df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
36 lines
1.6 KiB
Python
36 lines
1.6 KiB
Python
"""Look at raw HTML around h4.site01 in 보령시 to find category name."""
|
|
import re
|
|
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}
|
|
|
|
for name, url in [('보령시', 'https://www.brcn.go.kr/kor/sitemap_11.do'),
|
|
('서천군', 'https://www.seocheon.go.kr/kor/sitemap_11.do')]:
|
|
print(f'\n=== {name} === {url}')
|
|
r = requests.get(url, headers=H, timeout=15, verify=False, allow_redirects=True)
|
|
r.encoding = r.apparent_encoding
|
|
html = r.text
|
|
# Find h4.siteNN occurrences
|
|
for m in re.finditer(r'<h4[^>]*site\d+[^>]*>([\s\S]*?)</h4>', html):
|
|
inner = re.sub(r'\s+', ' ', m.group(1)).strip()[:200]
|
|
full = re.sub(r'\s+', ' ', m.group(0)).strip()[:200]
|
|
print(f' h4: {full}')
|
|
# Find gnb anchors
|
|
soup = BeautifulSoup(html, 'html.parser')
|
|
gnb = soup.select_one('#gnb, #tm, nav#topmenu, nav.gnb, .gnb_wrap, .menu_wrap')
|
|
if gnb:
|
|
a_top = [a.get_text(strip=True) for a in gnb.select('> ul > li > a') or gnb.select('ul > li > a.th_1st, ul > li > a.depth1_ti, ul > li > a.first, ul > li > a')]
|
|
print(f' GNB top items: {a_top[:10]}')
|
|
# Find the top-level menu anchors (any way)
|
|
print(' Possible main category anchors:')
|
|
for cls_pattern in ['ov', 'th_1st', 'depth1_ti', 'first', 'gnb-main-trigger']:
|
|
for a in soup.find_all('a', class_=cls_pattern):
|
|
t = a.get_text(strip=True)
|
|
if t and len(t) < 30:
|
|
print(f' .{cls_pattern}: "{t}"')
|
|
break
|