180 lines
5.3 KiB
Python
180 lines
5.3 KiB
Python
# -*- encoding:utf-8 -*-
|
||
|
||
'''
|
||
@Author : dingjiawen
|
||
@Date : 2023/11/7 17:31
|
||
@Usage :
|
||
@Desc : 正则匹配re库基本使用
|
||
'''
|
||
|
||
import re
|
||
|
||
'''
|
||
基本使用
|
||
'''
|
||
|
||
|
||
def baseUse():
|
||
content = 'hello 123456789 World_This is a Reges Demo'
|
||
pattern = '^hello\s(\d+)\sWorld'
|
||
result = re.match(pattern, content)
|
||
|
||
print(result) # <re.Match object; span=(0, 21), match='hello 123456789 World'>
|
||
print(result.group()) # hello 123456789 World 输出匹配到的内容
|
||
print(result.group(1)) # 123456789 输出第一个被()包围的匹配结果
|
||
print(result.span()) # (0, 21) 输出匹配的范围
|
||
|
||
|
||
# 高级用法
|
||
'''
|
||
贪婪匹配与非贪婪匹配
|
||
.*表示尽可能多匹配字符
|
||
.*?表示尽可能少匹配字符
|
||
'''
|
||
|
||
'''
|
||
re.I 表示匹配对大小写不明感
|
||
re.L 实现本地化识别匹配
|
||
re.M 表示多航匹配，影响^和$
|
||
re.S 表示匹配内容包括换行符在内的所有字符
|
||
re.U 表示根据Unicode解析字符，这个表示会影响\w,\W,\b和\B
|
||
re.S 表示匹配内容包括换行符在内的所有字符
|
||
'''
|
||
def prior():
|
||
content = '''hello 123456789 World_This
|
||
is a Reges Demo
|
||
'''
|
||
result = re.match('^he.*?(\d+).*?Demo$', content)
|
||
print(result.group(1)) # 未匹配到，报错 AttributeError: 'NoneType' object has no attribute 'group'
|
||
result = re.match('^he.*?(\d+).*?Demo$', content, re.S)
|
||
print(result.group(1)) # 123456789
|
||
|
||
|
||
'''
|
||
search:模糊匹配
|
||
'''
|
||
def search():
|
||
content = 'Extra stings Hello 1234567 World_This is a Regex Demo Extra stings'
|
||
result = re.match('Hello.*?(\d+).*?Demo', content) # 必须要以Hello开头才能匹配到
|
||
print(result) # None
|
||
result = re.search('Hello.*?(\d+).*?Demo', content)
|
||
print(result) # <re.Match object; span=(13, 53), match='Hello 1234567 World_This is a Regex Demo'>
|
||
|
||
|
||
def searchHtml():
|
||
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">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))
|
||
|
||
result = re.search('<li.*?singer="(.*?)">(.*?)</a>', html, re.S)
|
||
if result:
|
||
print(result.group(1), result.group(2))
|
||
|
||
result = re.search('<li.*?singer="(.*?)">(.*?)</a>', html)
|
||
if result:
|
||
print(result.group(1), result.group(2))
|
||
|
||
'''
|
||
findAll:找到所有匹配的
|
||
'''
|
||
def findall():
|
||
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">但愿人长久</a>
|
||
</li>
|
||
</ul>
|
||
</div>'''
|
||
results = re.findall('<li.*?href="(.*?)".*?singer="(.*?)">(.*?)</a>', html, re.S)
|
||
print(results)
|
||
print(type(results))
|
||
for result in results:
|
||
print(result)
|
||
print(result[0], result[1], result[2])
|
||
|
||
results = re.findall('<li.*?>\s*?(<a.*?>)?(\w+)(</a>)?\s*?</li>', html, re.S)
|
||
for result in results:
|
||
print(result[1])
|
||
|
||
|
||
'''
|
||
sub:正则匹配修改文本
|
||
使用正则匹配，去除掉能匹配上的内容
|
||
'''
|
||
def sub():
|
||
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">但愿人长久</a>
|
||
</li>
|
||
</ul>
|
||
</div>'''
|
||
html = re.sub('<a.*?>|</a>', '', html)
|
||
print(html)
|
||
results = re.findall('<li.*?>(.*?)</li>', html, re.S)
|
||
for result in results:
|
||
print(result.strip())
|
||
|
||
'''
|
||
compile:编译
|
||
将相关模式编译成pattern对象，进行复用
|
||
'''
|
||
def complie():
|
||
content1 = '2019-12-15 12:00'
|
||
content2 = '2019-12-17 12:55'
|
||
content3 = '2019-12-22 13:21'
|
||
pattern = re.compile('\d{2}:\d{2}')
|
||
result1 = re.sub(pattern, '', content1)
|
||
result2 = re.sub(pattern, '', content2)
|
||
result3 = re.sub(pattern, '', content3)
|
||
print(result1, result2, result3)
|
||
|
||
if __name__ == '__main__':
|
||
sub()
|