#!/usr/bin/env python
# coding: utf-8
# # Table of Contents
#
# # Python 文件操作
#
# Python操作文件时，一般要经历如下步骤
# - 打开文件
# - 操作文件
# ## 打开文件
# In[ ]:
# 文件句柄 = open('文件路径'， ‘模式’)
# Python内置open函数可以打开一个系统中存在的文件，会创建一个文件对象，通过这个文件对象就可以通过底文件进行操作。
#
# 打开文件时，需要指定文件路径和以什么模式打开文件。 打开后获得该文件的句柄，通过问句柄对该文件操作。
# ## 打开文件模式
#
# 打开文件的模式有：
# - r，只读模式（默认）
# - w，只写模式（不可读；路径文件不存在将会创建文件，如果存在会清空里面的内容；注意！）
# - a，追加模式（可读；文件不存在将创建，文件存在则在末尾追加内容。）
#
# “+” 增强模式：
# - r+，可读，可写，可追加
# - w+，写读（文件存在会清空里面内容，注意！）
# - a+，同a
#
# “U” 兼容模式，在读取文件时，可以将\r \n \r\n自动转换成 \n （与 r 或 r+ 模式同使用）：
# - rU
# - r+U
#
# “b” 处理二进制文件，与其他模式可（如图片）：
# - rb
# - wb
# - ab
# ## open 对象
# In[ ]:
class file(object):
def close(self): # real signature unknown; restored from __doc__
关闭文件
"""
close() -> None or (perhaps) an integer. Close the file.
Sets data attribute .closed to True. A closed file cannot be used for
further I/O operations. close() may be called more than once without
error. Some kinds of file objects (for example, opened by popen())
may return an exit status upon closing.
"""
def fileno(self): # real signature unknown; restored from __doc__
文件描述符
"""
fileno() -> integer "file descriptor".
This is needed for lower-level file interfaces, such os.read().
"""
return 0
def flush(self): # real signature unknown; restored from __doc__
刷新文件内部缓冲区
""" flush() -> None. Flush the internal I/O buffer. """
pass
def isatty(self): # real signature unknown; restored from __doc__
判断文件是否是同意tty设备
""" isatty() -> true or false. True if the file is connected to a tty device. """
return False
def next(self): # real signature unknown; restored from __doc__
获取下一行数据，不存在，则报错
""" x.next() -> the next value, or raise StopIteration """
pass
def read(self, size=None): # real signature unknown; restored from __doc__
读取指定字节数据
"""
read([size]) -> read at most size bytes, returned as a string.
If the size argument is negative or omitted, read until EOF is reached.
Notice that when in non-blocking mode, less data than what was requested
may be returned, even if no size parameter was given.
"""
pass
def readinto(self): # real signature unknown; restored from __doc__
读取到缓冲区，不要用，将被遗弃
""" readinto() -> Undocumented. Don't use this; it may go away. """
pass
def readline(self, size=None): # real signature unknown; restored from __doc__
仅读取一行数据
"""
readline([size]) -> next line from the file, as a string.
Retain newline. A non-negative size argument limits the maximum
number of bytes to return (an incomplete line may be returned then).
Return an empty string at EOF.
"""
pass
def readlines(self, size=None): # real signature unknown; restored from __doc__
读取所有数据，并根据换行保存值列表
"""
readlines([size]) -> list of strings, each a line from the file.
Call readline() repeatedly and return a list of the lines so read.
The optional size argument, if given, is an approximate bound on the
total number of bytes in the lines returned.
"""
return []
def seek(self, offset, whence=None): # real signature unknown; restored from __doc__
指定文件中指针位置
"""
seek(offset[, whence]) -> None. Move to new file position.
Argument offset is a byte count. Optional argument whence defaults to
(offset from start of file, offset should be >= 0); other values are 1
(move relative to current position, positive or negative), and 2 (move
relative to end of file, usually negative, although many platforms allow
seeking beyond the end of a file). If the file is opened in text mode,
only offsets returned by tell() are legal. Use of other offsets causes
undefined behavior.
Note that not all file objects are seekable.
"""
pass
def tell(self): # real signature unknown; restored from __doc__
获取当前指针位置
""" tell() -> current file position, an integer (may be a long integer). """
pass
def truncate(self, size=None): # real signature unknown; restored from __doc__
截断数据，仅保留指定之前数据
"""
truncate([size]) -> None. Truncate the file to at most size bytes.
Size defaults to the current file position, as returned by tell().
"""
pass
def write(self, p_str): # real signature unknown; restored from __doc__
写内容
"""
write(str) -> None. Write string str to file.
Note that due to buffering, flush() or close() may be needed before
the file on disk reflects the data written.
"""
pass
def writelines(self, sequence_of_strings): # real signature unknown; restored from __doc__
将一个字符串列表写入文件
"""
writelines(sequence_of_strings) -> None. Write the strings to the file.
Note that newlines are not added. The sequence can be any iterable object
producing strings. This is equivalent to calling write() for each string.
"""
pass
def xreadlines(self): # real signature unknown; restored from __doc__
可用于逐行读取文件，非全部
"""
xreadlines() -> returns self.
For backward compatibility. File objects now include the performance
optimizations previously implemented in the xreadlines module.
"""
pass
# ## 操作文件
# In[1]:
# 创建文件
create_file = open('open.file', 'w')
for i in range(5):
content = str(i) + '\n' # 将数字变成字符串，然后加上换行符
create_file.write(content)
create_file.close() # 关闭文件句柄
# 读取文件内容
read_file = open('open.file', 'r', encoding="utf-8") # 指定编码打开文件
for line in read_file: # open创建的文件对象是可迭代的
print(line)
read_file.close() # 关闭文件句柄，打开文件一定要关闭
# In[2]:
new_read_file = open('open.file', 'r+', encoding='utf-8')
new_read_file.read(1) # 指定读取字节大小。
new_read_file.seek(4) # 移动指针，到第几个字节。
new_read_file.tell() # 获取当前指针位置
new_read_file.read(1)
new_read_file.read(1)
new_read_file.seek(4) # 移动指针，到第几个字节。
new_read_file.tell() # 获取当前指针位置
new_read_file.write('this is new word') # 移动过指针后，写操作会把指针后面的内容覆盖掉，注意！
new_read_file.close()
check_read_file = open('open.file', 'r+', encoding='utf-8')
check_read_file.read()
# open打开文件后总要记得关闭是不是特别麻烦，你可以使用**with**， with会帮你close。**with** 还支持同时打开多个文件。
# In[3]:
# 在原有文件上修改(其实就是将现在的文件递归逐行写到新文件，修改操作在写入前做修改然后再写入。)
with open('open.file', 'r', encoding='utf-8') as old_file, open('newopen.file', 'w', encoding='utf-8') as new_file:
for line in old_file.readlines():
if '0' in line:
line = line.replace('0', '9999')
new_file.write(line)
import os
os.rename('newopen.file', 'open.file') # 新文件覆盖旧文件
with open('open.file', 'r', encoding='utf-8') as check_file:
check_file.read()