# -*- 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 def get(u): try: req=urllib.request.Request(u,headers={'User-Agent':'Mozilla/5.0'}) return urllib.request.urlopen(req,timeout=20,context=ctx).read().decode('utf-8','ignore') except Exception as e: return 'ERR:%s'%e SITES={ '옥천':'https://www.oc.go.kr/www/sub.do?key=121', '음성':'https://www.eumseong.go.kr/www/sub.do?key=722', '제천':'https://www.jecheon.go.kr/www/sitemap.do?key=553', '청주':'https://www.cheongju.go.kr/www/sitemap.do?key=589', '충주':'https://www.chungju.go.kr/www/sitemap.do?key=553', } for nm,u in SITES.items(): h=get(u) if h.startswith('ERR'): print(nm,h[:60]); continue s=BeautifulSoup(h,'html.parser') d1=len(s.select('li.depth1_item')); d4=len(s.select('.depth4_item, .depth4')) smbox=len(s.select('div.sitemap_box, #sitemap')) sm2=len(s.select('ul.sm2depth')); h4=len(s.select('a.h4')); bu=len(s.select('ul.bu')) print('%s len=%d | depth1_item=%d depth4=%d | sitemap_box=%d sm2depth=%d a.h4=%d ul.bu=%d'%(nm,len(h),d1,d4,smbox,sm2,h4,bu))