python写exploit采集器

import requests
from bs4 import *
import threading
import re
import optparse

urlsd=[]
#neirons=[]

def main():
    parser=optparse.OptionParser()
    parser.add_option(‘-m‘,action=‘store_true‘,dest=‘home‘,help=‘Save the home directory in the local area‘)
    parser.add_option(‘-w‘,action=‘store_true‘,dest=‘web‘,help=‘Save all the attack loads of Web‘)
    parser.add_option(‘-s‘,dest=‘search‘,help=‘search exploit‘)
    parser.add_option(‘-y‘,action=‘store_true‘,dest=‘long‘,help=‘Save the Long-range all exploit‘)
    parser.add_option(‘-b‘,action=‘store_true‘,dest=‘local‘,help=‘Save the local all exploit‘)
    (options,args)=parser.parse_args()
    if options.home:
        poc()
    elif options.web:
        web()
    elif options.search:
        searchs=options.search
        searchexploit(searchs)
    elif options.long:
        logins()
    elif options.local:
        local()
    else:
        parser.print_help()
        exit()
def poc():
    global headers
    print(‘[+]Emptying exploit1.txt‘)
    kw=open(‘exploitcs1.txt‘,‘w‘)
    kw.close()
    print(‘[+]Complete the emptying‘)
    print(‘[+] Generating a new list of exploit‘)
    url=‘http://expku.com/‘
    headers={‘user-agetn‘:‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36‘}
    rest=requests.get(url=url,headers=headers)
    qinx=rest.content.decode(‘gbk‘)
    kop=BeautifulSoup(qinx,‘html.parser‘)
    for x in kop.find_all(‘a‘):
        a=re.findall(‘<a href=".*?" target="_blank">.*?</a>‘,str(x))
        neiron="".join(a)
        nei=BeautifulSoup(neiron,‘html.parser‘)

        uw=nei.find_all(‘a‘)
        for u in uw:
            u1=u.get(‘href‘)
            urlsd.append(‘http://expku.com/‘.strip()+u1)

    urlsd.remove(urlsd[0])
    lk=list(set(urlsd))
    for m in lk:
        rest2=requests.get(url=m,headers=headers)
        pl=BeautifulSoup(rest2.content.decode(‘gbk‘),‘html.parser‘)
        for l in pl.find_all(‘h1‘):
            ks=‘title:‘,l.get_text(),‘‘,‘url:‘,rest2.url
            print(ks)
            li=‘{}‘.format(ks)
            xr=li.replace(‘(‘,‘‘).replace(‘)‘,‘‘).replace(‘,‘,‘‘).replace("‘‘",‘‘)
            pw=open(‘exploitcs1.txt‘,‘a‘)
            pw.write(xr)
            pw.write(‘\n‘)
            pw.close()
def web():
    print(‘[+]empty exploit web.txt‘)
    odw=open(‘exploitweb.txt‘,‘w‘)
    odw.close()
    print(‘[+]empty complete‘)
    print(‘[+]Start writing to the collected web exploit‘)
    urlsd=[]
    headers = {
        ‘user-agetn‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36‘}
    for h in range(88):
        url=‘http://expku.com/web/list_6_{}.html‘.format(h)
        reques=requests.get(url=url,headers=headers)
        kw=BeautifulSoup(reques.content.decode(‘gbk‘),‘html.parser‘)
        vb=kw.find_all(‘a‘)
        for q in vb:
            pq=q.get(‘href‘)
            urls=‘http://expku.com‘.strip()+pq
            kq=re.findall(‘http://expku.com/web/.*.html‘,urls)
            for k in kq:
                urlsd.append(k)
        kc=list(set(urlsd))
        for b in kc:
            tfs=requests.get(url=b,headers=headers)
            bds=BeautifulSoup(tfs.content.decode(‘gbk‘),‘html.parser‘)
            for t in bds.find_all(‘h1‘):
                print(t.get_text(), ‘‘, tfs.url)
                print(t.get_text(),‘‘,tfs.url,file=open(‘exploitweb.txt‘,‘a‘))


