df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
60 lines
2.1 KiB
Python
60 lines
2.1 KiB
Python
# -*- coding: utf-8 -*-
|
|
"""조회 전용(저장 안 함): 부착 행 중 이미지(img_opentype) 없이
|
|
링크(licenseType)만 있는 '텍스트 부착' 행의 URL을 시·군별로 나열."""
|
|
import sys, os, openpyxl
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
|
|
sys.path.insert(0, r'D:\01.프로젝트\DB수집\_스크립트')
|
|
sys.stdout.reconfigure(encoding='utf-8')
|
|
|
|
import _recheck_kogl_all as RC
|
|
|
|
O_COL, K_COL = 15, 11
|
|
|
|
|
|
def scan(name, region, weak):
|
|
mod = RC.CN if region == 'cn' else RC.CB
|
|
cfg = RC.get_cfg(name, region)
|
|
xlsx, body_sel = cfg['xlsx'], cfg['body_sel']
|
|
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 o and str(o).strip() != '미부착' and ws.cell(r, K_COL).value:
|
|
targets.append((r, str(ws.cell(r, K_COL).value).strip(), o))
|
|
if not targets:
|
|
return name, []
|
|
fetch_fn = RC.make_fetch(region, weak)
|
|
|
|
def work(t):
|
|
r, url, oldO = t
|
|
img_t, link_t, st = RC.detect_row(url, body_sel, mod, fetch_fn)
|
|
return (r, url, oldO, img_t, link_t, st)
|
|
|
|
out = []
|
|
with ThreadPoolExecutor(max_workers=6) as ex:
|
|
for r, url, oldO, img_t, link_t, st in ex.map(work, targets):
|
|
if st == 'ok' and not img_t and link_t:
|
|
out.append((r, url, str(oldO).strip(), sorted(link_t)))
|
|
return name, sorted(out)
|
|
|
|
|
|
def main():
|
|
sel = [a for a in sys.argv[1:] if not a.startswith('-')]
|
|
sites = [t for t in RC.TARGETS if (not sel or t[0] in sel)]
|
|
grand = 0
|
|
for name, region, weak in sites:
|
|
nm, rows = scan(name, region, weak)
|
|
if rows:
|
|
print(f'\n■ {nm} — 텍스트(링크)만 부착 {len(rows)}건')
|
|
for r, url, oldO, lk in rows:
|
|
print(f' row{r:>3} | 기존O={oldO:<14} | 링크={lk} | {url}')
|
|
grand += len(rows)
|
|
else:
|
|
print(f'■ {nm} — 없음')
|
|
print(f'\n총 텍스트-only 부착 행: {grand}건')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
main()
|