df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
20 lines
752 B
Python
20 lines
752 B
Python
# -*- coding: utf-8 -*-
|
|
import sys,io,urllib.request,ssl,re
|
|
from bs4 import BeautifulSoup
|
|
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='utf-8')
|
|
ctx=ssl.create_default_context(); ctx.check_hostname=False; ctx.verify_mode=ssl.CERT_NONE
|
|
try: ctx.set_ciphers('DEFAULT@SECLEVEL=1')
|
|
except: pass
|
|
def get(u):
|
|
req=urllib.request.Request(u,headers={'User-Agent':'Mozilla/5.0'})
|
|
return urllib.request.urlopen(req,timeout=25,context=ctx).read().decode('utf-8','ignore')
|
|
h=get('https://www.yd21.go.kr/kr/html/guide/0701.html')
|
|
s=BeautifulSoup(h,'html.parser')
|
|
# sitemap container
|
|
sm=s.select_one('.sitemap') or s
|
|
dls=sm.find_all('dl')
|
|
print('dl수',len(dls))
|
|
for dl in dls[:2]:
|
|
print('--- dl ---')
|
|
print(re.sub(r'\s+',' ',str(dl))[:900])
|