简单的做法：
需要在python中获取大文件（数十万行）的行数。
def file_len(fname):
with open(fname) as f:
for i, l in enumerate(f):
pass return i + 1
有效的方法（缓冲区读取策略）：
首先看下运行的结果：
ViaooChain 维奥连锁招商网站系统
下载
网站功能资讯模块资料模块会员模块产品展示模块产品订购模块购物车模块留言模块在线加盟模块多级后台管理系统网站环境本系统为 asp.net开发donet版本为1.1框架数据库为acdess2000授权方式为免费，本版本本地可直接运行（使用http://localhost或http://127.0.0.1访问）如需放到外网通过域名访问，则需通过qq联系我免费索取钥匙文件，将钥匙文件放到网站空间根目录即可
mapcount : 0.471799945831 simplecount : 0.634400033951 bufcount : 0.468800067902 opcount : 0.602999973297
因此，对于Windows/Python2.6来说，缓冲区读取策略似乎是最快的。
以下是代码：
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)) 
