python下载文件记录黑名单的实现代码

时间:2021-11-14 06:04:25

具体代码如下所示:

?
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
#!/usr/bin/python
# -*- coding: GBK -*-
# -*- coding: UTF-8 -*-
from ftplib import FTP
import os
import datetime
ftp_server = '127.0.0.1' # 对应ftp服务器地址
username = 'ponshine' # 用户名
password = '1qaz2wsx' # 密码
ftp_path = '/GBCC/' # ftp目录
local_path = "C:\F\python\pythonwangtest\wyjj2\\" #本地的目录
# 连接FTP
def ftpconnect():
  ftp = FTP()
  ftp.set_debuglevel(2) # 打开调试级别2,显示详细信息
  ftp.connect(ftp_server, 21) # 连接
  ftp.login(username, password) # 登录,如果匿名登录则用空串代替即可
  return ftp
# 获取当前的年月日时分秒
def getdatetime():
  i = datetime.datetime.now()
  date = ("%s%s%s%s%s%s" % (i.year, i.month, i.day, i.hour,i.minute,i.second))
  return date # 需返回才能取值
# 获取当前的年月日
def getdate():
  import datetime
  i = datetime.datetime.now()
  date = ("%s%s%s" % (i.year, i.month, i.day))
  return date # 需返回才能取值
def downloadfile(remotepath, localpath):
  ftp = ftpconnect() # 连接ftp
  print ftp.getwelcome() # 显示ftp服务器欢迎信息
  ftp_filename = ftp.nlst(remotepath) # 运用nlst()获取文件
  print 'ftp_filename: ', ftp_filename # ftp上的文件名
  for eachfile in ftp_filename: # 循坏取文件名
    if eachfile.endswith('.AVL'):
      localpath_files = eachfile.split("/")
      localpath_file = localpath_files[len(localpath_files) - 1] # 文件名:localpath_file= GBCC_201611102155_01.AVL
      print "localpath_file--->" + localpath_file
      # 创建记录下载文件名的文件名
      writefiletext = local_path + getdate() + ".txt" # 记录下载后的文件名
      print "writefile_text--->" + writefiletext      
      if os.path.exists(writefiletext):
        print writefiletext + "is exists"
      else:
        print writefiletext + "is not exists"
        makefile = open(writefiletext,"w+")
        makefile.close()
      files = open(writefiletext, "r") # 打开黑名单
      print "writefiletext--->" + writefiletext
      try:
        all_the_text = files.read()
        print "all_the_text-------》" + all_the_text
        if all_the_text.__contains__(localpath_file):
          print "文件已下载,不需要重复下载"
        else:
          print "文件没有下载,现在开始下载"
          bufsize = 1024 # 设置缓冲块大小
          fp = open(localpath + localpath_file, "wb+")
          ftp.retrbinary('RETR ' + eachfile, fp.write, bufsize) # 下载文件
          fo = open(writefiletext,"ab+")
          fo.write(localpath_file + "\n") # 将每个文件名写入文件
          fo.flush() # 刷新文件
          fo.close()
          fp.flush()
      finally:
        print "结束了"
        files.close()
  ftp.set_debuglevel(0)
  ftp.close()
if __name__ == "__main__":
  downloadfile("/GBCC", "C:\F\python\pythonwangtest\wyjj2\\")

  补充:python 黑名单过滤

  需要过滤一些词语

写了下面这个函数,在blacklist 文件中添加需要过滤的词语

?
1
2
3
4
5
6
7
8
9
10
#过滤黑名单列表中出现的
def in_lists(str):
  str_lists=[]
  fd = open('./filter/blacklist')
  for line in fd.readlines():
    str_lists.append(line.strip())
  if str in str_lists:
    return 0
  else:
    return 1

通过 python 自带的 filter函数 调用, in_lists ,filter函数会过滤掉 bool 值为 1 的列表中的元素

 filter( in_lists , urls )

总结

以上所述是小编给大家介绍的python下载文件记录黑名单,希望对大家有所帮助,如果大家有任何疑问请给我留言,小编会及时回复大家的。在此也非常感谢大家对服务器之家网站的支持!

原文链接:http://www.cnblogs.com/wangyouqun2017/p/7722775.html