df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
77 lines
2.4 KiB
Python
77 lines
2.4 KiB
Python
"""Inspect specific selectors found in probe6 for 아산시, 서산시, 부여군."""
|
|
import warnings
|
|
from urllib.parse import urljoin
|
|
|
|
import requests
|
|
from bs4 import BeautifulSoup
|
|
|
|
warnings.filterwarnings('ignore')
|
|
|
|
UA = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
|
|
H = {'User-Agent': UA}
|
|
|
|
|
|
def fetch(url):
|
|
r = requests.get(url, headers=H, timeout=15, verify=False, allow_redirects=True)
|
|
r.encoding = r.apparent_encoding
|
|
return r.url, r.text
|
|
|
|
|
|
def outline(el, depth=0, max_lines=120, lines=None):
|
|
if lines is None:
|
|
lines = []
|
|
if len(lines) >= max_lines:
|
|
return lines
|
|
name = el.name
|
|
cls = ' '.join(el.get('class', []))
|
|
eid = el.get('id', '')
|
|
label = name
|
|
if eid:
|
|
label += f'#{eid}'
|
|
if cls:
|
|
label += '.' + cls.replace(' ', '.')
|
|
if name == 'a':
|
|
txt = el.get_text(strip=True)[:50]
|
|
href = el.get('href', '')[:80]
|
|
lines.append(' ' * depth + f'{label} "{txt}" → {href}')
|
|
else:
|
|
lines.append(' ' * depth + label)
|
|
for c in el.find_all(recursive=False):
|
|
if c.name in ('script', 'style'):
|
|
continue
|
|
outline(c, depth + 1, max_lines, lines)
|
|
if len(lines) >= max_lines:
|
|
return lines
|
|
return lines
|
|
|
|
|
|
# 부여군: find .pc_sitemap
|
|
print('\n=== 부여군: .pc_sitemap 또는 inline sitemap ===')
|
|
real, html = fetch('https://www.buyeo.go.kr/html/kr/')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
for sel in ['.pc_sitemap', '#pc_sitemap', '.sitemap_grep', '.allMenu', '.allmenu',
|
|
'div[class*=sitemap]', 'div[class*=gnb]']:
|
|
for el in soup.select(sel):
|
|
ac = len(el.find_all('a'))
|
|
if ac >= 30:
|
|
cls = ' '.join(el.get('class', []))
|
|
print(f' ★ sel={sel} {el.name}.{cls} id={el.get("id","")} a={ac}')
|
|
|
|
# 아산시: mobile-nav.krds-gnb-mobile
|
|
print('\n=== 아산시: mobile-nav ===')
|
|
real, html = fetch('https://www.asan.go.kr/main/')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
el = soup.select_one('nav#mobile-nav')
|
|
if el:
|
|
for line in outline(el, max_lines=80):
|
|
print(' ', line)
|
|
|
|
# 서산시: top_menu
|
|
print('\n=== 서산시: ul#top_menu ===')
|
|
real, html = fetch('https://www.seosan.go.kr/www/index.do')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
el = soup.select_one('ul#top_menu') or soup.select_one('div.menu_wrap')
|
|
if el:
|
|
for line in outline(el, max_lines=80):
|
|
print(' ', line)
|