import urllib.requestimport restarturl="http://wooyun.org/searchbug.php?q=%E9%87%91%E8%9E%8D"def get_html_response(url):    html_response = urllib.request.urlopen(url).read().decode(‘utf-8‘)    return html_responsedef geturl(starturl):    a=get_html_response(starturl)    childurl=(re.findall(r‘/bugs/wooyun-\w*-\w*\b‘,a))    return childurldef get_nextpage(starturl):    d=get_html_response(starturl)    nextpage=(re.findall(r‘searchbug.php\?q=金融&pNO=\w‘,d))    return nextpageresult=[]result2=[]for i in get_nextpage(starturl):    result+=geturl(‘http://wooyun.org/‘+re.sub(‘金融‘,‘%E9%87%91%E8%9E%8D‘,i))    #扫描各种漏洞的url地址放入result中result=set(result)#去除result中重复的地址#print(len(result))#测试结果为87，正确#信息存储+文件处理output=open("D:\\a.txt",‘w+‘)for i in result:    k=get_html_response(‘http://wooyun.org/‘+re.sub(‘金融‘,‘%E9%87%91%E8%9E%8D‘,i))#下载页面到k，可以把    info=re.findall(r‘<h3>\w*：\s*\w*\s*</h3>‘,k)#空白字符用/s,寻找所有适用于<h3>标签的文字    for j in info:        j=re.sub(r‘：\s‘,‘:‘,j)        j=re.sub(r‘<h3>‘,‘‘,j)        j=re.sub(r‘</h3>‘,‘,‘,j)        j=j.split()        output.writelines(j)        output.writelines("\n")output.close()