# -*- coding: utf-8 -*- """서산 bbs_category_list 부모-카테고리 보드 전개 + 카테고리행 L/M/N/O/P/Q(process_row). - 부모판정: leaf라벨이 자기 카테고리에 없음(self-referential 제외) AND 직후행이 이미 카테고리 아님. - 카테고리행: leaf+1열, process_row로 L/M/N/O/P/Q. - 기존 관광지 5행도 O/P/Q 채움. - bottom-up 처리(삽입이 상위행 위치 안흔듦) + 병합재매핑 + 하이퍼링크 전체재구성. 사용: python -X utf8 _서산_카테고리전개.py [--write] """ import sys, os, shutil, importlib.util from urllib.parse import urljoin, urlsplit, parse_qsl, urlencode, urlunsplit import openpyxl from openpyxl.worksheet.hyperlink import Hyperlink def canon(u): sp=urlsplit(u) q=[(k,v) for k,v in parse_qsl(sp.query,keep_blank_values=True) if v] return urlunsplit((sp.scheme,sp.netloc,sp.path,urlencode(sorted(q)),'')) HERE=os.path.dirname(os.path.abspath(__file__)) s=importlib.util.spec_from_file_location('m',os.path.join(HERE,'_chungnam_phase234_all.py')) m=importlib.util.module_from_spec(s); s.loader.exec_module(m) XLSX=r'D:\01.프로젝트\DB수집\작업파일\광역_사이트맵\충청남도\8.서산시\충청남도_서산시.xlsx' BODY=['#contents','#txt','main'] def leaf_col(ws,r): for c in range(10,3,-1): if ws.cell(r,c).value not in (None,''): return c return 4 def get_cats(K): soup=m.fetch(K) if soup is None: return None div=soup.select_one('div.bbs_category_list') if not div: return None out=[] for a in div.find_all('a',href=True): t=(a.get_text() or '').strip() if t: out.append((t,urljoin(K,a['href']))) return out or None # 전체 포함 전체목록(self판정용). 전개때 부모동일URL 제외. def find_parents(ws): res=[] for r in range(3,ws.max_row+1): if ws.cell(r,12).value!='게시판': continue K=ws.cell(r,11).value if not(isinstance(K,str) and K.startswith('http')): continue lc=leaf_col(ws,r); lab=ws.cell(r,lc).value cats=get_cats(K) if not cats: continue cl=[t for t,_ in cats] if lab in cl: continue # 이미 카테고리행(self) if ws.cell(r+1,lc+1).value==cl[0]: continue # 이미 전개됨 res.append((r,lab,lc,cats)) return res def remap_merges(ws, ins, n): ranges=[(x.min_col,x.min_row,x.max_col,x.max_row) for x in list(ws.merged_cells.ranges)] for x in list(ws.merged_cells.ranges): ws.unmerge_cells(str(x)) ws.insert_rows(ins,n) for mc,mr,xc,xr in ranges: if mr>=ins: mr+=n; xr+=n elif xr>=ins: xr+=n ws.merge_cells(start_row=mr,start_column=mc,end_row=xr,end_column=xc) def main(): write='--write' in sys.argv wb=openpyxl.load_workbook(XLSX); ws=wb.active C=None for r in range(3,ws.max_row+1): if ws.cell(r,3).value: C=ws.cell(r,3).value; break parents=find_parents(ws) parents.sort(key=lambda t:-t[0]) # bottom-up print('전개대상 부모보드:',[(lab,len(cats)) for r,lab,lc,cats in sorted(parents,key=lambda t:t[0])]) if not write: for r,lab,lc,cats in sorted(parents,key=lambda t:t[0]): print(' r%d %s(leafcol%d) → %s'%(r,lab,lc,[t for t,_ in cats])) return shutil.copy(XLSX, XLSX.replace('.xlsx','_backup_카테고리전개전.xlsx')) total_new=0 for r,lab,lc,cats in parents: # descending pk=canon(ws.cell(r,11).value) cats=[(t,u) for t,u in cats if canon(u)!=pk] # 전체(부모동일URL) 제외 n=len(cats); ins=r+1 if n==0: continue remap_merges(ws, ins, n) for i,(t,url) in enumerate(cats): rr=ins+i out=m.process_row(url, BODY) ws.cell(rr,3).value=C ws.cell(rr,lc+1).value=t ws.cell(rr,11).value=url ws.cell(rr,12).value=out['L'] or '게시판' ws.cell(rr,13).value=out['M'] if out['M']!='' else 0 ws.cell(rr,14).value=out['N'] ws.cell(rr,15).value=out['O']; ws.cell(rr,16).value=out['P']; ws.cell(rr,17).value=out['Q'] ws.row_dimensions[rr].height=15 ws.merge_cells(start_row=r,start_column=lc,end_row=r+n,end_column=lc) # 부모 leaf 병합 total_new+=n print(' r%d %s +%d행'%(r,lab,n)) # 기존 관광지 5행 O/P/Q 채움 (searchCtgry+bbsNo=617) fixed=0 for r in range(3,ws.max_row+1): K=ws.cell(r,11).value if isinstance(K,str) and 'bbsNo=617' in K and 'searchCtgry=' in K and ws.cell(r,8).value: out=m.process_row(K, BODY) ws.cell(r,14).value=out['N'] ws.cell(r,15).value=out['O']; ws.cell(r,16).value=out['P']; ws.cell(r,17).value=out['Q'] fixed+=1 # 하이퍼링크 전체 재구성 for r in range(3,ws.max_row+1): v=ws.cell(r,11).value; cell=ws.cell(r,11) if isinstance(v,str) and v.startswith('http'): cell.hyperlink=Hyperlink(ref=cell.coordinate,target=v) else: cell.hyperlink=None wb.save(XLSX) print(f'적용: 신규 {total_new}행 · 관광지 O/P/Q채움 {fixed}행 · 하이퍼링크 재구성 · 백업') if __name__=='__main__': main()