正则表达式概述

一种文本模式，描述在搜索文本时要匹配的一个或多个字符串

典型应用场景

数据验证，文本扫描，文本提取，文本替换，文本分割

语法

字面值(普通字符、需转义)，元字符

匹配规则

正则表达式实例

import re

#匹配数字

text="Tom is 8 years old.Mike is 25 years old"

pattern_num=re.compile('\d+')

result_num=re.findall(pattern_num,text)

print(result_num)



#匹配含需转义的字符串

string="\\author:Tom"

pattern_string=re.compile(r'\\author')

result_string=re.findall(pattern_string,string)

print(result_string)



#匹配首字母大写的字符串

pattern_name=re.compile(r'[A-Z]\w+')

result_name=re.findall(pattern_name,text)

print(result_name)



#match 匹配(从开头匹配）

html='<html><head></head><body></body></html>'

html_position=' <html><head></head><body></body></html>'

pattern_html=re.compile(r'<html>')

result_html=re.match(pattern_html,html)

result_html_position=pattern_html.match(html_position,1)

print(result_html)

print(result_html_position)



#search匹配

result_html_position_search=pattern_html.search(html_position)

print(result_html_position_search)



#group编组

pattern_text_group=re.compile(r'(\d+).*?(\d+)')

result_text_group=re.search(pattern_text_group,text)

print(result_text_group)

print(result_text_group.group())

print(result_text_group.group(0))

print(result_text_group.group(1))

print(result_text_group.group(2))

print(result_text_group.start(1))

print(result_text_group.end(1))

print(result_text_group.groups())

print(re.search(r'(ab)+c','ababc'))

print(re.search(r'cent(er|re)','center'))

print(re.search(r'cent(er|re)','centre'))

print(re.search(r'(\w+) \1','hello hello world'))

text_dict="Tom:98"

pattern_dict=re.compile(r'(\w+):(\d+)')

result_dict=re.search(pattern_dict,text_dict)

print(result_dict.group())

pattern_dict_name=re.compile(r'(?P<name>\w+):(?P<score>\d+)')

result_dict_name=re.search(pattern_dict_name,text_dict)

print(result_dict_name.group('name'))

print(result_dict_name.group('score'))

正则应用
#字符串切割

celebrated_dictum='Beautiful is better than ugly.\nExplicit is better than implicit.\nSimple is better than complex'

celebrated_dictum_pattern=re.compile(r'\n')

result_celebrated_dictum=celebrated_dictum_pattern.split(celebrated_dictum)

print(result_celebrated_dictum)

print(re.split(r'\W','Good morning'))



#字符串替换

ords='ORD000\nORD001\nORD002'

print(re.sub(r'\d+','-',ords))

celebrated_dictum_sub='Beautiful is *better* than ugly.'

print(re.sub(r'\*(.*?)\*','<strong>\g<1></strong>',celebrated_dictum_sub))



#编译标记(re.M 匹配多行，re.S匹配所有字符包括\n)

mark_text='Python python PYTHON'

print(re.search(r'python',mark_text))

print(re.findall(r'python',mark_text,re.I))

posted on 2019-08-28 13:38 *赤子之心* 阅读(233) 评论(0) 收藏举报