Handling Files, Directories, and Data

Alan · Alan · commit 0b18e574f4e4 · 2019-02-27T14:56:01.000+08:00
diff --git a/Chapter05/Haltermanpythonbook.pdf b/Chapter05/Haltermanpythonbook.pdf
diff --git a/Chapter05/compare_data.py b/Chapter05/compare_data.py
@@ -0,0 +1,9 @@
+import pandas as pd
+
+df1 = pd.read_csv('student1.csv')
+df2 = pd.read_csv('student2.csv')
+s1 = set([tuple(values) for values in df1.values.tolist()])
+s2 = set([tuple(values) for values in df2.values.tolist()])
+s1.symmetric_difference(s2)
+print(pd.DataFrame(list(s1.difference(s2))), '\n')
+print(pd.DataFrame(list(s2.difference(s1))), '\n')
diff --git a/Chapter05/compress_a_directory.py b/Chapter05/compress_a_directory.py
@@ -0,0 +1,2 @@
+import shutil
+shutil.make_archive('work', 'zip', 'work/')
diff --git a/Chapter05/examine_tar_file_content.py b/Chapter05/examine_tar_file_content.py
@@ -0,0 +1,3 @@
+import tarfile
+tar_file = tarfile.open('work.tar.gz', 'r:gz')
+print(tar_file.getnames())
diff --git a/Chapter05/hello.py b/Chapter05/hello.py
@@ -0,0 +1,3 @@
+print("")
+print("Hello World\n")
+print("Hello Python\n")
diff --git a/Chapter05/merge_data.py b/Chapter05/merge_data.py
@@ -0,0 +1,6 @@
+import pandas as pd
+
+df1 = pd.read_csv('student1.csv')
+df2 = pd.read_csv('student2.csv')
+result = pd.concat([df1, df2])
+print(result)
diff --git a/Chapter05/metadata_example.py b/Chapter05/metadata_example.py
@@ -0,0 +1,12 @@
+import PyPDF2
+
+def main():
+	file_name = 'Haltermanpythonbook.pdf'
+	pdfFile = PyPDF2.PdfFileReader(open(file_name, 'rb'))
+	pdf_data = pdfFile.getDocumentInfo()
+	print('----Metadata of the file----')
+	for md in pdf_data:
+		print(md+ ':' +pdf_data[md])
+
+if __name__ == '__main__':
+	main()
diff --git a/Chapter05/pattern_match.py b/Chapter05/pattern_match.py
@@ -0,0 +1,10 @@
+import glob
+
+file_match = glob.glob('*.txt')
+print(file_match)
+file_match = glob.glob('[0-9].txt')
+print(file_match)
+file_match = glob.glob('**/*.txt', recursive=True)
+print(file_match)
+file_match = glob.glob('**/', recursive=True)
+print(file_match)
diff --git a/Chapter05/shutil_copy_example.py b/Chapter05/shutil_copy_example.py
@@ -0,0 +1,5 @@
+import shutil
+import os
+
+shutil.copy('hello.py', 'welcome.py')
+print('Copy Successful')
diff --git a/Chapter05/shutil_move_example.py b/Chapter05/shutil_move_example.py
@@ -0,0 +1,2 @@
+import shutil
+shutil.move('/home/vagrant/sample.txt', '/home/vagrant/Desktop/.')
diff --git a/Chapter05/student1.csv b/Chapter05/student1.csv
@@ -0,0 +1,7 @@
+Id,Name,Gender,Age,Address
+101,John,Male,20,New York
+102,Mary,Female,18,London
+103,Aditya,Male,22,Mumbai
+104,Leo,Male,22,Chicago
+105,Sam,Male,21,Paris
+106,Tina,Female,23,Sydney
diff --git a/Chapter05/student2.csv b/Chapter05/student2.csv
@@ -0,0 +1,7 @@
+Id,Name,Gender,Age,Address
+101,John,Male,21,New York
+102,Mary,Female,20,London
+103,Aditya,Male,22,Mumbai
+104,Leo,Male,23,Chicago
+105,Sam,Male,21,Paris
+106,Tina,Female,23,Sydney
diff --git a/Chapter05/tarfile_example.py b/Chapter05/tarfile_example.py
@@ -0,0 +1,6 @@
+import tarfile
+
+tar_file = tarfile.open('work.tar.gz', 'w:gz')
+for name in ['welcome.py', 'hello.py', 'hello.txt', 'sample.txt', 'sample1.txt']:
+	tar_file.add(name)
+tar_file.close()
diff --git a/Chapter05/unzip_a_directory.py b/Chapter05/unzip_a_directory.py
@@ -0,0 +1,2 @@
+import shutil
+shutil.unpack_archive('work1.zip')
diff --git a/Chapter05/welcome.py b/Chapter05/welcome.py
@@ -0,0 +1,3 @@
+print("")
+print("Hello World\n")
+print("Hello Python\n")
diff --git a/README.md b/README.md
@@ -17,7 +17,7 @@
 
 [第五章 文件、目录和数据处理](https://alanhou.org/handling-files-directories-data/)：本章你将学习使用os模块来处理各种活动。读者会学习到数据以及应用到数据上的一些方法，如复制、剪切、合并和比较。还将学习tarfile模块及如何及用这一模块。
 
-第六章 文件存档、加密和解密：研究文件存档、创建存档以及TAR和ZIP包的创建。还会学到如何使用应用解压缩.tar和.zip文件。
+[第六章 文件存档、加密和解密](https://alanhou.org/file-archiving-encrypting-decrypting/)：研究文件存档、创建存档以及TAR和ZIP包的创建。还会学到如何使用应用解压缩.tar和.zip文件。
 
 第七章 文本处理和正则表达式：查看Python中的文本处理和正则表达式。Python中有一个很强大的称为正则表达式的库，可进行搜索和提取数据等操作。本章还将学习对文件使用正则表达式，以及如何读取和写入文件。
 

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	`+import shutil`
	`2`	`+shutil.make_archive('work', 'zip', 'work/')`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+import tarfile`
	`2`	`+tar_file = tarfile.open('work.tar.gz', 'r:gz')`
	`3`	`+print(tar_file.getnames())`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+print("")`
	`2`	`+print("Hello World\n")`
	`3`	`+print("Hello Python\n")`
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	`+import shutil`
	`2`	`+shutil.move('/home/vagrant/sample.txt', '/home/vagrant/Desktop/.')`