def searchexploit(searchs):
    print(‘[+]search give the result as follows:‘)
    jg=[]
    rs=[]
    urlsh=[]
    headers = {‘user-agetn‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36‘}
    urls=‘http://expku.com/search.php?keyword={}‘.format(searchs)
    resq=requests.get(url=urls,headers=headers)
    weq=BeautifulSoup(resq.content.decode(‘gbk‘),‘html.parser‘)
    oeq=weq.find_all(‘a‘)
    for r in oeq:
        ds=r.get(‘title‘)
        durl=r.get(‘href‘)
        burw=re.findall(‘/.*/.*.html‘,durl)
        op="".join(burw)
        rs.append(op)
        kdw = ‘{}‘.format(ds)
        jg.append(kdw.replace(‘None‘, ‘‘))
    while ‘‘ in rs:
        rs.remove(‘‘)
    for g in rs:
        uw=‘http://expku.com‘.strip()+g
        urlsh.append(uw)
        urlsqf=‘http://expku.com‘.strip()+durl

    while ‘‘ in jg:
        jg.remove(‘‘)

    for g in range(0,len(urlsh)):
        print(jg[g],urlsh[g])

def logins():
    print(‘[+]empty exploitlong.txt‘)
    lwe=open(‘exploitlong.txt‘,‘w‘)
    lwe.close()
    print(‘[+]Get all remote exploit‘)
    urls=[]
    zj=[]
    headers = {
        ‘user-agetn‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36‘}
    for i in range(75):
        url=‘http://expku.com/remote/list_4_{}.html‘.format(i)
        regw=requests.get(url=url,headers=headers)
        lvq=BeautifulSoup(regw.content.decode(‘gbk‘),‘html.parser‘)
        fwq=lvq.find_all(‘a‘)
        for d in fwq:
            eq=d.get(‘href‘)
            oeq=re.findall(‘/remote/.*.html‘,eq)
            for b in oeq:
                ks=‘http://expku.com‘.strip()+b
                urls.append(ks)
        qwe=list(set(urls))
        for asd in lvq.find_all(‘a‘):
            kl=re.findall(‘<a href=".*" target="_blank">.*</a>‘,str(asd))
            for n in kl:
                vk=‘‘.strip()+n
                peq=BeautifulSoup(vk,‘html.parser‘)
                for t in qwe:
                    zj.append(peq.get_text()+‘ ‘+t)
        jb=list(set(zj))
        for j in jb:
            print(j)
            print(j,file=open(‘exploitlong.txt‘,‘a‘))


def local():
    print(‘[+]empty exploitlocal.txt‘)
    wd=open(‘exploitlocal.txt‘,‘w‘)
    wd.close()
    print(‘[+]get local exploit‘)
    for j in range(56):
        uk=[]
        url=‘http://expku.com/local/list_5_{}.html‘.format(j)
        headers = {
            ‘user-agetn‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36‘}
        rwqe=requests.get(url=url,headers=headers)
        vdq=BeautifulSoup(rwqe.content.decode(‘gbk‘),‘html.parser‘)
        hk=vdq.find_all(‘a‘)
        for f in hk:
            ddo=f.get(‘href‘)
            kio=re.findall(‘/local/.*.html‘,str(ddo))
            for g in kio:
                url=‘http://expku.com‘.strip()+g
                uk.append(url)
        yf=list(set(uk))
        for c in yf:
            rtq=requests.get(url=c,headers=headers)
            vdq=BeautifulSoup(rtq.content.decode(‘gbk‘),‘html.parser‘)
            for a in vdq.find_all(‘h1‘):
                print(a.get_text(),‘‘,rtq.url)
                print(a.get_text(), ‘‘, rtq.url,file=open(‘exploitlocal.txt‘,‘a‘))

#while ‘‘ in neirons:
 #   neirons.remove(‘‘)

#while ‘ ‘ in neirons:
 #   neirons.remove(‘ ‘)


#urlsd.remove(urlsd[0])
#rd=list(set(urlsd))

#for q in range(0,len(rd)):
 #   print(neirons[q],rd[q])

if __name__ == ‘__main__‘:
    main()