df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
50 lines
1.9 KiB
Python
50 lines
1.9 KiB
Python
# -*- coding: utf-8 -*-
|
|
import openpyxl, requests, urllib3, re, json, sys, io
|
|
from bs4 import BeautifulSoup
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
urllib3.disable_warnings()
|
|
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
|
|
H={'User-Agent':'Mozilla/5.0'}
|
|
B='https://www.jejusi.go.kr'
|
|
ws=openpyxl.load_workbook('제주특별자치도_제주시.xlsx').active
|
|
|
|
rows=[]
|
|
for r in range(3, ws.max_row+1):
|
|
b=ws.cell(r,2).value
|
|
if not b or b<45: continue
|
|
K=ws.cell(r,11).value or ''
|
|
rows.append({'row':r,'B':b,'name':ws.cell(r,6).value or ws.cell(r,5).value,'L':ws.cell(r,12).value,'K':K})
|
|
|
|
def get(u):
|
|
return requests.get(u, timeout=20, headers=H, verify=False).text
|
|
|
|
def scan(x):
|
|
K=x['K']
|
|
if 'jejusi.go.kr' not in K or '.do' not in K:
|
|
return None
|
|
try:
|
|
html=get(K).replace('&','&')
|
|
except Exception:
|
|
return None
|
|
s=BeautifulSoup(html,'html.parser')
|
|
box=s.select_one('div.depth_tabmenu')
|
|
if not box: return None
|
|
tabs=[]
|
|
for a in box.select('li a'):
|
|
href=a.get('href') or ''
|
|
tabs.append({'label':a.get_text(strip=True),'href':href,'blank':a.get('target')=='_blank','active':'active' in ' '.join(a.find_parent('li').get('class',[]))})
|
|
if len(tabs)<2: return None
|
|
return {**x,'tabs':tabs}
|
|
|
|
res=[]
|
|
with ThreadPoolExecutor(max_workers=8) as ex:
|
|
res=[r for r in ex.map(scan, rows) if r]
|
|
|
|
# group by tab-set signature to dedupe (same tab bar appears on each tab page)
|
|
print('depth_tabmenu 가진 행:', len(res))
|
|
for x in sorted(res, key=lambda z:z['B']):
|
|
print(f"B{x['B']} {x['name'][:20]:20s} L={x['L']} K={x['K'].split('jejusi.go.kr')[-1].split('?')[0]}")
|
|
for t in x['tabs']:
|
|
print(f" - {t['label'][:24]:24s} {'[새창]' if t['blank'] else ''}{'[active]' if t['active'] else ''} {t['href'].split('jejusi.go.kr')[-1][:55] if 'jejusi' in t['href'] else t['href'][:55]}")
|
|
json.dump(res, open('_tabscan.json','w',encoding='utf-8'), ensure_ascii=False)
|