按文本文件行的头、尾和向后读取

Question

如何在Python中实现诸如“head”和“tail”命令以及按文本文件的行向后读取之类的命令？

Answer 1

这是我的个人文件类；-)

class File(file):
    """ An helper class for file reading  """

    def __init__(self, *args, **kwargs):
        super(File, self).__init__(*args, **kwargs)
        self.BLOCKSIZE = 4096

    def head(self, lines_2find=1):
        self.seek(0)                            #Rewind file
        return [super(File, self).next() for x in xrange(lines_2find)]

    def tail(self, lines_2find=1):  
        self.seek(0, 2)                         #Go to end of file
        bytes_in_file = self.tell()
        lines_found, total_bytes_scanned = 0, 0
        while (lines_2find + 1 > lines_found and
               bytes_in_file > total_bytes_scanned): 
            byte_block = min(
                self.BLOCKSIZE,
                bytes_in_file - total_bytes_scanned)
            self.seek( -(byte_block + total_bytes_scanned), 2)
            total_bytes_scanned += byte_block
            lines_found += self.read(self.BLOCKSIZE).count('\n')
        self.seek(-total_bytes_scanned, 2)
        line_list = list(self.readlines())
        return line_list[-lines_2find:]

    def backward(self):
        self.seek(0, 2)                         #Go to end of file
        blocksize = self.BLOCKSIZE
        last_row = ''
        while self.tell() != 0:
            try:
                self.seek(-blocksize, 1)
            except IOError:
                blocksize = self.tell()
                self.seek(-blocksize, 1)
            block = self.read(blocksize)
            self.seek(-blocksize, 1)
            rows = block.split('\n')
            rows[-1] = rows[-1] + last_row
            while rows:
                last_row = rows.pop(-1)
                if rows and last_row:
                    yield last_row
        yield last_row

用法示例：

with File('file.name') as f:
    print f.head(5)
    print f.tail(5)
    for row in f.backward():
        print row

Answer 2

head 很简单：

from itertools import islice
with open("file") as f:
    for line in islice(f, n):
        print line

如果您不想将整个文件保留在内存中，tail 就更难了。如果输入是文件，您可以从文件末尾开始读取块。如果输入是管道，原始的 tail 也可以工作，因此更通用的解决方案是读取并丢弃整个输入，除了最后几行。一个简单的方法是使用collections.deque：

from collections import deque
with open("file") as f:
    for line in deque(f, maxlen=n):
        print line

在这两个代码片段中，n 是要打印的行数。

Answer 3

尾巴：

def tail(fname, lines):
    """Read last N lines from file fname."""
    f = open(fname, 'r')
    BUFSIZ = 1024
    f.seek(0, os.SEEK_END)
    fsize = f.tell()
    block = -1
    data = ""
    exit = False
    while not exit:
        step = (block * BUFSIZ)
        if abs(step) >= fsize:
            f.seek(0)
            exit = True
        else:
            f.seek(step, os.SEEK_END)
        data = f.read().strip()
        if data.count('\n') >= lines:
            break
        else:
            block -= 1
    return data.splitlines()[-lines:]