利用Hackhttp爬取cnvd漏洞名称

爬取国家信息安全中心漏洞名称cnvd
还是老话作为一个萌新，关于Python的基本语法就不多说了，这里直接从各个小的程序开始，本文会不断地进行更新，一步步来走进Python~

hackhttp模板：造福人类

发起get/post/ 发起http原始数据包

漏洞利用：更为快捷放放不安

#hackhttp使用方法
hh=hackhttp.hackhttp()
code,head,html,redirect_url,log=hh.http(url)
状态码/响应头/http相应内容类型string/跳转地址302/日志信息

import hackhttp
hh = hackhttp.hackhttp()
code, head, body, redirect, log = hh.http('https://www.bugscan.net')
print 'code'

同时也希望各位可以给点好的建议哈~
好啦废话补多少直接上源码

# -*- coding: utf-8 -*-
import hackhttp
from bs4 import BeautifulSoup
import re
from xlutils.copy import copydef tomcat(raw):
url = 'https://www.cnvd.org.cn/flaw/list.html?flag=ture'
urlparse('https://www.cnvd.org.cn/flaw/list.html?flag=ture')
hh = hackhttp.hackhttp()
code, head, html, redirect, log = hh.http(url=url,raw=raw)
soup = BS(html,'lxml')
tomcat_html = soup.tbody
#print tomcat_html
tomcat_cnvds = BS(str(tomcat_html),'lxml')
cnvds = tomcat_cnvds.find_all(name='a',attrs={'href':re.compile('/flaw/show/CNVD-.*?')})
#print cnvds
for cnvd in cnvds:
print cnvd['title']
raw_start = '''
POST /flaw/list.htm?flag=true HTTP/1.1
Host: www.cnvd.org.cn
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8
Accept-Language: zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2
Accept-Encoding: gzip, deflate
Referer: http://www.cnvd.org.cn/flaw/list.htm?flag=true
Content-Type: application/x-www-form-urlencoded
Content-Length: 388
Cookie: __jsluid=8179a859828c25ac3ae9abf49459fcd1; bdshare_firstime=1539606874920; JSESSIONID=BA1C017EE87D35335F8CA8F46FD33DD4; Hm_lvt_d7682ab43891c68a00de46e9ce5b76aa=1539657307; Hm_lpvt_d7682ab43891c68a00de46e9ce5b76aa=1539657317
Connection: keep-alive
Upgrade-Insecure-Requests: 1
number=%E8%AF%B7%E8%BE%93%E5%85%A5%E7%B2%BE%E7%A1%AE%E7%BC%96%E5%8F%B7&startDate=&endDate=&field=&order=&flag=true&keyword=tomcat&condition=1&keywordFlag=0&cnvdId=&cnvdIdFlag=0&baseinfoBeanbeginTime=&baseinfoBeanendTime=&baseinfoBeanFlag=0&refenceInfo=&referenceScope=-1&manufacturerId=-1&categoryId=-1&editionId=-1&causeIdStr=&threadIdStr=&serverityIdStr=&positionIdStr=&max=20&offset='''

for pages_count in range(0,121,20):
raw = raw_start+str(pages_count)
tomcat(raw)

各位大佬就可以自己看看啦！ 哈哈第一次发文 又点小紧张