14 lines
508 B
Python
14 lines
508 B
Python
# coding: utf-8
|
|
import requests, re
|
|
H={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
|
|
u='https://www.kisa.or.kr/20207'
|
|
r=requests.get(u,headers=H,timeout=20)
|
|
html=r.content.decode('utf-8','replace')
|
|
print('len',len(html))
|
|
for kw in ['sub_tab_menu','sub_tab','tab_menu','tabmenu','동향분석','20207','sub_lnb','lnb']:
|
|
print(kw, html.count(kw))
|
|
# print any tab-related class
|
|
import re
|
|
classes=set(re.findall(r'class="([^"]*tab[^"]*)"',html))
|
|
print('tab classes:', classes)
|