'게시물이?\s*없|등록된?\s*(?:게시물|자료|글)\s*가?\s*없|검색된\s*(?:게시물|결과)\s*가?\s*없')
def realimg(b):
    for img in b.find_all('img'):
        src=img.get('src') or ''
        if not src or M.KOGL_IMG_PAT.search(src) or DECO.search(src): continue
        if EXCL.search(src+' '+(img.get('alt') or '')): continue
        return True
    return False
def media(b):
    t=len(b.get_text(strip=True))>30; img=realimg(b); vid=False
    for ifr in b.find_all('iframe'):
        ss=ifr.get('src') or ''
        if M.YOUTUBE_PAT.search(ss): vid=True
        elif MAPPDF.search(ss): img=True
    if not vid and (b.find('video') or b.find('a',href=M.YOUTUBE_PAT) or M.VIDEO_EXT.search(str(b))): vid=True
    aud=bool(b.find('audio')) or bool(AUDIO.search(str(b)))
    return img,vid,aud,t
def detail_urls(b,base,lim=10):
    from urllib.parse import urljoin
    out=[];seen=set()
    for a in b.find_all('a',href=True):
        h=a['href']
        if h and not h.startswith('#') and DETAIL.search(h):
            f=urljoin(base,h)
            if f not in seen: seen.add(f);out.append(f)
            if len(out)>=lim: break
    return out
def njoin(t,i,v,a):
    p=[]
    if t:p.append('어문')
    if i:p.append('이미지')
    if v:p.append('영상')
    if a:p.append('오디오')
    return ','.join(p) if p else '없음'
def judge(K,L):
    soup=None
    for _ in range(3):
        soup=M.fetch(SESS,K)
        if soup is not None: break
    if soup is None: return None
    b=M.get_body(soup,M.BODY_SEL); txt=b.get_text(' ',strip=True)
    img,vid,aud,t=media(b)
    if L=='게시판':
        dus=detail_urls(b,K,10)
        if not dus and (EMPTY.search(txt) or not t): return '없음'
        for du in dus:
            ds=M.fetch(SESS,du)
            if not ds: continue
            db=M.get_body(ds,M.BODY_SEL)
            i2,v2,a2,t2=media(db); img=img or i2;vid=vid or v2;aud=aud or a2;t=t or t2
    return njoin(t,img,vid,aud)
def main():
    write='--write' in sys.argv
    wb=openpyxl.load_workbook(XLSX); ws=wb.active
    jobs=[(r,ws.cell(r,11).value,ws.cell(r,12).value) for r in range(START,ws.max_row+1)
          if isinstance(ws.cell(r,11).value,str) and ws.cell(r,11).value.startswith('http') and ws.cell(r,12).value in ('페이지','게시판')]
    res={}
    with ThreadPoolExecutor(max_workers=6) as ex:
        futs={ex.submit(judge,K,L):r for r,K,L in jobs}
        for f in as_completed(futs):
            r=futs[f]
            try: res[r]=f.result()
            except: res[r]=None
    chg=[]
    for r in sorted(res):
        n=res[r]
        if n is None: continue
        old=ws.cell(r,14).value
        if n!=(old or ''): chg.append((r,old,n))
    print('N변경 %d행:'%len(chg))
    for r,o,n in chg[:60]: print('  r%d %s: %s→%s'%(r,ws.cell(r,7).value or ws.cell(r,6).value,o,n))
    if write and chg:
        shutil.copy(XLSX,XLSX.replace('.xlsx','_backup_N재판정전.xlsx'))
        for r,o,n in chg: ws.cell(r,14).value=n
        wb.save(XLSX); print('적용 %d행'%len(chg))
if __name__=='__main__': main()