利用Python爬取工控行业系统漏洞

先贴连接，让各位观众老爷看看，对不对你们的胃口

工控行业系统漏洞

可以看到，这个网页是html静态的，所以问题变的非常的简单

只需要用request请求网页就可以了

话不多说，直接贴代码

import requests
from urllib.parse import urlencode
from lxml import etree
import pymysql
import time
import xlwt
import xlrd

def makeurl():
    # http://ics.cnvd.org.cn/?tdsourcetag=s_pctim_aiomsg&max=20&offset=0
    baseurl = 'http://ics.cnvd.org.cn/?'
    params = {
        'tdsourcetag': 's_pctim_aiomsg',
        'max': '20'
    }
    for page in range(MAX_PAGE):
        params['offset'] = page * 20
        url = baseurl + urlencode(params)
        print('url is ', url)
        yield url

def get_page_urllist(url):
    headers = {
        'Host': 'ics.cnvd.org.cn',
        'Referer': 'http://ics.cnvd.org.cn/?tdsourcetag=s_pctim_aiomsg&max=20&offset=40',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36'
    }
    response = requests.get(url, headers=headers)
    return response.text

def parse_urllist(content):
    html = etree.HTML(content)
    for li in html.xpath('//tbody[@id="tr"]/tr'):
        yield li.xpath('td/a/@href')[0]

def get_page(url):
    headers = {
        'Host': '