Python xlrd、xlwt模块用于主机漏洞跟踪的数据分析

简介：
脚本基于Python xlrd、xlwt模块的数据分析，用于主机漏洞跟踪，希望给读者带来些帮助。脚本实现功能：

脚本实现功能：

一、newsreport上的ip与资产表上的IP做比较，即B+C ->D+E 或B->F,若都不相同，则舍弃掉newsreport上的该ip行
(newspaper 为python爬虫爬去绿盟漏洞报表html后整理的excel结果)
二、上个月的漏洞跟踪表的FHI列与newsreport的BCF列做对比，对比相等的就是（未整改状态）统计匹配的数目保存下来，
之后记到汇总表那里。而这个月找到、上个月无的漏洞即是（新增状态）统计匹配的数目也保存下来，把漏洞状态
三、汇总表上找到对应业务的FHI（ip+端口+漏洞名称），把汇总表上已有的该ip漏洞状态写到newsreport上。

注：统计表上不包括低的漏洞，最后需要保存的表及sheet为修改后的newsreport，把它命名为业务名，
1月份互联网公网漏洞数据统计.xlsx的前俩个sheet,（其中12月整改复核情况的最后一列不用理。）
各业务漏洞跟踪表下的汇总sheet就是1月公网的统计表的C列。设备主机去重，漏洞不去重

脚本涉及的表单材料：

脚本源代码：

脚本源代码：

try:
    import xlrd
except:
    print("pip3 install xlrd")
try:
    import xlwt
except:
    print("pip3 install xlwt")
import os
import re
import sys
import time
import csv
import operator
###读取一个excel表中某一个sheet表的全部数据
def readTable(filename,index,flag,readcols=[],colname=''):
    data_list=[]
    data=xlrd.open_workbook(filename)

    if type(index)==int:
        table=data.sheets()[index]
    elif type(index)==str:
        table=data.sheet_by_name(index)
    #读取表格内容
    nrows=table.nrows#表格行数
    ncols=table.ncols
    cell_ip=0   
    for row in range(nrows):
        row_list=[]
        if flag:#flag为True，读取整个表

            for col in range(ncols):
                ctype=table.cell(row,col).ctype
                cell=table.cell(row,col).value
                if ctype == 2 and cell % 1 == 0:  # 如果是整形
                        cell = str(int(cell))
                row_list.append(cell.strip())
        else:#flag为False，读取某些列
            if colname!='' and table.cell(row,3).value!=colname:
                continue
            for i in range(len(readcols)):
                ctype=table.cell(row,readcols[i]).ctype
                cell=table.cell(row,readcols[i]).value
                if ctype == 2 and cell % 1 == 0:  # 如果是整形
                        cell = str(int(cell))
                row_list.append(cell)
        data_list.append(row_list)
    return data_list

def readCsv(filename):
    new_data=[]
    csv_reader = csv.reader(open(filename))
    for row in csv_reader:
        if len(row)<10:
            count=10-len(row)
            for x in range(count):
                row.append("")
        if(row[0]=='low'):
            row[0]='低'
        elif (row[0]=='middle'):
            row[0]='中'
        else :
            row[0]='高'
        new_data.append(row)

    return new_data

def compareData(new_data, old_data, ip_list,total_bug):
    new_data_list = []
    for i in range(1,len(new_data)):
        for k in range(1,len(ip_list)):
            if (new_data[i][1] == ip_list[k][3] and new_data[i][2] == ip_list[k][4]) or new_data[i][1] == ip_list[k][5]:
                if new_data[i][0]!='低':
                    for j in range(0,len(old_data)):
                        if (new_data[i][1] == old_data[j][0]) and (new_data[i][2] == old_data[j][2]) and (new_data[i][5] == old_data[j][1]):
                            new_data[i][9]=(u'未整改') 
                            break                     
                    for j in range(0,len(total_bug)):
                        if (new_data[i][1] == total_bug[j][1]) and (new_data[i][2] == total_bug[j][3]) and (new_data[i][5] == total_bug[j][2]): 
                            new_data[i][9]=total_bug[j][4]
                            break
                    if (new_data[i][9]!="误报" and new_data[i][9]!="已整改但未修复" and new_data[i][9]!=(u'未整改')):
                        new_data[i][9]=(u'新增')

                new_data_list.append(new_data[i])
    return new_data_list
def getInfo(new_data,old_data):
    total_old_bug_num=0#上月高中危漏洞数量
    new_bug_num=0#新增
    old_bug_num=0#未整改
    feedback_bug_num_1=0#误报
    feedback_bug_num_2=0#已整改但未修复
    middle_ip=set()
    high_ip=set()
    middle_bug_num=0#中危漏洞
    high_bug_num=0#高危漏洞
    total_ip_num=0
    for i in range(0,len(old_data)):
        if old_data[i][3]!='低':
            total_old_bug_num+=1

