python遍历字符_在Python中一次遍历字符串单词

逐字逐句地遍历文件内容(在我的例子中，是来自古腾堡项目的Oz向导)，有三种不同的方式：from __future__ import with_statement

import time

import re

from cStringIO import StringIO

def word_iter_std(filename):

start = time.time()

with open(filename) as f:

for line in f:

for word in line.split():

yield word

print 'iter_std took %0.6f seconds' % (time.time() - start)

def word_iter_re(filename):

start = time.time()

with open(filename) as f:

txt = f.read()

for word in re.finditer('\w+', txt):

yield word

print 'iter_re took %0.6f seconds' % (time.time() - start)

def word_iter_stringio(filename):

start = time.time()

with open(filename) as f:

io = StringIO(f.read())

for line in io:

for word in line.split():

yield word

print 'iter_io took %0.6f seconds' % (time.time() - start)

woo = '/tmp/woo.txt'

for word in word_iter_std(woo): pass

for word in word_iter_re(woo): pass

for word in word_iter_stringio(woo): pass

导致：% python /tmp/junk.py

iter_std took 0.016321 seconds

iter_re took 0.028345 seconds

iter_io took 0.016230 seconds