1. 讀寫文件(第8章)
1.1 文件與文件路徑
通過import os調用os模塊操作目錄,常用函數如下:
函數 | 用途 |
---|---|
os.getcwd() | 取得當前工作路徑 |
os.chdir() | 改變當前工作路徑 |
os.makedirs(path) | 創建新文件夾 |
os.listdir(path) | 返回文件名字符串的列表 |
os.path.join(path1,path2,…) | 連接路徑 |
os.path.abspath(path) | 返回絕對路徑 |
os.path.isabs(path) | 檢查是否絕對路徑 |
os.path.relpath(path, start) | 返回從start路徑到path的相對路徑 |
os.path.dirname(path) | 返回目錄名 |
os.path.basename(path) | 返回文件名 |
os.path.split(path) | 返回目錄名和文件名的元組 |
os.path.getsize(path) | 返回path參數中文件的字節數 |
os.path.exists(path) | 檢查路徑是否存在 |
os.path.isfile(path) | 檢查路徑是否文件 |
os.path.isdir(path) | 檢查路徑是否文件夾 |
1.2 文件讀寫
在Python 中,讀寫文件有3 個步驟:
- 調用open()函數,返回一個File 對象。
- 調用File 對象的read()或write()方法。
- 調用File 對象的close()方法,關閉該文件
# 將'w'作爲第二個參數傳遞給open(),以寫模式打開該文件
# 寫模式會清空源文件
baconFile = open('bacon.txt', 'w')
baconFile.write('Hello world!\n')
baconFile.close()
# 將'a'作爲第二個參數傳遞給open(),以添加模式打開該文件
# 添加模式將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()
# 讀文件
baconFile = open('bacon.txt')
# read將文件的內容看成是單個大字符串
content = baconFile.read()
# readlines從該文件取得一個字符串的列表。列表中的每個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. 項目練習
2.1 生成隨機的測驗試卷文件
# -*- coding: utf-8 -*-
import random
# 測驗數據
# 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'}
# 生成試卷
# 試卷份數
n_quiz=2
for quizNum in range(n_quiz):
# Create the quiz and answer key files.
# 試卷
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.
# 頭文件
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())
# 創建了美國州名的隨機列表
random.shuffle(states)
# 創建答案
# Loop through all 50 states, making a question for each.
for questionNum in range(50):
# Get right and wrong answers.
# 正確答案
correctAnswer = capitals[states[questionNum]]
# 錯誤答案
wrongAnswers = list(capitals.values())
# 刪除正確的答案
del wrongAnswers[wrongAnswers.index(correctAnswer)]
# 隨機取出三個答案
wrongAnswers = random.sample(wrongAnswers, 3)
answerOptions = wrongAnswers + [correctAnswer]
random.shuffle(answerOptions)
# 將內容寫入測驗試卷和答案文件
# 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 瘋狂填詞
創建一個瘋狂填詞(Mad Libs)程序,它將讀入文本文件,並讓用戶在該文本文件中出現ADJECTIVE、NOUN、ADVERB 或VERB 等單詞的地方,加上他們自己的文本。
import re
# text:
'''
The ADJECTIVE panda walked to the NOUN and then VERB. A nearby NOUN was unaffected by these events
'''
# 輸入文件
input_file = open('./input_text.txt')
input_text = input_file.read()
input_file.close()
# 輸出文本
output_text = input_text
# 輸入文本尋找關鍵詞
keywords = re.compile('adjective|noun|verb', re.IGNORECASE)
mo = keywords.findall(input_text)
# 一個一個詞進行替換
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)
# 每一次替換一個詞
output_text = regex.sub(replacewords, output_text, 1)
# 寫入新文件
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 正則表達式查找
編寫一個程序,打開文件夾中所有的.txt 文件,查找匹配用戶提供的正則表達式的所有行。結果應該打印到屏幕上。
import os
import re
path = "./"
# 判斷路徑目錄是否存在
folder = os.path.exists(path)
if folder == False:
print("文件目錄不存在!")
#返回指定目錄下所有的文件名和文件夾名列表
file_Name = os.listdir(path)
#創建正則表達式
keywords = re.compile(r'ADJECTIVE')
# 找出txt文件
for i in range(len(file_Name)):
#判斷是否爲txt文件
if os.path.isfile(os.path.join(path, file_Name[i])) and file_Name[i].split('.')[-1] == 'txt':
# 打開文件
file = open(os.path.join(path, file_Name[i]))
file_texts = file.readlines()
for texts in file_texts:
#找出匹配正則表達式的內容
text_put = keywords.search(texts)
#輸出結果
if text_put != None:
#打印當前行
print('{}'.format(texts))
The ADJECTIVE panda walked to the NOUN and then VERB. A nearby NOUN was unaffected by these events.