    for i in range(0,len(new_data)):
        if(new_data[i][8]!=""):
            total_ip_num+=1
        if new_data[i][0]!='低':
            if new_data[i][9]=='新增':
                new_bug_num+=1
            elif new_data[i][9]=='未整改':
                old_bug_num+=1
            elif new_data[i][9]=='误报':
                feedback_bug_num_1+=1
            elif new_data[i][9]=='已整改但未修复':
                feedback_bug_num_2+=1
        if new_data[i][0]=='中' and new_data[i][9]!='误报' :
            middle_bug_num+=1
            middle_ip.add(new_data[i][1])
        if new_data[i][0]=='高' and new_data[i][9]!='误报':
            high_bug_num+=1
            high_ip.add(new_data[i][1])
    middle_ip=middle_ip.difference(high_ip)#去除高漏洞ip 
    total_bug_num=middle_bug_num+high_bug_num#高中危漏洞数量   
    return[total_ip_num,len(high_ip),len(middle_ip),len(middle_ip)+len(high_ip),high_bug_num,\
    middle_bug_num,total_bug_num],[(total_old_bug_num-old_bug_num),new_bug_num,feedback_bug_num_1,\
    feedback_bug_num_2,old_bug_num]

def writeTable(new_data,sheetName):
    sheet_head=[
        '工单申请','评估类型','评估申请时间','业务名称','子业务','IP地址/URL',
        '漏洞参数','漏洞名称','对应端口','漏洞类型','扫描工具','风险类型','风险等级',
        '漏洞说明','漏洞发现时间','漏洞验证说明','加固建议','安全评估厂家','安全评估人员',
        '安全评估专家电话','漏洞状态','是否误报','是否完成整改','未整改原因','整改人','整改人电话',
        '备注'
    ]
    font=xlwt.Font()
    borders = xlwt.Borders()
    font.name='宋体'
    font.height =220
    borders.left=xlwt.Borders.THIN
    borders.right = xlwt.Borders.THIN
    borders.top = xlwt.Borders.THIN
    borders.bottom = xlwt.Borders.THIN

    style_1=xlwt.XFStyle()
    style_1.font=font
    style_1.borders=borders

    style_2=xlwt.XFStyle()
    style_2.borders=borders
    style_2.font.name='微软雅黑'
    style_2.font.bold=True
    style_2.font.height =220
    style_2.alignment.horz = xlwt.Alignment.HORZ_CENTER
    style_2.alignment.vert = xlwt.Alignment.VERT_CENTER

    style_3=xlwt.XFStyle()
    style_3.alignment.horz = xlwt.Alignment.HORZ_CENTER
    style_3.alignment.vert = xlwt.Alignment.VERT_CENTER
    style_3.font=font
    style_3.borders=borders

    YW_time=time.strftime("YW-ZX-%Y-%m-%d",time.localtime())
    localtime=time.strftime("%Y/%m/%d",time.localtime())
    f = xlwt.Workbook()
    sheet = f.add_sheet(sheetName, cell_overwrite_ok=True)
    for i in range(len(sheet_head)):
        sheet.write(0, i, label=sheet_head[i],style=style_2)
    for i in range(len(new_data)):
            sheet.write(i+1,0,label=YW_time,style=style_3) 
            sheet.write(i+1,1,label='系统主机扫描',style=style_3)
            sheet.write(i+1,2,label=localtime,style=style_3)
            sheet.write(i+1,3,label=sheetName,style=style_3)
            sheet.write(i+1,10,label='绿盟远程安全评估系统',style=style_1)
            sheet.col(10).width=256*30
            sheet.write(i+1,14,label=localtime,style=style_3)
            sheet.write(i+1,17,label='天*信',style=style_3)
            sheet.write(i+1,18,label='郑，谢，吴，李',style=style_3)
            sheet.col(18).width=256*40
            sheet.write(i+1,19,label='188、156、188',style=style_3)
            sheet.col(19).width=256*50
    for i in range(len(new_data)):
        sheet.write(i+1,5, label=new_data[i][1],style=style_3)
        sheet.write(i+1,7, label=new_data[i][5],style=style_1)
        sheet.write(i+1,8, label=new_data[i][2],style=style_3)
        sheet.write(i+1,12, label=new_data[i][0],style=style_3)
        sheet.write(i+1,13, label=new_data[i][6],style=style_1)
        sheet.write(i+1,16, label=new_data[i][7],style=style_1)
        sheet.write(i+1,20, label=new_data[i][9],style=style_3)
    for i in (4,6,9,11,15,21,22,23,24,25,26):
        sheet.col(i).set_style(style_1)
    for i in(0,1,2,3,5,7,8,10,11,12,13,14,16,17):
        sheet.col(i).width=256*15
    filename='互联网公司-'+YW_time+'-'+sheetName+'公网-系统扫描漏洞跟踪表.xls'
    f.save(filename)

def main():
    path=os.listdir()
    new_data = []
    zichan_data = []
    old_data = []
    total_bug=[]
    new_data = readCsv('Newreport.csv')

    pattern=re.compile('[互联网公司].*?[系统扫描漏洞跟踪表].*?')
    ip_pattern=re.compile('.*?[互联网自有IP统计表].*?')
    for filename in path:
        if pattern.match(filename):
            print("1:",filename)
            old_data=readTable(filename,0,False,readcols=[5,7,8,12])
        elif ip_pattern.match(filename):
            print("2:",filename)
            zichan_data=readTable(filename,sys.argv[1],True) 
        elif filename=='汇总.xlsx':
            print("3:",filename)
            total_bug=readTable(filename,0,False,readcols=[3,5,7,8,20],colname=sys.argv[1])
    data = compareData(new_data,old_data, zichan_data,total_bug)
    """
    统计表数据
    """
    bug_info,compare_info=getInfo(data,old_data)
    print("统计表数据")
    print(bug_info,compare_info)
    writeTable(data,sys.argv[1])
if __name__ == '__main__':
    main()