通過關鍵字獲取漏洞平臺最新漏洞信息

因要每天去查找漏洞信息，來判斷架構和應用服務有沒有新漏洞被發現，若有 則需修復升級。所以寫了一個去漏洞庫平臺通過關鍵字爬取數據生成日志文件，這三個平臺，就美國國家信息安全漏洞庫地址會時不時出現超時情況。若出現超時，可多試兩次，三個平臺檢索出的漏洞差不多，寫的不好，僅供參考

python版本3.7
pip安裝requests即可

#coding=utf-8
import requests as r
import re
import time
import datetime

#爬取國家信息安全漏洞平臺
class gjxxaqpt:
    def get_404(self,url,keyword):
        #定義提交數據 qcvCname 檢索的詞，pageno 頁數 一般是抓取第一頁
        data = {"qcvCname":keyword,"pageno":1}
        #post數據
        result = r.post(url,data=data).text
        #正則匹配信息
        filter_result = re.findall('<li  a_title2" >\r\n                               \t\t  (.*?)</a>.*?<p><a href="(.*?)" target="_blank">(.*?)</a>.*?<img title="(.*?)" src=".*?<br/ >(.*?)\r\n\t\t\t\t\t\t   </div>.*?</li>',result,re.S)
        return filter_result

    def get_404_mes(self,url):
        header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'}
        try:
            result = r.get(url,headers=header).text
            filter_result = re.findall('<div class="d_ldjj">.*?</p><p >\n(.*?)\r\n\t\t\t</p>',result,re.S)
            if filter_result is not None:
                return filter_result[0]
            else:
                return ""
        except:
            print("連接超時"+url)

    def write_file(self,keyword,date_time):
        #定義post的url
        url = "http://www.cnnvd.org.cn/web/vulnerability/queryLds.tag"
        #定義后面組合信息需要的域名
        url_domain = "http://www.cnnvd.org.cn"
        #存放最后結果數據的數組
        mes_list = []
        #循環檢索關鍵詞
        for keyword in keylist:
            try:
                #調用方法獲取檢索的結果
                get_404_re = self.get_404(url,keyword)
                #循環結果，拼接成字符串，寫入log文件
                for res in get_404_re:
                    #判斷包含本年日期的漏洞
                    if date_time in res[4]:
                        mes_url = url_domain + res[1]
                        try:
                            message = self.get_404_mes(mes_url)
                            mes = res[0] + " | " "漏洞編號：" + res[2] + " | " + "等級：" + res[3] + " | " + "時間：" + res[4] + " | " + "詳情地址：" + mes_url + " | " + "漏洞簡介：" + message
                            mes_list.append(mes)
                        except:
                            print("timeout: "+mes_url)
            except:
                print("timeout:"+url+","+"keyword")
        return mes_list

#cve中文漏洞信息庫 - scap中文社區
class cve_scap:
    #獲取所有漏洞集合
    def get_cve_404(self,url,keyword):
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'}
        #定義提交數據 qcvCname 檢索的詞，pageno 頁數 一般是抓取第一頁
        data = {"search_type":"t_keyword","keyword":keyword}
        #post數據
        result = r.get(url,params=data).text
        filter_result = re.findall("<td class='hidden-xs'>.*?<a href=(.*?)>\n                            (.*?)\n                        </a>.*?<td class='hidden-xs hidden-sm'>(.*?)</td>.*?title='(.*?)' class='grade",result,re.S)
        return filter_result

    #對單個漏洞信息獲取
    def get_cve_404_mes(self,url):
        header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'}
        try:
            result = r.get(url,headers=header).text
            filter_result = re.findall("pad30T pad30B mrg0B' style='word-wrap: break-word;'>\n                        (.*?)</p>",result,re.S)
            if filter_result is not None:
                return filter_result[0]
            else:
                return ""
        except:
            print("timeout: " + url)

