df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
46 lines
2.0 KiB
Python
46 lines
2.0 KiB
Python
# -*- coding: utf-8 -*-
|
|
# 탭 그룹별 '파일에 행으로 없는' 탭아이템(누락) 추출
|
|
import openpyxl, json, io, sys, re
|
|
from urllib.parse import urljoin
|
|
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='utf-8')
|
|
F=r'D:\01.프로젝트\DB수집\작업파일\광역_사이트맵\충청남도\13.청양군\충청남도_청양군.xlsx'
|
|
ws=openpyxl.load_workbook(F).active
|
|
tabs=json.load(open('_cy3_tabs.json',encoding='utf-8'))
|
|
def norm(s): return re.sub(r'\s+','',(s or '')).replace('·','').lower()
|
|
def normurl(u):
|
|
if not u: return ''
|
|
u=u.split('#')[0].rstrip('/')
|
|
return u.replace('https://','').replace('http://','').replace('www.cheongyang.go.kr','').replace('//','/')
|
|
# 기존 행 라벨/URL 집합
|
|
labset=set(); urlset=set()
|
|
for r in range(3,ws.max_row+1):
|
|
for c in (5,6,7,8):
|
|
v=ws.cell(r,c).value
|
|
if v: labset.add(norm(v))
|
|
hl=ws.cell(r,11).hyperlink; u=hl.target if hl else ws.cell(r,11).value
|
|
if u: urlset.add(normurl(u))
|
|
total_missing=0
|
|
out={}
|
|
for rs,g in tabs.items():
|
|
r=int(rs); base=g['u']
|
|
miss=[]
|
|
for t in g['tabs']:
|
|
for it in t['items']:
|
|
lab=it['t']; href=it['href']
|
|
absu=urljoin(base,href) if href else ''
|
|
present = norm(lab) in labset or (absu and normurl(absu) in urlset)
|
|
if not present:
|
|
miss.append({'lab':lab,'href':href,'absu':absu,'blank':it['blank'],'cls':t['cls']})
|
|
if miss:
|
|
# dedup within group by label
|
|
seen=set(); m2=[]
|
|
for x in miss:
|
|
k=norm(x['lab'])
|
|
if k in seen: continue
|
|
seen.add(k); m2.append(x)
|
|
out[rs]={'b':g['b'],'lab':g['lab'],'L':g['L'],'miss':m2}
|
|
total_missing+=len(m2)
|
|
print('r%d B%s %-18s 누락 %d: %s'%(r,g['b'],g['lab'][:18],len(m2),' | '.join('%s%s'%(x['lab'][:16],'(새창)'if x['blank']else'') for x in m2)))
|
|
json.dump(out,open('_cy3_missing.json','w',encoding='utf-8'),ensure_ascii=False,indent=1)
|
|
print('\n누락보유 그룹:',len(out),'| 총 누락아이템:',total_missing)
|