【飞桨/百度领航团/零基础Python】百度飞桨领航团零基础Python速成营笔记-06

课程链接：课程传送门

一、文件处理

1.1、文件打开

• #建议使用这种方法，避免忘记close
  with open('work/train_data_cor.txt') as f:
      for line in f:
          data = line.strip().split(',')
          print('姓名：'+data.pop(0)+'生日：'+data.pop(0)+'时间：'+str(data))
  

1.1.2、文件内数据有问题

1.1.2.1、使用异常跳过有问题的数据

• f = open('work/train_data_wrg.txt')
  for line in f:
      data = line.strip().split(',')
      try:
          print('姓名：'+data.pop(0)+'生日：'+data.pop(0)+'时间：'+str(data))
      except:
          pass
  f.close()
  

1.1.2.2、增加代码判断

• f = open('work/train_data_wrg.txt')#1
  for line in f:#2
      data = line.strip().split(',')
      if len(data) != 1:
          print('姓名：'+data.pop(0)+'生日：'+data.pop(0)+'时间：'+str(data))
  
  f.close()
  

1.1.2.3、若文件不存在

• f = open('work/train_data1.txt') for line in f:
  data = line.strip().split(',')
  if len(data) != 1:
      print('姓名：'+data.pop(0)+'生日：'+data.pop(0)+'时间：'+data)
  f.close()
  

1.2、file对象的函数列表

• with open('work/train_data.txt') as f:
      data = f.read()
      print('整个文件\n'+data)
      f.seek(0)
      data = f.read(10)
      print('读取指定大小的文件内容\n'+data)
      print(f.tell())
  '''
  整个文件
  james,2004-5-21,2.34,3:21,2.34,2.45,3.01,2:01,2:01,3:10,2-22
  julie,2006-5-9,2.59,2.11,2:11,2:23,3-10,2-23,3:10,3.21,3-21
  kenny
  sarah,2004-3-8,2:58,2.58,2:39,2-25,2-55,2:54,2.18,2:55,2:55
  mikey,2003-9-10,2:22,3.01,3:01,3.02,3:02,3.02,3:22,2.49,2:38
  
  读取指定大小的文件内容
  james,2004
  10
  '''
  

1.3、文件的写入

• f = open('work/data.txt','w')
  f.write('this is file content')
  f.close()
  

二、json

1.1、对象转json

• import json
  class Athlete(json.JSONEncoder):   #继承json.JSONEncoder
      def __init__(self,a_name,a_dob=None,a_times=[]):
          self.name = a_name
          self.dob = a_dob
          self.times = a_times
      def top3(self):
          return sorted(set([self.sanitize(t) for t in self.times]))[0:3]
      def sanitize(self,time_string):
          if '-' in time_string:
              splitter = '-'
          elif ':' in time_string:
              splitter = ':'
          else:
              return (time_string)
          (mins,secs) = time_string.split(splitter)
          return (mins+'.'+secs)
  
  
  with open('work/train_data_cor.txt') as f:
      data = f.readline().strip().split(',')
      ath = Athlete(data.pop(0),data.pop(0),data)
      print(ath)
  
  ath_json = json.dumps(ath.__dict__)   #.__dict__把ath转换成字典的形式
  print(ath_json)
  

1.2、类中的json形式的变量保存到文件

• with open('work/json.txt','w') as f:
      json.dump(ath_json,f)  #注意dump与dumps的区别
  '''
  "{\"name\": \"james\", \"dob\": \"2004-5-21\", \"times\": [\"2.34\", \"3:21\", \"2.34\", \"2.45\", \"3.01\", \"2:01\", \"2:01\", \"3:10\", \"2-22\"]}"
  '''
  

1.3、读取json文件内容

• with open('work/json.txt') as f:
      ath = json.load(f)
      print(ath)
  '''
  {"name": "james", "dob": "2004-5-21", "times": ["2.34", "3:21", "2.34", "2.45", "3.01", "2:01", "2:01", "3:10", "2-22"]}
  '''
  

三、目录访问

3.1、目录访问常见命令

3.1.1、

• import os
  #返回当前工作目录
  current_path = os.getcwd()
  print('当前路径：'+current_path)
  

3.1.2

• #改变当前工作目录
  os.chdir('/home/aistudio/work')
  #运行mkdir命令
  os.system('mkdir today')
  

3.1.3

• from pathlib import Path
  #返回当前绝对路径
  abs_path = os.path.abspath('')
  print('abs_path：'+abs_path)
  #路径是否存在
  Path(abs_path).exists()
  

3.1.4

• print('当前路径：'+os.getcwd())
  listdir = os.listdir()
  #返回当前路径下文件和文件夹名
  print(listdir)
  

3.1.5

• #是否为文件夹
  os.path.isdir('/home/aistudio/work/today')
  

3.2、显示work路径下的所有类型为txt的文件

• import os
  listdir = os.listdir('/home/aistudio/work')
  
  target = []
  for name in listdir:
      #防止文件名与文件夹名一样的情况
      # print(os.path.isfile(name))
      
      temp = name.split('.')
      (filename,filetype) = (temp.pop(0),temp.pop(0))
      if filetype == 'txt':
          target.append(name)
   
      # print('name:%s,type:%s' %(filename,filetype))
  
  print(target)
  

• import pdb：debug时引入

3.3、显示文件夹中的txt文件

• import os
  
  target = []
  
  path = '/home/aistudio/work'
  listdir = os.listdir(path)
  for name in listdir:
      #防止文件名与文件夹名一样的情况
      if os.path.isfile(path+'/'+name):
          temp = name.split('.')
          (filename,filetype) = (temp.pop(0),temp.pop(0))
          if filetype == 'txt':
              target.append(name)  
      else:
          #如果是文件夹，需要读取该文件夹的列表        
          dir_path = path+'/'+name
          listdir = os.listdir(dir_path)
          for name in listdir:
              #防止文件名与文件夹名一样的情况
              if os.path.isfile(dir_path+'/'+name):
                  temp = name.split('.')
                  (filename,filetype) = (temp.pop(0),temp.pop(0))
                  if filetype == 'txt':
                      target.append(name)
  print('结果：'+str(target))
  

3.4、递归遍历文件夹内所有的txt文件

• import os
  
  def recur(path):
      listdir = os.listdir(path)
      for name in listdir:
          if name[0] is '.' or name[0] is '_':
              continue
          next_path = path+'/'+name
          if os.path.isfile(next_path) :
              # print(next_path + '=====isfile')
              temp = name.split('.')
              (filename,filetype) = (temp.pop(0),temp.pop(0))
              if filetype == 'txt':
                  target.append(name)
          else:
              recur(next_path)
      return os.path.dirname(next_path)
  path = '/home/aistudio/work'
  target = []
  recur(path)
  print(target)
  

四、进程和线程

• import threading, zipfile
  
  class AsyncZip(threading.Thread):
      def __init__(self, infile, outfile):
          threading.Thread.__init__(self)
          self.infile = infile
          self.outfile = outfile
      def run(self):
          f = zipfile.ZipFile(self.outfile, 'w', zipfile.ZIP_DEFLATED)
          f.write(self.infile)
          f.close()
          print('压缩完成，您要的文件在:', self.outfile)
  
  background = AsyncZip('work/loren.txt', 'work/myarchive.zip')
  print('压缩作业开始了，请您耐心等待...')
  background.start()
  print('我正在为您压缩，请问还需要帮您做什么呢？')
  background.join()
  

•