Python之re库

本篇仅作为代码记录

#!/usr/bin/python
# -*- coding: UTF-8 -*-    
# Author: RuiMing Lin
# DateTime: 2021/01/24 22:12
# Description: 正则表达式
import re

# match()从第一个字符开始匹配  如果没有符合规则的就是返回none
flag = False
# flag = True
if flag:
    content = 'Hello 123 4567 World_This is a Regex Demo'
    print(len(content))
    result = re.match('^Hello\s\d\d\d\s\d{4}\s\w{10}', content)
    print(result)
    print(result.group())
    print(result.span())

# 匹配目标
flag = False
# flag = True
if flag:
    content = 'Hello 1234567 World_This is a Regex Demo'
    result = re.match('^Hello\s(\d+)\sWorld', content)
    print(result)
    print(result.group())
    print(result.group(1))
    print(result.span())

# 通用匹配
flag = False
# flag = True
if flag:
    content = 'Hello 123 4567 World_This is a Regex Demo'
    result = re.match('^Hello.*Demo$', content)
    print(result)
    print(result.group())
    print(result.span())

# 贪婪模式
flag = False
# flag = True
if flag:
    content = 'Hello 1234567 World_This is a Regex Demo'
    result = re.match('^He.*(\d+).*Demo$', content)
    print(result)
    print(result.group(1))

# 非贪婪模式
flag = False
# flag = True
if flag:
    content = 'Hello 1234567 World_This is a Regex Demo'
    result = re.match('^He.*?(\d+).*Demo$', content)
    print(result)
    print(result.group(1))

# 注意非贪婪匹配的应用场合
flag = False
# flag = True
if flag:
    content = 'http://weibo.com/comment/kEraCN'
    result1 = re.match('http.*?comment/(.*?)', content)
    result2 = re.match('http.*?comment/(.*)', content)
    print('result1', result1.group(1))
    print('result2', result2.group(1))

'''
修饰符
re.I    使匹配对大小写不敏感
re.L    做本地化识别（locale-aware）匹配
re.M    多行匹配，影响 ^ 和 $
re.S    匹配包括换行在内的所有字符
re.U    根据 Unicode 字符集解析字符。这个标志影响 \\w、\\W、 \\b 和 \\B
re.X    该标志通过给予你更灵活的格式以便你将正则表达式写得更易于理解
在网页匹配中，较为常用的有 re.S 和 re.I
'''
flag = False
# flag = True
if flag:
    content = '''Hello 1234567 World_This
    is a Regex Demo
    '''
    result = re.match('^He.*?(\d+).*?Demo', content, re.S)
    print(result.group(1))

# 转义匹配
flag = False
# flag = True
if flag:
    content = '(百度)www.baidu.com'
    result = re.match('\(百度\)www\.baidu\.com', content)
    print(result)

# search()，扫描整个字符串，返回第一个匹配成功的
flag = False
# flag = True
if flag:
    content = 'Extra stings Hello 1234567 World_This is a Regex Demo Extra stings'
    result = re.search('Hello.*?(\d+).*?Demo', content)
    print(result)

html = '''<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>'''

#
flag = False
# flag = True
if flag:
    result = re.search('<li.*?active.*?singer="(.*?)">(.*?)</a>', html, re.S)
    if result:
        print(result.group(1), result.group(2))

# findall()
flag = False
flag = True
if flag:
    results = re.findall('<li.*?href="(.*?)".*?singer="(.*?)">(.*?)</a>', html, re.S)
    print(results)
    print(type(results))
    for result in results:
        print(result[0], result[1], result[2])