re.S,使 '.' 匹配换行在内的所有字符
>>> pattern=r'ghostwu.com'
>>> import re
>>> re.findall( pattern, 'ghostwuacom' )
['ghostwuacom']
>>> re.findall( pattern, 'ghostwubcom' )
['ghostwubcom']
>>> re.findall( pattern, 'ghostwu.com' )
['ghostwu.com']
>>> re.findall( pattern, 'ghostwu\ncom' )
[]
>>> re.findall( pattern, 'ghostwu\ncom', re.S )
['ghostwu\ncom']
>>>
re.M,多行匹配,主要影响( ^和$ )
>>> str="""
... hi,ghostwu,how are you
... ghostwu: my name is ghostwu,how are you
... ghostwu: nice to meet you
... hello ghostwu
... """
>>> pattern = r"^ghostwu"
>>> re.findall( pattern, str )
[]
>>> re.findall( pattern, str, re.M )
['ghostwu', 'ghostwu']
>>>
当正则有多行的时候,可以开启verbose模式re.X
>>> pattern=r"""
... \d{3,4}
... -?
... \d{8}
... """
>>> str="020-88888888"
>>> re.findall( pattern, str )
[]
>>> re.findall( pattern, str, re.X )
['020-88888888']
>>>
():分组与| 的使用, 假如我们要匹配一个.com,.cn,.net结尾的email
>>> pattern=r"\w @\w (.com|.cn|.net)"
>>> email="abc@qq.com">>> re.match( pattern, email )
<_sre.SRE_Match object at 0x7f2b74481828>
>>> re.match( pattern, 'abc@qq.cn' )
<_sre.SRE_Match object at 0x7f2b744818a0>
>>> re.match( pattern, 'abc@qq.net' )
<_sre.SRE_Match object at 0x7f2b74481828>
>>> re.match( pattern, 'abc@qq.io' )
>>>
匹配超链接
>>> html="""
... <a href="http://www.baidu.com">百度</a>
... <a href="index.html">首页</a>
... <p>这是一段说明</p>
... <a href="http://www.taobao.com">淘宝</a>
... """
>>> re=r"href=\"(. ?)\""
>>> pattern=r"href=\"(. ?)\""
>>> re
'href=\\"(. ?)\\"'
>>> import re
>>> re.findall( pattern, html )
['http://www.baidu.com', 'index.html', 'http://www.taobao.com']
>>>