day18——re正则表达式

day18

re模块——正则表达式

匹配方法

• findall()：从字符串中全部查找内容，返回一个列表

s = "meet_宝元_meet"
print(re.findall("meet",s))
# ['meet', 'meet']

• w：查找数字、字母（中文）、下划线
• W:查找非数字、字母（中文）、下划线

s = "meet_宝元_meet123"
print(re.findall("w",s))
print(re.findall("W",s))
# ['m', 'e', 'e', 't', '_', '宝', '元', '_', 'm', 'e', 'e', 't', '1', '2', '3']
# []

• s：查找任意空格、换行符、制表符
• S：查找非任意空格、换行符、制表符

s = "meet_ 宝元_ meet123    "
print(re.findall("s",s))
print(re.findall("S",s))
# [' ', ' ', ' ', ' ', ' ', ' ']
# ['m', 'e', 'e', 't', '_', '宝', '元', '_', 'm', 'e', 'e', 't', '1', '2', '3']

• d：查找数字
• D：查找非数字

s = "meet_ 宝元_ 123    "
print(re.findall("d",s))
print(re.findall("D",s))
# ['1', '2', '3']
# ['m', 'e', 'e', 't', '_', ' ', '宝', '元', '_', ' ', ' ', ' ', ' ', ' ']

• A或^：查找是否以什么开头

s = "meet_ 宝元_ 123    "
print(re.findall("Ameet",s))
print(re.findall("^meet",s))
# ['meet']
# ['meet']

• 或$：查找是否以什么结尾

s = "meet_ 宝元_ 123    tt"
print(re.findall("t",s))
print(re.findall("tt$",s))
# ['t']
# ['tt']

• ：查找换行符

s = "meet宝元_123meet 
 	 
"
print(re.findall("
",s))
# ['
', '
']

• ：查找制表符

s = "meet宝元_123meet 
 	 
"
print(re.findall("	", s))
# ['	']

• . ：只能匹配任意一个内容（非换行符）

s = "m
et宝元_123maet 
 	 "
print(re.findall("m.e", s))
print(re.findall("m.e", s,re.DOTALL))
# ['mae']
# ['m
e', 'mae']

• []：匹配字符组中的字符

s = "meet宝元_1A-23maet"
print(re.findall("[a-z]", s))  # 小写的a-z
print(re.findall("[A-Z]", s))  # 大写的A-Z
print(re.findall("[a-zA-Z]", s))  # 大小写的20字母
print(re.findall("[a-zA-Z0-9]", s))  # 大小写的20字母,0-9
print(re.findall("[^0-9]", s))  # 查找非0-9的内容
# ['m', 'e', 'e', 't', 'm', 'a', 'e', 't']
# ['A']
# ['m', 'e', 'e', 't', 'A', 'm', 'a', 'e', 't']
# ['m', 'e', 'e', 't', '1', 'A', '2', '3', 'm', 'a', 'e', 't']
# ['m', 'e', 'e', 't', '宝', '元', '_', 'A', '-', 'm', 'a', 'e', 't']

• *：匹配0个或者多个 [贪婪匹配]

s = "m mm mmmmmm"
print(re.findall("m*", s))
print(re.findall("m*m", s))
# ['m', '', 'mm', '', 'mmmmmm', '']
# ['m', 'mm', 'mmmmmm']

• +:匹配1个或多个 [贪婪匹配]

s = "m mm mmmmmm"
print(re.findall("m+", s))
print(re.findall("m+m", s))
# ['m', 'mm', 'mmmmmm']
# ['mm', 'mmmmmm']

• ?:匹配0个或1个 [非贪婪匹配]

s = "m mm mmmmmm"
print(re.findall("m?",s))
# ['m', '', 'm', 'm', '', 'm', 'm', 'm', 'm', 'm', 'm', '']

• 内容{n}：查找内容重复n次的

s = "m mm mmm mmmm mmmmm mmmmmm"
print(re.findall("m{2}", s))
print(re.findall("m{4}", s))
print(re.findall("m{6}", s))
# ['mm', 'mm', 'mm', 'mm', 'mm', 'mm', 'mm', 'mm', 'mm']
# ['mmmm', 'mmmm', 'mmmm']
# ['mmmmmm']

