下面是一个python程序，使用多处理库将行计数分布到不同的机器/核。使用8核windows 64服务器，我的测试将一个2000万行文件的计数从26秒提高到7秒。注意:不使用内存映射会使运行速度变慢。

import multiprocessing, sys, time, os, mmap
import logging, logging.handlers

def init_logger(pid):
    console_format = 'P{0} %(levelname)s %(message)s'.format(pid)
    logger = logging.getLogger()  # New logger at root level
    logger.setLevel( logging.INFO )
    logger.handlers.append( logging.StreamHandler() )
    logger.handlers[0].setFormatter( logging.Formatter( console_format, '%d/%m/%y %H:%M:%S' ) )

def getFileLineCount( queues, pid, processes, file1 ):
    init_logger(pid)
    logging.info( 'start' )

    physical_file = open(file1, "r")
    #  mmap.mmap(fileno, length[, tagname[, access[, offset]]]

    m1 = mmap.mmap( physical_file.fileno(), 0, access=mmap.ACCESS_READ )

    #work out file size to divide up line counting

    fSize = os.stat(file1).st_size
    chunk = (fSize / processes) + 1

    lines = 0

    #get where I start and stop
    _seedStart = chunk * (pid)
    _seekEnd = chunk * (pid+1)
    seekStart = int(_seedStart)
    seekEnd = int(_seekEnd)

    if seekEnd < int(_seekEnd + 1):
        seekEnd += 1

    if _seedStart < int(seekStart + 1):
        seekStart += 1

    if seekEnd > fSize:
        seekEnd = fSize

    #find where to start
    if pid > 0:
        m1.seek( seekStart )
        #read next line
        l1 = m1.readline()  # need to use readline with memory mapped files
        seekStart = m1.tell()

    #tell previous rank my seek start to make their seek end

    if pid > 0:
        queues[pid-1].put( seekStart )
    if pid < processes-1:
        seekEnd = queues[pid].get()

    m1.seek( seekStart )
    l1 = m1.readline()

    while len(l1) > 0:
        lines += 1
        l1 = m1.readline()
        if m1.tell() > seekEnd or len(l1) == 0:
            break

    logging.info( 'done' )
    # add up the results
    if pid == 0:
        for p in range(1,processes):
            lines += queues[0].get()
        queues[0].put(lines) # the total lines counted
    else:
        queues[0].put(lines)

    m1.close()
    physical_file.close()

if __name__ == '__main__':
    init_logger( 'main' )
    if len(sys.argv) > 1:
        file_name = sys.argv[1]
    else:
        logging.fatal( 'parameters required: file-name [processes]' )
        exit()

    t = time.time()
    processes = multiprocessing.cpu_count()
    if len(sys.argv) > 2:
        processes = int(sys.argv[2])
    queues=[] # a queue for each process
    for pid in range(processes):
        queues.append( multiprocessing.Queue() )
    jobs=[]
    prev_pipe = 0
    for pid in range(processes):
        p = multiprocessing.Process( target = getFileLineCount, args=(queues, pid, processes, file_name,) )
        p.start()
        jobs.append(p)

    jobs[0].join() #wait for counting to finish
    lines = queues[0].get()

    logging.info( 'finished {} Lines:{}'.format( time.time() - t, lines ) )

我不得不在类似的问题上发表这篇文章，直到我的声誉分数上升了一点(感谢那些撞了我的人!)。

所有这些解决方案都忽略了一种使其运行得更快的方法，即使用无缓冲(原始)接口，使用字节数组，并进行自己的缓冲。(这只适用于Python 3。在Python 2中，原始接口在默认情况下可以使用，也可以不使用，但在Python 3中，您将默认使用Unicode。)

