df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
111 lines
4.1 KiB
Python
111 lines
4.1 KiB
Python
"""Detailed structural look at 논산시, 아산시, 부여군 main sitemaps."""
|
|
import warnings
|
|
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}')
|
|
elif name == 'button':
|
|
txt = el.get_text(strip=True)[:50]
|
|
lines.append(' ' * depth + f'{label} BTN "{txt}"')
|
|
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
|
|
|
|
|
|
# 논산시 - look at div.sitemap.type1
|
|
print('=== 논산시 div.sitemap.type1 ===')
|
|
real, html = fetch('https://nonsan.go.kr/kor/html/sub07/0701.html')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
el = soup.select_one('div.sitemap.type1') or soup.select_one('div.sitemap')
|
|
if el:
|
|
cls = ' '.join(el.get('class', []))
|
|
print(f' Container: {el.name}.{cls} a={len(el.find_all("a"))}')
|
|
for line in outline(el, max_lines=70):
|
|
print(' ', line)
|
|
|
|
# 부여군 - try /html/kr/sitemap_pop.html or similar
|
|
print('\n\n=== 부여군 alternate sitemap probes ===')
|
|
for path in [
|
|
'/html/kr/sitemap_pop.html',
|
|
'/html/kr/sitemap.html',
|
|
'/html/kr/html/sub06/0601.html',
|
|
'/html/kr/html/sub05/0501.html',
|
|
'/html/kr/html/sub04/0401.html',
|
|
'/html/kr/html/sub09/0901.html',
|
|
'/html/kr/popup/sitemap.html',
|
|
'/html/kr/include/sitemap.html',
|
|
]:
|
|
url = f'https://www.buyeo.go.kr{path}'
|
|
try:
|
|
r = requests.get(url, headers=H, timeout=8, verify=False, allow_redirects=True)
|
|
r.encoding = r.apparent_encoding
|
|
if r.status_code == 200:
|
|
s = BeautifulSoup(r.text, 'html.parser')
|
|
best_count = 0
|
|
best_sel = ''
|
|
for sel in ['.sitemap', '#sitemap', '.sitemap_grep', '.allMenu', '.pc_sitemap', 'div[class*=sitemap]']:
|
|
for el in s.select(sel):
|
|
ac = len(el.find_all('a'))
|
|
if ac > best_count:
|
|
best_count = ac
|
|
best_sel = sel
|
|
print(f' {path}: HTTP 200, best_sel={best_sel}, a={best_count}')
|
|
except Exception as e:
|
|
pass
|
|
|
|
# 부여군 main page - look for inline pc_sitemap or modal
|
|
print('\n\n=== 부여군 main page: look for inline allMenu / pc_sitemap modal ===')
|
|
real, html = fetch('https://www.buyeo.go.kr/html/kr/')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
# Search for elements with id or class containing "sitemap"
|
|
for el in soup.select('[class*=sitemap], [id*=sitemap], [id*=allMenu], [class*=allMenu], [id*=allmenu], [class*=allmenu]'):
|
|
cls = ' '.join(el.get('class', []))
|
|
eid = el.get('id', '')
|
|
ac = len(el.find_all('a'))
|
|
print(f' {el.name}#{eid}.{cls} a={ac}')
|
|
|
|
# 아산시 - look at the .gnb-menu inline structure (use sectioned anchors mGnb-anchor1..6)
|
|
print('\n\n=== 아산시: all gnb-sub-list sections combined ===')
|
|
real, html = fetch('https://www.asan.go.kr/main/')
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
all_a = []
|
|
for sec in soup.select('div[id^=mGnb-anchor]'):
|
|
eid = sec.get('id', '')
|
|
section_a = sec.find_all('a', href=True)
|
|
print(f' {eid}: a={len(section_a)}')
|
|
for a in section_a[:3]:
|
|
print(f' "{a.get_text(strip=True)[:40]}" → {a["href"][:80]}')
|