Python开发【第三篇】：Python基本之文件操作
Python基本之文本操作
一、初识文本的基本操作
在python中打开文件有两种方式，即：open(...) 和 file(...) ，本质上前者在内部会调用后者来进行文件操作，推荐使用 open。
操作文件时，一般需要经历如下步骤：
- 打开文件
- 操作文件
1、open形式
一、打开文件
文件句柄 = open('文件路径', '模式')
打开文件时，需要指定文件路径和以何等方式打开文件，打开后，即可获取该文件句柄，日后通过此文件句柄对该文件操作。
打开文件的模式有：
- r ，只读模式【默认】
- w，只写模式【不可读；不存在则创建；存在则清空内容；】
- x， 只写模式【不可读；不存在则创建并写内容，存在则报错】
- a， 追加模式【可读； 不存在则创建；存在则只追加内容；】
"+" 表示可以同时读写某个文件
- r+， 读写【可读，可写】
- w+，写读【可读，可写】
- x+ ，写读【可读，可写】
- a+， 写读【可读，可写】
指针(位置)
位置：默认在开头，如果对它进行读(遍历全文件，到达最后)，再写的话就是在最后写。
调整：
问题：你用data=f.read(1)去读时，指针到达这个位置，但想写时它还是会在最后写。
解决：
f.seek()：定位到打开文件的位置。
字节：由每8位组成1个字节
字符：多个字节形成字符。
按打开的形式来决定：
1、以字节的方式打开来定位;
2、以字符的方式来定位;
可以主动把指针调到想要的位置，并用需要插入的内容去覆盖。
f.tell()：获取当前指针的位置。
f=open("db",'r+',encoding="utf-8") #如果打开无b，则read，按照字符读取 data=f.read(1) #tell当前指针所在的位置（字节） print(f.tell()) #调整当前，指向你的位置(字节) f.seek(f.tell()) #当前指针位置开始向后覆盖 f.write("777") data_write=f.read() print(data_write) f.close
"b"表示以字节的方式操作
- rb 或 r+b
- wb 或 w+b
- xb 或 w+b
- ab 或 a+b
注：以b方式打开时，读取到的内容是字节类型，写入时也需要提供字节类型
#两种方式： 1、python自己帮你转换成字符串处理。 f=open('db','r',encoding="utf-8") data=f.read() print(data,type(data)) f.close 2、自己处理二进制数据 f=open('db','ab') data=f.write(bytes("你好",encoding="utf8")) print(data) f.close
二、操作
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
class TextIOWrapper(_TextIOBase): """ Character and line based layer over a BufferedIOBase object, buffer. encoding gives the name of the encoding that the stream will be decoded or encoded with. It defaults to locale.getpreferredencoding(False). errors determines the strictness of encoding and decoding (see help(codecs.Codec) or the documentation for codecs.register) and defaults to "strict". newline controls how line endings are handled. It can be None, '', '\n', '\r', and '\r\n'. It works as follows: * On input, if newline is None, universal newlines mode is enabled. Lines in the input can end in '\n', '\r', or '\r\n', and these are translated into '\n' before being returned to the caller. If it is '', universal newline mode is enabled, but line endings are returned to the caller untranslated. If it has any of the other legal values, input lines are only terminated by the given string, and the line ending is returned to the caller untranslated. * On output, if newline is None, any '\n' characters written are translated to the system default line separator, os.linesep. If newline is '' or '\n', no translation takes place. If newline is any of the other legal values, any '\n' characters written are translated to the given string. If line_buffering is True, a call to flush is implied when a call to write contains a newline character. """ def close(self, *args, **kwargs): # real signature unknown 关闭文件 pass def fileno(self, *args, **kwargs): # real signature unknown 文件描述符 pass def flush(self, *args, **kwargs): # real signature unknown 刷新文件内部缓冲区 pass def isatty(self, *args, **kwargs): # real signature unknown 判断文件是否是同意tty设备 pass def read(self, *args, **kwargs): # real signature unknown 读取指定字节数据 pass def readable(self, *args, **kwargs): # real signature unknown 是否可读 pass def readline(self, *args, **kwargs): # real signature unknown 仅读取一行数据 pass def seek(self, *args, **kwargs): # real signature unknown 指定文件中指针位置 pass def seekable(self, *args, **kwargs): # real signature unknown 指针是否可操作 pass def tell(self, *args, **kwargs): # real signature