22 lines
778 B
Python
22 lines
778 B
Python
# coding: utf-8
|
|
import requests, re
|
|
from bs4 import BeautifulSoup
|
|
H={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
|
|
def fetch(u):
|
|
r=requests.get(u,headers=H,timeout=20)
|
|
s=BeautifulSoup(r.content,'html.parser')
|
|
return r,s
|
|
u='https://www.kisa.or.kr/20207'
|
|
r,s=fetch(u)
|
|
print('status',r.status_code,'final',r.url)
|
|
# find sub_tab_menu
|
|
for sel in ['ul.sub_tab_menu','.sub_tab_menu','ul[class*=sub_tab]','ul[class*=tab]']:
|
|
els=s.select(sel)
|
|
if els:
|
|
print('=== selector',sel,'count',len(els))
|
|
for i,el in enumerate(els[:3]):
|
|
print(' [%d] class=%s'%(i,el.get('class')))
|
|
for a in el.find_all('a'):
|
|
print(' a:', repr(a.get_text(strip=True)), '->', a.get('href'))
|
|
break
|