Python爬取 工控行业系统漏洞

先贴链接，让各位观众老爷看看，对不对大家的胃口

工控行业系统漏洞

能够看到，这个网页是html静态的，因此问题变的很是的简单

只须要用request请求网页就能够了

话很少说，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': 'www.cnvd.org.cn',
        '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_page(content, url):
    html = etree.HTML(content)
    item = {}
    item['url'] = url
    item['标题'] = str(html.xpath('//div[@class="blkContainerSblk"]/h1/text()')[0])

    item['CNVD_ID'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="CNVD-ID"]/following-sibling::*[1]//text()')])
    item['公开日期'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="公开日期"]/following-sibling::*[1]//text()')])
    item['危害级别'] = ''.join([i.strip().replace(' ', '').replace('\r', '').replace('\n', '').replace('\t', '') for i in
                            html.xpath('//tbody/tr/td[text()="危害级别"]/following-sibling::*[1]//text()')])
    item['影响产品'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="影响产品"]/following-sibling::*[1]//text()')])
    try:
        item['BUGTRAQ_ID'] = ''.join(
            [i.strip() for i in html.xpath('//tbody/tr/td[text()="BUGTRAQ ID"]/following-sibling::*[1]//text()')])
    except:
        item['BUGTRAQ_ID'] = ''
    item['CVE_ID'] = ''.join(
        [i.strip() for i in
         html.xpath('//tbody/tr/td[text()="CVE ID"]/following-sibling::*[1]//text()')]) + ' ' + ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="CVE ID"]/following-sibling::*[1]//@href')])

    item['漏洞描述'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="漏洞描述"]/following-sibling::*[1]//text()')])
    item['漏洞类型'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="漏洞类型"]/following-sibling::*[1]//text()')])
    item['参考连接'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="参考连接"]/following-sibling::*[1]//text()')])
    item['漏洞解决方案'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="漏洞解决方案"]/following-sibling::*[1]//text()')])
    item['厂商补丁'] = ''.join(
        [i.strip() for i in html.xpath(
            '//tbody/tr/td[text()="厂商补丁"]/following-sibling::*[1]//text()')]) + ' http://www.cnvd.org.cn' + ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="厂商补丁"]/following-sibling::*[1]//@href')])
    item['验证信息'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="验证信息"]/following-sibling::*[1]//text()')])
    item['报送时间'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="报送时间"]/following-sibling::*[1]//text()')])
    item['收录时间'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="收录时间"]/following-sibling::*[1]//text()')])
    item['更新时间'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="更新时间"]/following-sibling::*[1]//text()')])
    item['漏洞附件'] = ''.join(
        [i.strip() for i in html.xpath('//tbody/tr/td[text()="漏洞附件"]/following-sibling::*[1]//text()')])

    return item


def save_data(index, item, workbook):
    sheet = workbook.get_sheet('sheet1')  # 建立一个sheet表格
    for col, value in enumerate(item.values()):
        sheet.write(index, col, value)
    workbook.save(filename)
    print('保存成功')


def excel_prepare(heads):
    workbook = xlwt.Workbook()
    sheet = workbook.add_sheet('sheet1', cell_overwrite_ok=True)  # 建立一个sheet表格
    for col, value in enumerate(heads):
        sheet.write(0, col, value)
    return workbook


def urlisexist(url, urlset):
    if url in urlset:
        return True
    else:
        return False


def getallurl(filename):
    workbook = xlrd.open_workbook(filename)
    sheet1 = workbook.sheet_by_name('sheet1')
    results = sheet1.col_values(0, 1)
    return results


def read_old(filename):
    workbook = xlrd.open_workbook(filename)
    sheet1 = workbook.sheet_by_name('sheet1')
    alloldset = []
    for index in range(sheet1.nrows):
        alloldset.append(sheet1.row_values(index))
    return alloldset, sheet1.nrows


def save_old(index, olditem):
    sheet = workbook.get_sheet('sheet1')  # 建立一个sheet表格
    for col, value in enumerate(olditem):
        sheet.write(index, col, value)
    workbook.save(filename)


if __name__ == '__main__':
    # http://ics.cnvd.org.cn/?tdsourcetag=s_pctim_aiomsg&max=20&offset=0

    # 睡眠时间
    TIMESLEEP = 0

    filename = '工程控制系统漏洞.xls'

    MAX_PAGE = 96



    heads = ['url',
             '标题',
             'CNVD_ID',
             '公开日期',
             '危害级别',
             '影响产品',
             'BUGTRAQ_ID',
             'CVE_ID',
             '漏洞描述',
             '漏洞类型',
             '参考连接',
             '漏洞解决方案',
             '厂商补丁',
             '验证信息',
             '报送时间',
             '收录时间',
             '更新时间',
             '漏洞附件']

    try:
        alloldset, length = read_old(filename)
    except:
        alloldset = []
        length = 1

    workbook = excel_prepare(heads)

    for index, olditem in enumerate(alloldset):
        save_old(index, olditem)

    try:
        urlset = getallurl(filename)
    except:
        urlset = []

    index = length
    for urlofpage in makeurl():
        pagelistcontent = get_page_urllist(urlofpage)
        for url in parse_urllist(pagelistcontent):
            print('url is >>>', url)
            if not urlisexist(url, urlset):
                time.sleep(TIMESLEEP)
                result = get_page(url)
                item = parse_page(result, url)
                print('item is >>>', item)
                save_data(index, item, workbook)
                index = index + 1

    workbook.save(filename)

不懂的地方，下方评论提问