[python]《Python编程快速上手:让繁琐工作自动化》学习笔记2

1. 读写文件笔记（第8章）(代码下载)

1.1 文件与文件路径
通过import os调用os模块操作目录，常用函数如下：

函数	用途
os.getcwd()	取得当前工作路径
os.chdir()	改变当前工作路径
os.makedirs(path)	创建新文件夹
os.listdir(path)	返回文件名字符串的列表
os.path.join(path1,path2,...)	连接路径
os.path.abspath(path)	返回绝对路径
os.path.isabs(path)	检查是否绝对路径
os.path.relpath(path, start)	返回从start路径到path的相对路径
os.path.dirname(path)	返回目录名
os.path.basename(path)	返回文件名
os.path.split(path)	返回目录名和文件名的元组
os.path.getsize(path)	返回path参数中文件的字节数
os.path.exists(path)	检查路径是否存在
os.path.isfile(path)	检查路径是否文件
os.path.isdir(path)	检查路径是否文件夹

1.2 文件读写

在Python 中，读写文件有3 个步骤：

1. 调用open()函数，返回一个File 对象。
2. 调用File 对象的read()或write()方法。
3. 调用File 对象的close()方法，关闭该文件

# 将'w'作为第二个参数传递给open(),以写模式打开该文件
# 写模式会清空源文件
baconFile = open('bacon.txt', 'w')
baconFile.write('Hello world!\n')
baconFile.close()

# 将'a'作为第二个参数传递给open()，以添加模式打开该文件
# 添加模式将在已有文件的末尾添加文本
baconFile = open('bacon.txt', 'a')
baconFile.write('Bacon is not a vegetable.')
baconFile.close()

# 读文件
baconFile = open('bacon.txt')
# read将文件的内容看成是单个大字符串
content = baconFile.read()
# readlines从该文件取得一个字符串的列表。列表中的每个字符串就是文本中的每一行
# content = baconFile.readlines()
baconFile.close()
print(content)

Hello world!
Bacon is not a vegetable.

2. 项目练习

2.1 生成随机的测验试卷文件

# -*- coding: utf-8 -*-
import random


# 测验数据
# The quiz data. Keys are states and values are their capitals.
capitals = {'Alabama': 'Montgomery', 'Alaska': 'Juneau', 'Arizona': 'Phoenix',
'Arkansas': 'Little Rock', 'California': 'Sacramento', 'Colorado': 'Denver',
'Connecticut': 'Hartford', 'Delaware': 'Dover', 'Florida': 'Tallahassee',
'Georgia': 'Atlanta', 'Hawaii': 'Honolulu', 'Idaho': 'Boise', 'Illinois':
'Springfield', 'Indiana': 'Indianapolis', 'Iowa': 'Des Moines', 'Kansas':
'Topeka', 'Kentucky': 'Frankfort', 'Louisiana': 'Baton Rouge', 'Maine':
'Augusta', 'Maryland': 'Annapolis', 'Massachusetts': 'Boston', 'Michigan':
'Lansing', 'Minnesota': 'Saint Paul', 'Mississippi': 'Jackson', 'Missouri':
'Jefferson City', 'Montana': 'Helena', 'Nebraska': 'Lincoln', 'Nevada':
'Carson City', 'New Hampshire': 'Concord', 'New Jersey': 'Trenton', 'New Mexico': 'Santa Fe', 'New York': 'Albany', 'North Carolina': 'Raleigh',
'North Dakota': 'Bismarck', 'Ohio': 'Columbus', 'Oklahoma': 'Oklahoma City',
'Oregon': 'Salem', 'Pennsylvania': 'Harrisburg', 'Rhode Island': 'Providence',
'South Carolina': 'Columbia', 'South Dakota': 'Pierre', 'Tennessee':
'Nashville', 'Texas': 'Austin', 'Utah': 'Salt Lake City', 'Vermont':
'Montpelier', 'Virginia': 'Richmond', 'Washington': 'Olympia', 
'West Virginia': 'Charleston', 'Wisconsin': 'Madison', 'Wyoming': 'Cheyenne'}
    
