[Python知识库]「爬FTP数据并下载到本地（python）」

?感觉网上很多的东西比较零零散散，根据这次的任务要求整合一个可以扫描网段的ip地址并爬取IP地址中可以匿名登陆FTP的数据（有原创有学习）

1. 扫描一个网段，获取其中所有的开放FTP服务的机器的IP地址
2. 依次获取每个FTP的文件目录内容，从每个FTP中下载一定量的文件

   import platform
   import sys
   import os
   import time
   import _thread
   import datetime
   from ftplib import FTP
   
   
   class FTP_P(FTP):
       def dirs(self, *args):
           cmd = 'LIST'
           templist = []
           func = None
           if args[-1:] and type(args[-1]) != type(''):
               args, func = args[:-1], args[-1]
           for arg in args:
               if arg:
                   cmd = cmd + (' ' + arg)
           self.retrlines(cmd, templist.append)
           return templist
   
   def download_single_url_ftp(stri):
       try:
           ftp = FTP_P()
           ftp.encoding = "utf-8"
           ftp.connect(stri,21)  # 连接的ftp sever和端口
           ftp.login("anonymous")  # 连接的用户名，密码
           # print(ftp.getwelcome()) #打印出欢迎信息
           ftp.cwd(r"/")  # 设置FTP当前操作的路径
           for i in ftp.dirs():
               print(i+'')
           ftpath = '/'
           localpath = 'D:/data/'
           ftpDownload(ftp,ftpath,localpath)
           ftp.quit()  # 退出ftp
       except (ConnectionRefusedError, TimeoutError, WindowsError) as e:
               print("{}的Ftp连接失败 {}".format(stri,str(e)))
               print()
               pass
       except BaseException as e:
               print("{}的Ftp连接失败 {}".format(stri,str(e)))
               print()
               pass
   
   
   def ftpDownload(ftp, ftpath, localpath):
       '''
       :param ftp: 登陆ftp返回的信息
       :param ftpath: ftp中的目标路径
       :param localpath: 存放下载文件的本地路径
       :return:
       '''
       print('Remote Path: {0}'.format(ftpath))
       if not os.path.exists(localpath):
           os.makedirs(localpath)#如果文件不在创建文件
       for file in ftp.nlst():
           print('file:', file)
           if len(ftp.nlst(file)) == 0:
               pass
           elif file == ftp.nlst(file)[0]:
               print('扫描到文件')
               ftpDownloadFile(ftp,file, localpath)
           else:
               print('扫描到文件夹')
               path = ftp.pwd() + '/' + file
               local = localpath+'/'+ file
               ftp.cwd(path)
               ftpDownload(ftp, path, local)#递归
               ftp.cwd('..')
       return True
   #python saomiao.py 149
   
   def ftpDownloadFile(ftp, ftpfile, localfile):
       bufsize = 1024
       path = os.path.join(localfile,ftpfile)
       with open(path, 'wb') as fid:
           print('正在下载：',ftpfile)
           ftp.retrbinary('RETR {0}'.format(ftpfile), fid.write, bufsize)  # 接收服务器文件并写入本地文件
           print('下载完毕。')
       return True
   
   
   def get_os():
       os = platform.system()
       if os == "Windows":
           return "n"
       else:
           return "c"
   
   def ping_ip(ip_str):
       cmd = ["ping", "-{op}".format(op=get_os()),
              "1", ip_str]
       output = os.popen(" ".join(cmd)).readlines()
   
       flag = False
       for line in list(output):
           if not line:
               continue
           if str(line).upper().find("TTL") >=0:#判断存活时间
               flag = True
               break
       if flag:
           print("*** *** *** ip: %s 可以ping通  *** *** ***"%(ip_str))
           download_single_url_ftp(ip_str)
   
   def find_ip(ip_prefix):
       for i in range(1,256):
           ip = ('%s.%s'%(ip_prefix,i))
           _thread.start_new_thread(ping_ip, (ip,))
           time.sleep(0.5)
           # ping_ip(ip)
   
   if __name__ == "__main__":
       startTime = datetime.datetime.now()
       print("start time %s"%(time.ctime()))
       net=sys.argv[1]
       args = "".join(("211.71."+net+".1"))#211.71.149
       ip_prefix = '.'.join(args.split('.')[:-1])#211.71.149
   
       find_ip(ip_prefix)
   
       endTime = datetime.datetime.now()
       print("end time %s"%(time.ctime()))
       print("total takes :",(endTime - startTime).seconds)