DB_JOB/작업파일/완료/광역_사이트맵/충청남도/9.서천군/_classify.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

39 lines
1.7 KiB
Python

import openpyxl, requests, sys, re
from bs4 import BeautifulSoup
import urllib3
urllib3.disable_warnings()
sys.stdout.reconfigure(encoding='utf-8')
p = r'D:\01.프로젝트\DB수집\작업파일\광역_사이트맵\충청남도\9.서천군\충청남도_서천군.xlsx'
wb = openpyxl.load_workbook(p); ws = wb.active
H = {'User-Agent':'Mozilla/5.0'}
def get(u):
r = requests.get(u, headers=H, timeout=20, verify=False); r.encoding=r.apparent_encoding or 'utf-8'; return r.text
# rows flagged with basic_tab from prior scan
rows = [17,22,25,35,48,57,66,70,78,94,97,102,104,107,134,135,136,168,170,171,176,183,193,199,200,217,219,222,233,235,236,237,250,268]
for r in rows:
cell = ws.cell(r,11)
url = cell.hyperlink.target if cell.hyperlink else cell.value
label = ws.cell(r,7).value or ws.cell(r,6).value or ''
L = ws.cell(r,12).value
try:
soup = BeautifulSoup(get(url),'html.parser')
except Exception as e:
print(f'R{r} ERR {e}'); continue
ul = soup.select_one('ul.basic_tab')
if not ul:
print(f'R{r} no basic_tab now'); continue
hrefs=[(' '.join(li.get_text().split())[:14], (li.find("a").get("href") if li.find("a") else "")) for li in ul.select('li')]
# classify
kinds=set()
for t,h in hrefs:
if not h or h.strip() in ('#','') or h.startswith('javascript') or h.startswith('#'):
kinds.add('anchor')
elif 'list.do' in h or 'cate_' in h or '?' in h:
kinds.add('filter')
else:
kinds.add('page')
has_slave = bool(soup.select_one('ul.slave_tab'))
print(f'R{r:>3} {str(label)[:18]:18} L={L} n={len(hrefs)} kinds={kinds} slave={has_slave}')
for t,h in hrefs[:6]:
print(f' - {t:14} {h[:55]}')