    #信息獲取
    def write_file(self,keylist,date_time):
        #定義post的url
        url = "http://cve.scap.org.cn/vulns/1"
        #定義數組，存放信息
        mes_list = []
        for keyword in keylist:
            #爬取網站
            html_filter = self.get_cve_404(url,keyword)
            #定義后面組合信息需要的域名
            url_domain = "http://cve.scap.org.cn"
            for res in html_filter:
                if date_time in res[2]:
                    try:
                        mes_url = url_domain + res[0].strip('"')
                        message = self.get_cve_404_mes(mes_url)
                        mes = "漏洞編號：" + res[1] + " | " + "等級：" + res[3] + " | " + "時間：" + res[2] + " | " + "詳情地址：" + mes_url + " | " + "漏洞簡介：" + message.replace("\n","")
                        mes_list.append(mes)
                    except:
                        print("timeout: "+mes_url)

        return mes_list

#美國國家信息安全漏洞庫
class nvd_nist:
    #獲取所有漏洞集合
    def get_nvd_404(self,url,keyword):
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'}
        #定義提交數據 qcvCname 檢索的詞，pageno 頁數 一般是抓取第一頁
        data = {"form_type":"Basic","results_type":"overview","query":keyword,"search_type":"all"}
        #關閉ssl告警提示
        r.packages.urllib3.disable_warnings()
        #post數據
        result = r.get(url,params=data,verify=False).text
        filter_result = re.findall("<tr data-testid=\"vuln-row.*?<a href=\"(.*?)\" id=\".*?data-testid=\"vuln-detail-link-[0-9]{1,2}\">(.*?)</a></strong><br/>.*?<p data-testid='vuln-summary-[0-9]{1,2}'>(.*?)</p>.*?<span data-testid='vuln-published-on-[0-9]{1,2}'>(.*?)</span>",result,re.S)
        return filter_result

    def write_file(self,keylist,date_time):
        #查找漏洞的url地址
        url = "https://nvd.nist.gov/vuln/search/results"
        #拼接url的地址
        url_dom = "https://nvd.nist.gov"
        #存儲最后結果的數組
        mes_list = []
        #循環獲取關鍵字的漏洞信息
        for keyword in keylist:
            try:
                filter_html = self.get_nvd_404(url,"nginx")
                for res in filter_html:
                    url_domain = url_dom + res[0]
                    #對英文的時間格式進行轉換
                    eng_time = res[3]
                    if "AM" in eng_time:
                        up_time = eng_time.split("AM")[0]
                    elif "PM" in eng_time:
                        up_time = eng_time.split("PM")[0]
                    else:
                        print("時間判斷有誤")
                    #我獲取到的時間是英文的時間格式，需要轉換為數字時間格式，這里時間字符串和里面的時間格式要保持一次，差一個空格，也不行
                    time_format=str(datetime.datetime.strptime(up_time,'%B %d, %Y; %H:%M:%S '))
                    if date_time in time_format:
                        mes = "漏洞編號：" + res[1]  + " | " + "時間：" + time_format + " | " + "詳情地址：" + url_domain + " | " + "漏洞簡介：" + res[2]
                        mes_list.append(mes)
            except:
                print("timeout:" + url + "," + keyword)
        return mes_list

if __name__ == "__main__":
    #需要查找的關鍵字數組
    keylist=['nginx','openssl','openssh']
    #獲取本年的日期
    date_time = time.strftime("%Y",time.localtime())
    #打開寫入log文件
    files = open("404_message.log","w+",encoding='utf-8')

    #獲取國家信息漏洞庫
    guojia = gjxxaqpt()
    files.write("#國家信息漏洞庫:\n")
    for i in guojia.write_file(keylist,date_time):
        files.write(i+"\n")
    files.write("\n")

    #cve中文漏洞信息庫 - scap中文社區 查找
    cve = cve_scap()
    files.write("#cve中文漏洞信息庫:\n")
    for i in cve.write_file(keylist,date_time):
        files.write(i+"\n")
    files.write("\n")

    #美國國家信息安全漏洞庫 查找
    nvd = nvd_nist()
    files.write("#美國國家信息安全漏洞庫:\n")
    for i in nvd.write_file(keylist,date_time):
        files.write(i+"\n")
    files.write("\n")

    files.close()