df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
46 lines
2.2 KiB
Python
46 lines
2.2 KiB
Python
import sys, io
|
|
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
|
|
import openpyxl
|
|
PKG = r'D:\01.프로젝트\DB수집\작업파일\_제출패키지_2026-06-03\프리랜서1\충청남도_부여군.xlsx'
|
|
wb = openpyxl.load_workbook(PKG); ws = wb.active
|
|
|
|
# rows where K has URL but L/ or where M/N/O blank on 게시판/페이지
|
|
print('=== content rows with missing L(형태) ===')
|
|
for r in range(3, ws.max_row+1):
|
|
if ws.cell(r,2).value in (None,''): continue
|
|
k=ws.cell(r,11).value; l=ws.cell(r,12).value
|
|
if (k not in (None,'')) and (l in (None,'')):
|
|
print(f' r{r} B={ws.cell(r,2).value} K={k!r} L={l!r}')
|
|
|
|
print('\n=== L distribution + M/N/O blanks ===')
|
|
from collections import Counter
|
|
lc=Counter()
|
|
mblank=[]; nblank=[]
|
|
for r in range(3, ws.max_row+1):
|
|
if ws.cell(r,2).value in (None,''): continue
|
|
l=ws.cell(r,12).value; lc[l]+=1
|
|
m=ws.cell(r,13).value; n=ws.cell(r,14).value
|
|
if l in ('페이지','게시판') and m in (None,''): mblank.append(r)
|
|
if l in ('페이지','게시판') and n in (None,''): nblank.append(r)
|
|
print('L:', dict(lc))
|
|
print('M blank(페이지/게시판):', len(mblank), mblank[:20])
|
|
print('N blank(페이지/게시판):', len(nblank), nblank[:20])
|
|
|
|
# single-row D/E/F merges & gaps: list D merges to see grouping
|
|
print('\n=== D-column merges (메뉴명 groups) ===')
|
|
dm=sorted([m for m in ws.merged_cells.ranges if m.min_col==4 and m.min_row>=3], key=lambda x:x.min_row)
|
|
prev_end=2
|
|
for m in dm:
|
|
gap = '' if m.min_row==prev_end+1 else f' <-- GAP rows {prev_end+1}..{m.min_row-1}'
|
|
print(f' D{m.min_row}:{m.max_row} = {ws.cell(m.min_row,4).value!r}{gap}')
|
|
prev_end=m.max_row
|
|
# rows after last D merge
|
|
if prev_end < ws.max_row:
|
|
# check if remaining rows have D values (single-cell, unmerged)
|
|
rem=[r for r in range(prev_end+1, ws.max_row+1) if ws.cell(r,2).value not in (None,'')]
|
|
print(f' (rows after last D-merge: {rem[:10]} ... {len(rem)} rows, D values e.g. {[ws.cell(r,4).value for r in rem[:5]]})')
|
|
|
|
print('\n=== row heights anomaly (non-15) ===')
|
|
hh=[(r, ws.row_dimensions[r].height) for r in range(1, ws.max_row+1) if ws.row_dimensions[r].height not in (15, None)]
|
|
print('non-15 heights:', len(hh), hh[:20])
|