unknown 获取指针位置 pass def truncate(self, *args, **kwargs): # real signature unknown 截断数据，仅保留指定之前数据 pass def writable(self, *args, **kwargs): # real signature unknown 是否可写 pass def write(self, *args, **kwargs): # real signature unknown 写内容 pass def __getstate__(self, *args, **kwargs): # real signature unknown pass def __init__(self, *args, **kwargs): # real signature unknown pass @staticmethod # known case of __new__ def __new__(*args, **kwargs): # real signature unknown """ Create and return a new object. See help(type) for accurate signature. """ pass def __next__(self, *args, **kwargs): # real signature unknown """ Implement next(self). """ pass def __repr__(self, *args, **kwargs): # real signature unknown """ Return repr(self). """ pass buffer = property(lambda self: object(), lambda self, v: None, lambda self: None) # default closed = property(lambda self: object(), lambda self, v: None, lambda self: None) # default encoding = property(lambda self: object(), lambda self, v: None, lambda self: None) # default errors = property(lambda self: object(), lambda self, v: None, lambda self: None) # default line_buffering = property(lambda self: object(), lambda self, v: None, lambda self: None) # default name = property(lambda self: object(), lambda self, v: None, lambda self: None) # default newlines = property(lambda self: object(), lambda self, v: None, lambda self: None) # default _CHUNK_SIZE = property(lambda self: object(), lambda self, v: None, lambda self: None) # default _finalizing = property(lambda self: object(), lambda self, v: None, lambda self: None) # default
三、关闭文件
1、f.close()
手动写上，运行到此处时关闭
2、通过with自动关闭
with open('xb') as f:
pass
2、file形式
一、打开文件：
file_obj = file("文件路径","模式")
打开文件的模式有：
- r，以只读方式打开文件
- w，打开一个文件只用于写入。如果该文件已存在则将其覆盖。如果该文件不存在，创建新文件。
- a，打开一个文件用于追加。如果该文件已存在，文件指针将会放在文件的结尾。也就是说，新的内容将会被写入到已有内容之后。如果该文件不存在，创建新文件进行写入。
- w+，打开一个文件用于读写。如果该文件已存在则将其覆盖。如果该文件不存在，创建新文件。
"+" 表示可以同时读写某个文件
- r+，可读写文件。【可读；可写；可追加】
- w+，写读
- a+，同a
"U"表示在读取时，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"表示处理二进制文件（如：FTP发送上传ISO镜像文件，linux可忽略，windows处理二进制文件时需标注）
- rb
- wb
- ab
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 0 (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
二、WITH管理上下文
为了避免打开文件后忘记关闭，可以通过管理上下文，即：
with open('log','r') as f: pass
如此方式，当with代码块执行完毕时，内部会自动关闭并释放文件资源。
在Python 2.7 之后，with又支持同时对多个文件的上下文进行管理，即：
with open('log1') as obj1, open('log2') as obj2: pass
with open('db1'，'r',encoding="utf-8") as f1, open('db2','w',enconding="utf-8") as f2: times=0 for line in f1: times+=1 print(line) if times <=10 f2.write(line) else break
#修改文件中的数据，修改一行写一行。 with open('db1'，'r',encoding="utf-8") as f1, open('db2','w',enconding="utf-8") as f2: for line in f1: new_str=line.replace("hello",'st') f2.write(line)
三、常见操作
读取文件的内容：
# 一次性加载所有内容到内存 obj.read()
有参数： b按字节
无b按字符 # 一次性加载所有内容到内存，并根据行分割成字符串 obj.readlines() # 每次仅读取一行数据 for line in obj: print line
for循环文件对象的每一行
for line in f pirnt(line)
获取当前指针位置(字节)
obj.tell()
跳转到指定位置(字节)
obj.seek(1)
写文件的内容：
obj.write('内容')
#有b写字节，无b写字符。
仅读取一行
f.open("db",'r') f.readline() #读取第一行 f.readline() #读取第二行
截断数据
f.open("db",'r+',encoding="utf-8") f.seek(3) f.truncate() #从指针位置开始向后的所有截断 f.close
关闭文件句柄：
obj.close()
文件描述符：fileno
强制刷新到硬盘
#在等待用户输入时，强制输入到硬盘。
f=open("db",'a',encoding="utf-8") f.write("123") f.flush() input("输入：")
是否可读
f.open("db","w") f.readable()