• 内容{n,m}：查找内容重复n-m次

s = "m mm mmm mmmm mmmmm mmmmmm"
print(re.findall("m{2,5}", s))
# ['mm', 'mmm', 'mmmm', 'mmmmm', 'mmmmm']

• a|b :或

s = "m mm mmss ss s"
print(re.findall("m|s", s))
# ['m', 'm', 'm', 'm', 'm', 's', 's', 's', 's', 's']

• ()：匹配括号内的表达式，也表示一个组

s = "meet_assdf_mssst_(.)mmns_aaamaaatmsssssssssssstt"
print(re.findall("m(..)t", s))
print(re.findall("m(.?)t", s))
print(re.findall("m(..?)t", s))
print(re.findall("m(?:..?)t",s))  # ?:m和t都连上
print(re.findall("m(.*)t", s))
print(re.findall("m(.*?)t", s))
print(re.findall("m(.+)t", s))
print(re.findall("m(.+?)t", s))
# ['ee']
# []
# ['ee']
# ['meet']
# ['eet_assdf_mssst_(.)mmns_aaamaaatmsssssssssssst']
# ['ee', 'sss', 'mns_aaamaaa', 'ssssssssssss']
# ['eet_assdf_mssst_(.)mmns_aaamaaatmsssssssssssst']
# ['ee', 'sss', 'mns_aaamaaa', 'ssssssssssss']

print(re.search("(?P<tag_name>w+)w+w+","h1hellh1").group())
print(re.search("(?P<aaa>w+)dfa","asbsadfasdfa").group("aaa"))
print(re.search("(?P<cx>w+)dfa","asbsadfasdfa").group())
# h1hellh1
# asbsadfas   # ?P：命名
# asbsadfasdfa

s = 'alex_sb ale123_sb wu12sir_sb wusir_sb ritian_sb 的 alex wusir '
print(re.findall("w+_sb",s))
print(re.findall("[a-z]+_sb",s))
# ['alex_sb', 'ale123_sb', 'wu12sir_sb', 'wusir_sb', 'ritian_sb']
# ['alex_sb', 'sir_sb', 'wusir_sb', 'ritian_sb']

方法

• search()：找到一个后就停止查找，从字符串中进行查找，找到后返回的是一个对象，查看元素(group())

s = '_sb alex 123_sb wu12sir_sb wusir_sb ritian_sb 的 x wusir '
print(re.search("ale",s)) # 如果不存在返回None
print(re.search("ale",s).group()) # 如果不存在报错
# <re.Match object; span=(4, 7), match='ale'>
# ale

• match()：找到一个后就停止查找，只从字符串的开头查找，找到后返回一个对象，查看元素(group())

s = 'ale_sb alex 123_sb wu12sir_sb wusir_sb ritian_sb 的 x wusir '
print(re.match("ale",s))  # 开头找不到就返回None
print(re.match("ale",s).group()) # 开头找不到就报错
# <re.Match object; span=(0, 3), match='ale'>
# ale

• split()：分割

s = '_sb alex,123:sb;wu12sir#sb*wusir!sb ritian_sb 的 x wusir '
print(re.split("[#,:!*]",s))
# ['_sb alex', '123', 'sb;wu12sir', 'sb', 'wusir', 'sb ritian_sb 的 x wusir ']

• sub（）：替换

print(re.sub("barry","宝元",'barry是最好的讲师，barry就是一个普通老师，请不要将barry当男神对待。'))
# 宝元是最好的讲师，宝元就是一个普通老师，请不要将宝元当男神对待。

• compile()：定义匹配规则

obj = re.compile("w")
print(obj.findall("meet_宝元_阿萨大大"))
print(re.findall("w","meet_宝元_阿萨大大"))
# ['m', 'e', 'e', 't', '_', '宝', '元', '_', '阿', '萨', '大', '大']
# ['m', 'e', 'e', 't', '_', '宝', '元', '_', '阿', '萨', '大', '大']

