从网页上抓取Windows补丁信息然后整型输出（Python）

时间：2024-01-09 17:31:32

Powershell实现：http://www.cnblogs.com/IvanChen/p/4488246.html

今天通过Python实现：

# coding=utf-8

import re

import requests

import csv

import sys

from lxml import etree

reload(sys)

sys.setdefaultencoding('utf8')

summaryurl = 'https://technet.microsoft.com/en-us/library/security/mt637763.aspx'

summarycontent = requests.get(summaryurl).content

selector = etree.HTML(summarycontent)

mslist = selector.xpath('//*[@id="mainBody"]/table/tr/td[2]/p/a/text()')

pattern_published_date = re.compile(r"[a-zA-Z]*?\s[0-9]*?,\s[0-9]*")

pattern_severity = re.compile(r"[a-zA-Z]*$")

pattern_kbnumber = re.compile(r"\d+")

pattern_vultype = re.compile(r"Information Disclosure|Remote Code Execution|Elevation of Privilege|Security Feature Bypass|Cumulative Security Update|Denial of Service|Tampering|Spoofing", re.I)

csvfile = file('eggs.csv', 'wb')

writer = csv.writer(csvfile, dialect="excel")

writer.writerow(['Date', 'MSRC', 'KB', 'Severity', 'Version', 'Summary', 'Type'])

for eachmsrc in mslist:

    msrcurl = "https://technet.microsoft.com/en-us/library/security/" + eachmsrc + ".aspx"

    msrc_content = requests.get(msrcurl).content

    msrc_selector = etree.HTML(msrc_content)

    published_date = msrc_selector.xpath('//*[@id="pubInfo"]/p[1]/text()')

    kbnumber = msrc_selector.xpath('//*[@id="mainBody"]/h2/text()')

    severity = msrc_selector.xpath('//*[@id="content"]/div[2]/h1/text()')

    version = msrc_selector.xpath('//*[@id="pubInfo"]/p[2]/text()')

    summary = msrc_selector.xpath('//*[@id="mainBody"]/div[3]/div/p[1]/text()')

    vultype = msrc_selector.xpath('string(//*[@id="mainBody"]/div[3]/div)')

    ft_published_date = re.search(pattern_published_date, published_date[0]).group()

    ft_kbnumber = re.search(pattern_kbnumber, kbnumber[0]).group()

    ft_severity = re.search(pattern_severity, severity[0].strip('\n ')).group()

    ft_version = version[1]

    ft_summary = summary[0]

    ft_vultype = re.search(pattern_vultype, vultype)

    if ft_vultype:

        writer.writerow([ft_published_date, eachmsrc, ft_kbnumber, ft_severity, ft_version, ft_summary, ft_vultype.group()])

    else:

        vultype = msrc_selector.xpath('string(//*[@id="mainBody"]/div[position()>3]/div/table)')

        ft_vultype = re.search(pattern_vultype, vultype)

        writer.writerow([ft_published_date, eachmsrc, ft_kbnumber, ft_severity, ft_version, ft_summary, ft_vultype.group()])

csvfile.close()

相关文章