b0acd1e705
- 공공기관2/3 작업본 + 오늘 제출 17곳 D~J 카테고리 셀병합 정상화 - 한국지역난방공사 옵션2(고아셀 F98 수정)+전행 높이17 - 제출_프리랜서2_2026-06-21.zip 생성(17개 xlsx, 2,468행) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
46 lines
2.2 KiB
Python
46 lines
2.2 KiB
Python
# -*- coding: utf-8 -*-
|
|
import openpyxl,sys,urllib.request,ssl,re,bs4,time
|
|
sys.stdout.reconfigure(encoding='utf-8')
|
|
ctx=ssl.create_default_context(); ctx.check_hostname=False; ctx.verify_mode=ssl.CERT_NONE
|
|
def fetch(u,tries=3):
|
|
for i in range(tries):
|
|
try:
|
|
req=urllib.request.Request(u,headers={'User-Agent':'Mozilla/5.0'})
|
|
return urllib.request.urlopen(req,timeout=20,context=ctx).read()
|
|
except Exception as e:
|
|
if i==tries-1: raise
|
|
time.sleep(2)
|
|
def maxnum(soup):
|
|
nums=[]
|
|
for el in soup.select('.b-left-n, td.b-left-n, th.b-left-n'):
|
|
t=el.get_text(strip=True)
|
|
if t.isdigit(): nums.append(int(t))
|
|
return max(nums) if nums else None
|
|
wb=openpyxl.load_workbook('한국청소년활동진흥원.xlsx'); ws=wb.active
|
|
out=[]
|
|
for r in range(3,ws.max_row+1):
|
|
url=ws.cell(r,11).value
|
|
curL=ws.cell(r,12).value
|
|
if not url or not str(url).startswith('http'):
|
|
out.append(f'{r}\tEMPTY/NOURL'); continue
|
|
if 'kywa.or.kr' not in url or url.startswith('https://booking'):
|
|
out.append(f'{r}\tEXT\t{url}'); continue
|
|
try:
|
|
h=fetch(url); soup=bs4.BeautifulSoup(h,'html.parser')
|
|
tc=[(a.get_text(strip=True),a.get('href','')) for a in soup.select('ul.tab-clear li a.tap-setting, ul.tab-clear li a')]
|
|
has_all=any(t[0]=='전체' for t in tc)
|
|
is_content_tab = tc and not has_all and len(tc)>=2 and all('.jsp' in (t[1] or '') for t in tc)
|
|
mx=maxnum(soup)
|
|
gp=[int(x) for x in re.findall(r'go_page\((\d+)\)',h.decode('utf-8','ignore'))]
|
|
lastpg=max(gp) if gp else None
|
|
board = (mx is not None) or has_all or (lastpg and lastpg>1)
|
|
kind='CONTENT_TAB' if is_content_tab else ('CAT_BOARD' if (has_all or board) else 'PAGE')
|
|
info=f'{r}\t{kind}\tcurL={curL}\tM(maxnum)={mx}\tlastpg={lastpg}\ttabs={len(tc)}'
|
|
if is_content_tab: info+='\tCONTENT:'+' | '.join(f'{t[0]}->{t[1]}' for t in tc)
|
|
elif tc: info+='\tCATS:'+'/'.join(t[0] for t in tc)
|
|
out.append(info+'\t'+url.split('/')[-1][:30])
|
|
except Exception as e:
|
|
out.append(f'{r}\tERR\t{str(e)[:40]}\t{url[:50]}')
|
|
open('_scan_out.txt','w',encoding='utf-8').write('\n'.join(out))
|
|
print('\n'.join(out))
|