2017/6/8-python正则表达式的使用

参考文章https://mp.weixin.qq.com/s?timestamp=1496889018&src=3&ver=1&signature=a6AusC2HYPkwlVHDlfVK2NqAOuHGoLS6540WVCePMdB5e9zRehxx*ieX3iJYr-bietGtNvqBRHqB3FVMPTisWTW8cRYzHlI8-LnSL18q1ciblU3q3bfh-Ix4NNCdFM4LsnVD*Y48bIKEbaBRSdJ3VWZhOfPqJEjk1zOdxBpOe1g=

#match()函数的使用#\w匹配字母数字及下划线# \s匹配任意空白字符，等价于 [\t\n\r\f].# \d匹配任意数字，等价于 [0-9]# [...]用来表示一组字符,单独列出：[amk] 匹配 'a'，'m'或'k'# [^...]不在[]中的字符：[^abc] 匹配除了a,b,c之外的字符。#^匹配字符串的开头#{n}精确匹配n个前面表达式。import recontent='Hello 123 4567 World_This is a Regex Demo'print(len(content))pattern=re.compile(r'^Hello\s\d\d\d\s\d{4}\s\w{10}')result=re.match(pattern,content)print(result)print(result.group())print(result.span())

41<_sre.SRE_Match object; span=(0, 25), match='Hello 123 4567 World_This'>Hello 123 4567 World_This(0, 25)

#匹配目标#group()会输出完整的匹配结果，而group(1)会输出第一个被()包围的匹配结果import recontent='Hello 1234567 World_This is a Regex Demo'pattern=re.compile(r'^Hello\s(\d{7})\s(\w{5})')result=re.match(pattern,content)print(result)print(result.group())print(result.group(1))print(result.group(2))print(result.span())

<_sre.SRE_Match object; span=(0, 19), match='Hello 1234567 World'>Hello 1234567 World1234567World(0, 19)

#通用匹配#.匹配任意字符（除换行符外）#*匹配0次或者多次import recontent='Hello 123 4567 World_This is a Regex Demo'pattern=re.compile(r'^Hello.*Demo$')result=re.match(pattern,content)print(result)print(result.group())print(result.span())

<_sre.SRE_Match object; span=(0, 41), match='Hello 123 4567 World_This is a Regex Demo'>Hello 123 4567 World_This is a Regex Demo(0, 41)

#贪婪匹配与非贪婪匹配#01贪婪匹配import recontent='Hello 1234567 World_This is a Regex Demo'pattern=re.compile(r'^He.*(\d+).*Demo$')result=re.match(pattern,content)print(result)print(result.group())print(result.group(1))

<_sre.SRE_Match object; span=(0, 40), match='Hello 1234567 World_This is a Regex Demo'>Hello 1234567 World_This is a Regex Demo7

#02非贪婪匹配import recontent='Hello 1234567 World_This is a Regex Demo'pattern=re.compile(r'He.*?(\d+).*Demo$')result=re.match(pattern,content)print(result)print(result.group())print(result.group(1))

<_sre.SRE_Match object; span=(0, 40), match='Hello 1234567 World_This is a Regex Demo'>Hello 1234567 World_This is a Regex Demo1234567

#但这里注意，如果匹配的结果在字符串结尾，.*?就有可能匹配不到任何内容了，因为它会匹配尽可能少的字符，例如：import recontent='https://www.baidu.com/search/error.html'result1=re.match(r'^https.*search/(.*)',content)result2=re.match(r'https.*search/(.*?)',content)print(result1.group(1))print(result2.group(1))

error.html

#修饰符#正则表达式可以包含一些可选标志修饰符来控制匹配的模式。修饰符被指定为一个可选的标志。import recontent = '''Hello 1234567 World_Thisis a Regex Demo'''pattern=re.compile(r'^He.*?(\d+).*?Demo$',re.S)result=re.match(pattern,content)print(result.group(1))

1234567

#转义匹配import recontent='(百度)www.baidu.com'pattern=re.compile(r'\(百度\)www\.baidu\.com')result=re.match(pattern,content)print(result.group())

(百度)www.baidu.com

#search()import recontent = 'Extra stings Hello 1234567 World_This is a Regex Demo Extra stings'pattern=re.compile('He.*?(\d+).*Demo')result=re.search(pattern,content)print(result.group())print(result.group(1))

Hello 1234567 World_This is a Regex Demo1234567

import rehtml = '''<div id="songs-list">    <h2 class="title">经典老歌</h2>    <p class="introduction">        经典老歌列表    </p>    <ul id="list" class="list-group">        <li data-view="2">一路上有你</li>        <li data-view="7">            <a href="/2.mp3" singer="任贤齐">沧海一声笑</a>        </li>        <li data-view="4" class="active">            <a href="/3.mp3" singer="齐秦">往事随风</a>        </li>        <li data-view="6"><a href="/4.mp3" singer="beyond">光辉岁月</a></li>        <li data-view="5"><a href="/5.mp3" singer="陈慧琳">记事本</a></li>        <li data-view="5">            <a href="/6.mp3" singer="邓丽君"><i class="fa fa-user"></i>但愿人长久</a>        </li>    </ul></div>'''result=re.search('<li.*?active.*?singer="(.*?)">(.*?)</a>',html,re.S)if result:    print(result.group(1), result.group(2))

齐秦 往事随风

#sub()方法import recontent = '54aK54yr5oiR54ix5L2g'result=re.sub('\d+','',content)print(result)

aKyroiRixLg

log='2017-06-06 15:06:16,148 - root - DEBUG - logger debug message'print(log.split('-'))

['2017', '06', '06 15:06:16,148 ', ' root ', ' DEBUG ', ' logger debug message']