Python实现简单文本字符串处理的方法

mySent = 'This book is the best book on python!'
print mySent.split()

['This', 'book', 'is', 'the', 'best', 'book', 'on', 'python!']

import re
reg = re.compile('\\W*')
mySent = 'This book is the best book on python!'
listof = reg.split(mySent)
print listof

['This', 'book', 'is', 'the', 'best', 'book', 'on', 'python', '']

import re
reg = re.compile('\\W*')
mySent = 'This book is the best book on python!'
listof = reg.split(mySent)
new_list = [tok for tok in listof if len(tok)>0]
print new_list

['This', 'book', 'is', 'the', 'best', 'book', 'on', 'python']

import re
reg = re.compile('\\W*')
mySent = 'This book is the best book on python!'
listof = reg.split(mySent)
new_list = [tok.lower() for tok in listof if len(tok)>0]
print new_list

['this', 'book', 'is', 'the', 'best', 'book', 'on', 'python']

Hi Peter,

With Jose out of town, do you want to
meet once in a while to keep things
going and do some interesting stuff?

Let me know
Eugene

import re
reg = re.compile('\\W*')
email = open('email.txt').read()
list = reg.split(email)
new_txt = [tok.lower() for tok in list if len(tok)>0]
print new_txt