python 正则

match()

import re
pattern = re.compile(r'\d+')
m = pattern.match('12one')
print m
print m.group()
print m.start()
print m.end()
print m.span()

import re
pattern = re.compile(r'([a-z]+) ([a-z]+)', re.I)
m = pattern.match('hello world wide web')
print m.group()
print m.group(1)
print m.group(2)
print m.groups()

search()

import re
pattern = re.compile(r'\d+')
m = pattern.search('one12')
print m.group()

import re
pattern = re.compile(r'\d+')
m = pattern.search('hello 123 456')
if m:
    print 'matching string:', m.group()
    print 'position:', m.span()

findall()

import re
pattern = re.compile(r'\d+')
result1 = pattern.findall('hello 123 456')
result2 = pattern.findall('one12two34')
print result1
print result2

import re
pattern = re.compile(r'\d+\.\d+')
result = pattern.findall("123.141593, 'bigcat', 232312, 3.15, 3.")
for item in result:
    print item

finditer()

import re
pattern = re.compile(r'\d+')
result_iter1 = pattern.finditer('hello 123456 789')
result_iter2 = pattern.finditer('one1two2three3four4', 0, 10)
print type(result_iter1)
print type(result_iter2)
for m1 in result_iter1:
    print m1.group(), m1.span()
for m2 in result_iter2:
    print m2.group(), m2.span()

split()

import re
p = re.compile(r'[\s\,\;]+')
print p.split('a,b;; c   d')

sub()

#coding:utf-8
import re
p = re.compile(r'(\w+) (\w+)')
s = 'hello 123, hello 456'
print p.sub(r'hello world', s)
print p.sub(r'\2 \1', s)
print p.sub(lambda m:'h1' + ' ' + m.group(2), s)
print p.sub(lambda m:'h1' + ' ' + m.group(2), s, 1)

匹配中文

#coding:utf-8
import re

title = u'你好，hello，世界'
pattern = re.compile(ur'[\u4e00-\u9fa5]+')
result = pattern.findall(title)

print result

非贪婪

import re
line = "boooooobbby123"
regex_str = ".*?(b.*?b).*"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj)
    print(match_obj.group(1))