DB_JOB/_스크립트/_probe3.py
hehihoho3 df16c98366 백업: DB수집 전체 스냅샷 (공공기관2 정리 전)
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-18 18:15:40 +09:00

82 lines
2.6 KiB
Python

"""Find sitemap URLs for: 논산시, 아산시, 부여군, 서산시."""
import re
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):
try:
r = requests.get(url, headers=H, timeout=15, verify=False, allow_redirects=True)
r.encoding = r.apparent_encoding
return r.status_code, r.url, r.text
except Exception as e:
return 0, str(e), ''
def find_links_to(html, base, keyword='사이트맵'):
soup = BeautifulSoup(html, 'html.parser')
found = []
for a in soup.find_all('a', href=True):
txt = a.get_text(strip=True)
href = a['href']
if keyword in txt or 'sitemap' in href.lower() or 'allMenu' in href:
full = urljoin(base, href)
if full != base:
found.append((txt, full))
return found
CASES = [
('논산시', 'https://nonsan.go.kr/'),
('아산시', 'https://www.asan.go.kr/main/'),
('부여군', 'https://www.buyeo.go.kr/html/kr/'),
('서산시', 'https://www.seosan.go.kr/www/index.do'),
]
for name, base in CASES:
print(f'\n=== {name} {base} ===')
code, url, html = fetch(base)
if code != 200:
print(f' main 실패: {code}')
continue
links = find_links_to(html, url)
# Deduplicate
seen = set()
uniq = []
for t, u in links:
if u not in seen:
seen.add(u)
uniq.append((t, u))
print(f' 사이트맵/allMenu 링크 후보 ({len(uniq)}):')
for t, u in uniq[:10]:
print(f' "{t}"{u}')
# For top candidate, fetch and analyze
for t, u in uniq[:3]:
c2, u2, h2 = fetch(u)
if c2 != 200:
print(f' [{u}] HTTP {c2}')
continue
soup = BeautifulSoup(h2, 'html.parser')
# Find best container
best = (0, None, None)
for sel in ['.sitemap_grep', '.sitemap', '#sitemap', '.allMenu', '#allMenu',
'div[class*=sitemap]', 'div[class*=allMenu]', 'ul.sitemap_list',
'ul.depth1_ul', 'ul.depth1-ul', '#gnb', 'div.menu_all']:
for el in soup.select(sel):
ac = len(el.find_all('a'))
if ac > best[0]:
best = (ac, sel, el)
if best[1]:
cls = ' '.join(best[2].get('class', []))
print(f'{u2}: best={best[1]!r} cls={cls!r} a={best[0]}')
else:
print(f' [{u2}]: no container')