欧美bbbwbbbw肥妇,免费乱码人妻系列日韩,一级黄片

python爬取cnvd漏洞庫信息的實(shí)例

 更新時(shí)間:2019年02月14日 15:34:41   作者:黑面狐  
今天小編就為大家分享一篇python爬取cnvd漏洞庫信息的實(shí)例,具有很好的參考價(jià)值,希望對(duì)大家有所幫助。一起跟隨小編過來看看吧

今天一同事需要整理http://ics.cnvd.org.cn/工控漏洞庫里面的信息,一看960多個(gè)要整理到什么時(shí)候才結(jié)束。

所以我決定寫個(gè)爬蟲幫他抓取數(shù)據(jù)。

看了一下各類信息還是很規(guī)則的,感覺應(yīng)該很好寫。

but這個(gè)網(wǎng)站設(shè)置了各種反爬蟲手段。

經(jīng)過各種百度,還是解決問題了。

設(shè)計(jì)思路:

1.先抓取每一個(gè)漏洞信息對(duì)應(yīng)的網(wǎng)頁url

2.獲取每個(gè)頁面的漏洞信息

# -*- coding: utf-8 -*-
import requests
import re
import xlwt
import time
from bs4 import BeautifulSoup
headers = {
 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
 'Accept-Encoding': 'gzip, deflate, sdch',
 'Accept-Language': 'zh-CN,zh;q=0.8',
 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.71 Safari/537.36'
}
cookies={'__jsluid':'8d3f4c75f437ca82cdfad85c0f4f7c25'}
myfile=xlwt.Workbook()
wtable=myfile.add_sheet(u"信息",cell_overwrite_ok=True)
j = 0
a = 900
for i in range(4):
 url ="http://ics.cnvd.org.cn/?max=20&offset="+str(a)
 r = requests.get(urttp://ics.cnvd.org.cnl,headers=headers,cookies=cookies)
 print r.status_code
 while r.status_code != 200:
  r = requests.get(url,headers=headers,cookies=cookies)
  print r.status_code
 html = r.text
 soup = BeautifulSoup(html)
 #print html
 
 for tag in soup.find('tbody',id='tr').find_all('a',href=re.compile('http://www.cnvd.org.cn/flaw/show')):
  print tag.attrs['href']
  wtable.write(j,0,tag.attrs['href'])
  j += 1
 a += 20
 print u"已完成%s"%(a)
filename=str(time.strftime('%Y%m%d%H%M%S',time.localtime()))+"url.xls"
myfile.save(filename)
print u"完成%s的url備份"%time.strftime('%Y%m%d%H%M%S',time.localtime())
# -*- coding: utf-8 -*-
from selenium import webdriver
import xlrd
import xlwt
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import Select
from selenium.common.exceptions import NoSuchElementException
from selenium.common.exceptions import NoAlertPresentException
import unittest, time, re
 
class Gk(unittest.TestCase):
 def setUp(self):
  self.driver = webdriver.Firefox()
  self.driver.implicitly_wait(5)
  self.verificationErrors = []
  self.accept_next_alert = True
 
 def test_gk(self):
  myfile=xlwt.Workbook()
  wtable=myfile.add_sheet(u"info",cell_overwrite_ok=True)
  data = xlrd.open_workbook('url.xlsx')
  table = data.sheets()[0]
  nrows = table.nrows
  driver = self.driver
  
  j = 0
  for i in range(nrows):
   try:
    s = []
    driver.get(table.cell(i,0).value)
    title = driver.find_element_by_xpath("http://h1").text
    print title
    s.append(title)
    trs = driver.find_element_by_xpath("http://tbody").find_elements_by_tag_name('tr')
    for td in trs:
     tds = td.find_elements_by_tag_name("td")
     for tt in tds:
      print tt.text
      s.append(tt.text)
    k = 0
    for info in s:
     wtable.write(j,k,info)
     k += 1
    j += 1
   except:
    filename=str(time.strftime('%Y%m%d%H%M%S',time.localtime()))+"url.xls"
    myfile.save(filename)
    print u"異常自動(dòng)保存%s的漏洞信息備份"%time.strftime('%Y%m%d%H%M%S',time.localtime())
   
  filename=str(time.strftime('%Y%m%d%H%M%S',time.localtime()))+"url.xls"
  myfile.save(filename)
  print u"完成%s的漏洞信息備份"%time.strftime('%Y%m%d%H%M%S',time.localtime())
  
 def is_element_present(self, how, what):
  try: self.driver.find_element(by=how, value=what)
  except NoSuchElementException, e: return False
  return True
 
 def is_alert_present(self):
  try: self.driver.switch_to_alert()
  except NoAlertPresentException, e: return False
  return True
 
 def close_alert_and_get_its_text(self):
  try:
   alert = self.driver.switch_to_alert()
   alert_text = alert.text
   if self.accept_next_alert:
    alert.accept()
   else:
    alert.dismiss()
   return alert_text
  finally: self.accept_next_alert = True
 
 def tearDown(self):
  self.driver.quit()
  self.assertEqual([], self.verificationErrors)
 
if __name__ == "__main__":
 unittest.main()

好了??纯唇Y(jié)果怎樣!

python爬取cnvd漏洞庫信息

OK!剩下手動(dòng)整理一下,收工!

以上這篇python爬取cnvd漏洞庫信息的實(shí)例就是小編分享給大家的全部?jī)?nèi)容了,希望能給大家一個(gè)參考,也希望大家多多支持腳本之家。

相關(guān)文章

最新評(píng)論