• finditer()：返回一个迭代器的地址

g = re.finditer("w","大大撒旦")
# print(next(g).group())
for i in g:
    print(i.group())
# 大
# 大
# 撒
# 旦

练习

1、取整数
s = "1-2*(60+(-40.35/5)-(-4*3))"
print(re.findall("d+",s))
# ['1', '2', '60', '40', '35', '5', '4', '3']

1.2 匹配所有的数字（包含小数）
s = "1-2*(60+(-40.35/5)-(-4*3))"
print(re.findall("d+.d+|d+",s))
# ['1', '2', '60', '40.35', '5', '4', '3']

匹配所有的数字（包含小数包含负号）
s = "1-2*(60+(-40.35/5)-(-4*3))"
print(re.findall("-?d+.d+|-?d+",s))
# ['1', '-2', '60', '-40.35', '5', '-4', '3']

2,匹配一段你文本中的每行的邮箱
http://blog.csdn.net/make164492212/article/details/51656638 匹配所有邮箱
s = "http://blog.csdn.net/make164492212/article/details/51656638 匹配所有邮箱"
print(re.findall("h(?:.+)ls/", s))
# ['http://blog.csdn.net/make164492212/article/details/']

3，匹配一段你文本中的每行的时间字符串 这样的形式：'1995-04-27'
s1 = '''
时间就是1995-04-27,2005-04-27
1999-04-27 老男孩教育创始人
老男孩老师 alex 1980-04-27:1980-04-27
2018-12-08
'''
print(re.findall("d+-d+-d+",s1))
# ['1995-04-27', '2005-04-27', '1999-04-27', '1980-04-27', '1980-04-27', '2018-12-08']

4、匹配qq号：腾讯从10000开始：
num = input("请输入你的数字：")
print(re.findall("[1-9][0-9]{5,10}",num))
# 请输入你的数字：1719932187171993218
# ['1719932187', '171993218']

s1 = '''
<div id="cnblogs_post_body" class="blogpost-body"><h3><span style="font-family: 楷体;">python基础篇</span></h3>
<p><span style="font-family: 楷体;">&nbsp; &nbsp;<strong><a href="http://www.cnblogs.com/guobaoyuan/p/6847032.html" target="_blank">python 基础知识</a></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/p/6627631.html" target="_blank">python 初始python</a></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<strong><a href="http://www.cnblogs.com/guobaoyuan/articles/7087609.html" target="_blank">python 字符编码</a></strong></strong></span></p>
<p><span style="font-family: 楷体;"><strong><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/articles/6752157.html" target="_blank">python 类型及变量</a></strong></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/p/6847663.html" target="_blank">python 字符串详解</a></strong></span></p>
<p><span style="font-family: 楷体;">&nbsp; &nbsp;<strong><a href="http://www.cnblogs.com/guobaoyuan/p/6850347.html" target="_blank">python 列表详解</a></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/p/6850496.html" target="_blank">python 数字元祖</a></strong></span></p>
<p><span style="font-family: 楷体;">&nbsp; &nbsp;<strong><a href="http://www.cnblogs.com/guobaoyuan/p/6851820.html" target="_blank">python 字典详解</a></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<strong><a href="http://www.cnblogs.com/guobaoyuan/p/6852131.html" target="_blank">python 集合详解</a></strong></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/articles/7087614.html" target="_blank">python 数据类型</a>&nbsp;</strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/p/6752169.html" target="_blank">python文件操作</a></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/p/8149209.html" target="_blank">python 闭包</a></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/articles/6705714.html" target="_blank">python 函数详解</a></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/articles/7087616.html" target="_blank">python 函数、装饰器、内置函数</a></strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/articles/7087629.html" target="_blank">python 迭代器 生成器</a>&nbsp;&nbsp;</strong></span></p>
<p><span style="font-family: 楷体;"><strong>&nbsp; &nbsp;<a href="http://www.cnblogs.com/guobaoyuan/articles/6757215.html" target="_blank">python匿名函数、内置函数</a></strong></span></p>
</div>
'''
1,找到所有的span标签的内容
ret = re.findall('<span(.*?)>', s1)
print(ret)

print(re.findall('<a href="(.*?)"',s1))