前言：
不知道写什么好，绕来绕去还是写回爬虫这一块。之前的都爬了一遍。这次爬点好用一点的网站。
0x01:
自行备好requests模块
目标站：http://tool.chinaz.com/
0x2:
代码：
import optparseimport requestsimport reimport sysfrom bs4 import BeautifulSoupdef main(): usage="[-z Subdomain mining]" \ "[-p Side of the station inquiries]" \ "[-x http status query]" parser=optparse.OptionParser(usage) parser.add_option('-z',dest="Subdomain",help="Subdomain mining") parser.add_option('-p',dest='Side',help='Side of the station inquiries') parser.add_option('-x',dest='http',help='http status query') (options,args)=parser.parse_args() if options.Subdomain: subdomain=options.Subdomain Subdomain(subdomain) elif options.Side: side=options.Side Side(side) elif options.http: http=options.http Http(http) else: parser.print_help() sys.exit()def Subdomain(subdomain): print('-----------Subdomains quickly tap-----------') url="http://m.tool.chinaz.com/subdomain/?domain={}".format(subdomain) header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'} r=requests.get(url,headers=header).content g = re.finditer('\D[a-zA-Z0-9][-a-zA-Z0-9]{0,62}\D(\.[a-zA-Z0-9]\D[-a-zA-Z0-9]{0,62})+\.?', str(r)) for x in g: lik="".join(str(x)) opg=BeautifulSoup(lik,'html.parser') for link in opg.find_all('td'): lops=link.get_text() print(lops)def Side(side): print('--------Side of the station inquiries--------') url="http://m.tool.chinaz.com/same/?s={}".format(side) header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'} r=requests.get(url,headers=header).content g=r.decode('utf-8') ksd=re.finditer('[a-zA-Z0-9][-a-zA-Z0-9]{0,62}(\.[a-zA-Z0-9][-a-zA-Z0-9]{0,62})+\.?',str(g)) for l in ksd: ops="".join(str(l)) pods=BeautifulSoup(ops,'html.parser') for xsd in pods.find_all('a'): sde=re.findall('[a-zA-z]+://[^\s]*',str(xsd)) low="".join(sde) print(low)def Http(http): print('--------Http status query--------') url="http://{}".format(http) header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'} r=requests.get(url,headers=header) b=r.headers for sdw in b: print(sdw,':',b[sdw])if __name__ == '__main__': main() 运行截图：
-h 帮助
-z 子域名挖掘
-p 旁站查询
-x http状态查询
-z 截图
-p 截图
-x 截图
距离上学还有5天。啊啊啊啊啊啊啊啊啊啊啊