    
# 生成试卷
# 试卷份数    
n_quiz=2
for quizNum in range(n_quiz):
    # Create the quiz and answer key files.
    # 试卷
    quizFile = open('capitalsquiz%s.txt' % (quizNum + 1), 'w')
    # 答案
    answerKeyFile = open('capitalsquiz_answers%s.txt' % (quizNum + 1), 'w')
    # Write out the header for the quiz.
    # 头文件
    quizFile.write('Name:\n\nDate:\n\nPeriod:\n\n')
    quizFile.write((' ' * 20) + 'State Capitals Quiz (Form %s)' % (quizNum + 1))
    quizFile.write('\n\n')
    # Shuffle the order of the states.
    states = list(capitals.keys())
    # 创建了美国州名的随机列表
    random.shuffle(states)    
    
    
    # 创建答案    
    # Loop through all 50 states, making a question for each.
    for questionNum in range(50):
        # Get right and wrong answers.
        # 正确答案
        correctAnswer = capitals[states[questionNum]]
        # 错误答案
        wrongAnswers = list(capitals.values())
        # 删除正确的答案
        del wrongAnswers[wrongAnswers.index(correctAnswer)]
        # 随机取出三个答案
        wrongAnswers = random.sample(wrongAnswers, 3)
        answerOptions = wrongAnswers + [correctAnswer]
        random.shuffle(answerOptions)    
    
        # 将内容写入测验试卷和答案文件
        # Write the question and the answer options to the quiz file.
        quizFile.write('%s. What is the capital of %s?\n' % (questionNum + 1,states[questionNum]))
        
    
        for i in range(4):
            quizFile.write(' %s. %s\n' % ('ABCD'[i], answerOptions[i]))
        quizFile.write('\n')
        
        # Write the answer key to a file.   
        answerKeyFile.write('%s. %s\n' % (questionNum + 1, 'ABCD'[answerOptions.index(correctAnswer)]))
    quizFile.close()
    answerKeyFile.close()    

2.2 疯狂填词

创建一个疯狂填词（Mad Libs）程序，它将读入文本文件，并让用户在该文本文件中出现ADJECTIVE、NOUN、ADVERB 或VERB 等单词的地方，加上他们自己的文本。

import re

# text:
'''
The ADJECTIVE panda walked to the NOUN and then VERB. A nearby NOUN was unaffected by these events
'''
# 输入文件
input_file = open('./input_text.txt')
input_text = input_file.read()
input_file.close()

# 输出文本
output_text = input_text

# 输入文本寻找关键词
keywords = re.compile('adjective|noun|verb', re.IGNORECASE)
mo = keywords.findall(input_text)

# 一个一个词进行替换
for word in mo:
    if word[0].lower() == 'a':
        replacewords = input('Enter an {}:\n'.format(word))
    else:
        replacewords = input('Enter a {}:\n'.format(word))
    regex = re.compile(word)
    # 每一次替换一个词
    output_text = regex.sub(replacewords, output_text, 1)

# 写入新文件
output_file = open('output_text.txt', 'w')
output_file.write(output_text)
output_file.close()
print(output_text)

Enter an ADJECTIVE:
silly
Enter a NOUN:
chandelier
Enter a VERB:
screamed
Enter a NOUN:
pickup truck
The silly panda walked to the chandelier and then screamed. A nearby pickup truck was unaffected by these events.

2.3 正则表达式查找

编写一个程序，打开文件夹中所有的.txt 文件，查找匹配用户提供的正则表达式的所有行。结果应该打印到屏幕上。

import os
import re

path = "./"

# 判断路径目录是否存在
folder = os.path.exists(path)
if folder == False:
    print("文件目录不存在！")


#返回指定目录下所有的文件名和文件夹名列表
file_Name = os.listdir(path)

#创建正则表达式
keywords = re.compile(r'ADJECTIVE')

# 找出txt文件
for i in range(len(file_Name)):
    #判断是否为txt文件
    if os.path.isfile(os.path.join(path, file_Name[i])) and file_Name[i].split('.')[-1] == 'txt':
        # 打开文件
        file = open(os.path.join(path, file_Name[i]))
        file_texts = file.readlines()
        for texts in file_texts:
            #找出匹配正则表达式的内容
            text_put = keywords.search(texts)
            #输出结果
            if text_put != None:
                #打印当前行
                print('{}'.format(texts))

The ADJECTIVE panda walked to the NOUN and then VERB. A nearby NOUN was unaffected by these events.