使用一个修改版本的计时工具，我相信下面的代码比任何提供的解决方案都更快(并且稍微更python化):

def rawcount(filename):
    f = open(filename, 'rb')
    lines = 0
    buf_size = 1024 * 1024
    read_f = f.raw.read

    buf = read_f(buf_size)
    while buf:
        lines += buf.count(b'\n')
        buf = read_f(buf_size)

    return lines

使用单独的生成器函数，运行速度会快一点:

def _make_gen(reader):
    b = reader(1024 * 1024)
    while b:
        yield b
        b = reader(1024*1024)

def rawgencount(filename):
    f = open(filename, 'rb')
    f_gen = _make_gen(f.raw.read)
    return sum( buf.count(b'\n') for buf in f_gen )

这完全可以用itertools内嵌的生成器表达式来完成，但它看起来非常奇怪:

from itertools import (takewhile,repeat)

def rawincount(filename):
    f = open(filename, 'rb')
    bufgen = takewhile(lambda x: x, (f.raw.read(1024*1024) for _ in repeat(None)))
    return sum( buf.count(b'\n') for buf in bufgen )

以下是我的时间安排:

function      average, s  min, s   ratio
rawincount        0.0043  0.0041   1.00
rawgencount       0.0044  0.0042   1.01
rawcount          0.0048  0.0045   1.09
bufcount          0.008   0.0068   1.64
wccount           0.01    0.0097   2.35
itercount         0.014   0.014    3.41
opcount           0.02    0.02     4.83
kylecount         0.021   0.021    5.05
simplecount       0.022   0.022    5.25
mapcount          0.037   0.031    7.46

一行，可能很快:

num_lines = sum(1 for line in open('myfile.txt'))

如果你的文件中的所有行都是相同的长度(并且只包含ASCII字符)*，你可以非常便宜地执行以下操作:

fileSize     = os.path.getsize( pathToFile )  # file size in bytes
bytesPerLine = someInteger                    # don't forget to account for the newline character
numLines     = fileSize // bytesPerLine

*如果使用像é这样的unicode字符，我怀疑需要更多的努力来确定一行中的字节数。

简单的方法:

1)

>>> f = len(open("myfile.txt").readlines())
>>> f

430

>>> f = open("myfile.txt").read().count('\n')
>>> f
430
>>>

num_lines = len(list(open('myfile.txt')))

我相信内存映射文件将是最快的解决方案。我尝试了四个函数:由OP发布的函数(opcount);对文件中的行进行简单迭代(simplecount);带有内存映射字段(mmap)的Readline (mapcount);以及Mykola Kharechko (buffcount)提供的缓冲区读取解决方案。

我将每个函数运行五次，并计算出120万在线文本文件的平均运行时间。

Windows XP, Python 2.5, 2GB RAM, 2ghz AMD处理器

以下是我的结果:

mapcount : 0.465599966049
simplecount : 0.756399965286
bufcount : 0.546800041199
opcount : 0.718600034714

编辑:Python 2.6的数字:

mapcount : 0.471799945831
simplecount : 0.634400033951
bufcount : 0.468800067902
opcount : 0.602999973297

因此，对于Windows/Python 2.6，缓冲区读取策略似乎是最快的

代码如下:

from __future__ import with_statement
import time
import mmap
import random
from collections import defaultdict

def mapcount(filename):
    f = open(filename, "r+")
    buf = mmap.mmap(f.fileno(), 0)
    lines = 0
    readline = buf.readline
    while readline():
        lines += 1
    return lines

def simplecount(filename):
    lines = 0
    for line in open(filename):
        lines += 1
    return lines

def bufcount(filename):
    f = open(filename)                  
    lines = 0
    buf_size = 1024 * 1024
    read_f = f.read # loop optimization

    buf = read_f(buf_size)
    while buf:
        lines += buf.count('\n')
        buf = read_f(buf_size)

    return lines

def opcount(fname):
    with open(fname) as f:
        for i, l in enumerate(f):
            pass
    return i + 1


counts = defaultdict(list)

for i in range(5):
    for func in [mapcount, simplecount, bufcount, opcount]:
        start_time = time.time()
        assert func("big_file.txt") == 1209138
        counts[func].append(time.time() - start_time)

for key, vals in counts.items():
    print key.__name__, ":", sum(vals) / float(len(vals))