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>
83 lines
2.6 KiB
Python
83 lines
2.6 KiB
Python
import requests, json, io, time
|
|
from bs4 import BeautifulSoup
|
|
from urllib.parse import urljoin
|
|
import urllib3; urllib3.disable_warnings()
|
|
H={'User-Agent':'Mozilla/5.0'}
|
|
BASE="https://www.kdhc.co.kr"
|
|
def menuno(u):
|
|
import re
|
|
m=re.search(r'menuNo=(\d+)',u or '')
|
|
return m.group(1) if m else None
|
|
def fetch(u):
|
|
r=requests.get(u,headers=H,timeout=25,verify=False)
|
|
return BeautifulSoup(r.content,'html.parser')
|
|
|
|
data=json.load(io.open('_dump.json',encoding='utf-8'))
|
|
# unique urls (Klink) -> rows
|
|
seen={}
|
|
for row in data:
|
|
k=row.get('Klink') or row.get('K')
|
|
if not k: continue
|
|
seen.setdefault(k,[]).append(row)
|
|
|
|
groups=[] # each: list of (label,href,menuNo,active)
|
|
def gettabs(s):
|
|
res=[]
|
|
for ul in s.find_all('ul'):
|
|
lis=ul.find_all('li',class_='tebLi')
|
|
if not lis: continue
|
|
tabs=[]
|
|
for li in lis:
|
|
a=li.find('a')
|
|
if not a: continue
|
|
href=a.get('href') or ''
|
|
cls=a.get('class') or []
|
|
tabs.append((a.get_text(strip=True), href, 'active' in cls))
|
|
if len(tabs)>=2:
|
|
res.append(tabs)
|
|
return res
|
|
|
|
allgroups={}
|
|
errs=[]
|
|
for i,(k,rows) in enumerate(sorted(seen.items())):
|
|
try:
|
|
s=fetch(k)
|
|
tg=gettabs(s)
|
|
except Exception as e:
|
|
errs.append((k,str(e))); continue
|
|
for tabs in tg:
|
|
key=tuple(sorted((t[0],menuno(t[1]) or t[1]) for t in tabs))
|
|
if key not in allgroups:
|
|
allgroups[key]=tabs
|
|
time.sleep(0.15)
|
|
|
|
# sheet menuNos present
|
|
sheet_mn={}
|
|
for row in data:
|
|
k=row.get('Klink') or row.get('K') or ''
|
|
mn=menuno(k)
|
|
if mn: sheet_mn.setdefault(mn,[]).append(row['r'])
|
|
|
|
out=[]
|
|
for key,tabs in allgroups.items():
|
|
info=[]
|
|
for lbl,href,act in tabs:
|
|
mn=menuno(href)
|
|
absu=urljoin(BASE,href) if href.startswith('/') else href
|
|
in_sheet = mn in sheet_mn if mn else False
|
|
is_board = '/bbs/' in href or '/list.do' in href
|
|
info.append({'label':lbl,'href':href,'url':absu,'menuNo':mn,'active':act,'in_sheet':in_sheet,'sheet_rows':sheet_mn.get(mn,[]),'board':is_board})
|
|
out.append(info)
|
|
|
|
io.open('_tabgroups.json','w',encoding='utf-8').write(json.dumps(out,ensure_ascii=False,indent=1))
|
|
print('total page/board fetched:',len(seen))
|
|
print('distinct tab groups:',len(out))
|
|
print('errors:',len(errs))
|
|
for e in errs[:10]: print(' ERR',e)
|
|
print('=== GROUPS ===')
|
|
for g in out:
|
|
present=sum(1 for t in g if t['in_sheet'])
|
|
print(f'[{present}/{len(g)} in sheet]')
|
|
for t in g:
|
|
print(' ',('*' if t['active'] else ' '),'SHEET' if t['in_sheet'] else ' NEW',t['menuNo'],('BOARD' if t['board'] else 'page '),t['label'],'rows=',t['sheet_rows'])
|