day23正则模块的使用

正则表达式：由一系列特殊字符拼接而成的表达式/规则，该表达式用于从一个大字符串中匹配出符合规则的子字符串
import re

1、\w

print(re.findall('\w\w\w',"h ello 123_ (0"))
h ello 123_ (0
           \w\w\w

2. \W
print(re.findall('\W',"h ello 123_ (0"))

3、\s
print(re.findall('\s',"h e\tll\no 123_ (0"))
print(re.findall('\w\s',"h ello 123_ (0"))

4、\S
print(re.findall('\S',"h e\tll\no 123_ (0"))

5、\d
print(re.findall('\d',"h e\tll\no 123_ (0"))

6、\D
print(re.findall('\D',"h e\tll\no 123_ (0"))

print(re.findall("a\db","a1b a2b a b aab aaaaaaaa1b a2c a22c a 3c"))
a1b a2b a b aab aaaaaaaa1b a2c a22c a 3c
                           a\db

["a1b","a2b","a1b"]

7、\n与\t
msg="""h e\tll\n\no 123_ (0
\t1
    2
3
"""
print(re.findall('\n',msg))
print(re.findall('\t',msg))
print(re.findall(' ',msg))


8、^与$
print(re.findall("^egon","egon asdf 213123 egonafsadfegon"))
egon asdf 213123 egonafsadfegon
^egon

print(re.findall("egon$","egon asdf 213123 egonafsadfegon "))
                                                       egon$


print(re.findall("a\w\w\wc","ab12c3c a213c"))
print(re.findall("^a\w\w\wc$","ab_2c"))

9、.与[]
9.1 .：代表匹配一个字符，该字符可以是任意字符
print(re.findall("a\db","a1b a2b aab aaaaaaab a+b a-b a c"))
print(re.findall("a\wb","a1b a2b aab aaaaaaab a+b a-b a c"))
print(re.findall("a.b","a1b a2b aab aaaaaaab a+b a-b a b a c"))
print(re.findall("a.b","a1b a2b aab aaaaaaab a\tb a-b a\nb a c",re.DOTALL))


9.2 []：代表匹配一个字符，我们可以指定该字符的范围
print(re.findall("a[+-]b", "a1b a2b aab aaaaaaab a+b a-b a c"))
print(re.findall("a[.*/+-]b", "a.b a2b a*b a/b aab aaaaaaab a+b a-b a c"))
print(re.findall("a[a-z]b", "a.b a2b a*b a/b aab aaaaaaab a+b a-b a c")) # -放在[]内的开头或结果
print(re.findall("a[a-zA-Z]b", "a.b a2b a*b a/b aAb aCb aab aaaaaaab a+b a-b a c")) # -放在[]内的开头或结果
print(re.findall("a\db", "a.b a2b a*b a/b aAb aCb aab aaaaaaab a+b a-b a c")) # -放在[]内的开头或结果
print(re.findall("a[0-9]b", "a.b a2b a*b a/b aAb aCb aab aaaaaaab a+b a-b a c")) # -放在[]内的开头或结果

[^...]代表取反
print(re.findall("a[^0-9]b", "a.b a2b a*b a/b aAb aCb aab aaaaaaab a+b a-b a c")) # -放在[]内的开头或结果

9.3 *: 左边那个字符出现0次或者无穷次
print(re.findall("ab*","a ab abb abbbbbbbbbbbb bbbbbbbbb"))
a ab abb abbbbbbbbbbbb bbbbbbbbb
                       ab*

9.4 +: 左边那个字符出现1次或者无穷次
print(re.findall("ab+","a ab abb abbbbbbbbbbbb bbbbbbbbb"))
a ab abb abbbbbbbbbbbb bbbbbbbbb
ab+

9.5 {n,m}: 左边那个字符出现n次到m次
print(re.findall("ab{0,}","a ab abb abbbbbbbbbbbb bbbbbbbbb"))
print(re.findall("ab*","a ab abb abbbbbbbbbbbb bbbbbbbbb"))
print(re.findall("ab{1,}","a ab abb abbbbbbbbbbbb bbbbbbbbb"))
print(re.findall("ab+","a ab abb abbbbbbbbbbbb bbbbbbbbb"))

print(re.findall("ab{2,5}","a ab abb abbb abbbb abbbbbbbb abbbbbbbbbbbb bbbbbbbbb"))

9.6 ?: 左边那个字符出现0次到1次
print(re.findall("ab?","a ab abb abbbbbbbbbbbb bbbbbbbbb"))


9.7 .*: 匹配所有
print(re.findall("a.*b","123 a1231-==-000b123123123123123b"))
123 a1231-==-000b123123123123123b
    a.*b

print(re.findall("a.*?b","123 a1231-==-000b123123123123123b"))


例1：
msg = '<a href="https://pan.baidu.com/s/1skWyTT7" target="_blank"><strong><span style="color: #ff0000;">原理图：https://pan.baidu.com/s/1skWyTT7</span></strong></a><a href="https://www.baidu/com">"点我啊"</a>'
url_pattern = re.compile('href="(.*?)"')
res=url_pattern.findall(msg)
print(res)

res=url_pattern.findall('<a href="www.sina.com.cn"></a>')
print(res)

例2：
print(re.findall("a.*b","a1b a+b a-b a\nb a\tb",re.DOTALL))

10 ():分组
print(re.findall('ab+','ababab123')) #['ab', 'ab', 'ab']
print(re.findall('(ab)+123','ababab123')) #['ab']，匹配到末尾的ab123中的ab
ababab123
(ab)(ab)(ab)(ab)

10.1 取消分组
print(re.findall('(?:ab)+123','ababab123')) #findall的结果不是匹配的全部内容，而是组内的内容,?:可以让结果为匹配的全部内容

11 |：或者
print(re.findall("compan(?:ies|y)","Too many companies have gone bankrupt, and the next one is my company'"))

Too many companies have gone bankrupt, and the next one is my company
                                                              compan(ies|y)

print(re.findall("\d+\.?\d*","as9fdasl333...4444df1111asdf3333dfadf333.44dafadf3.5555asdfsafd.5555"))
as9fdasldf1111asdf3333dfadf333.44dafadf3.5555asdfsafd.5555
                           \d+\.?\d*


\d+\.?\d*
333333.3333333333333333


12. \
print(re.findall('a\\\\c','a\c a1c aac')) #对于正则来说a\\c确实可以匹配到a\c,但是在python解释器读取a\\c时，会发生转义，然后交给re去执行，所以抛出异常
print(re.findall(r'a\\c','a\c a1c aac')) #对于正则来说a\\c确实可以匹配到a\c,但是在python解释器读取a\\c时，会发生转义，然后交给re去执行，所以抛出异常

===========================re模块提供的方法介绍===========================
print(re.findall('e','alex make love') )   #['e', 'e', 'e'],返回所有满足匹配条件的结果,放在列表里
print(re.search('e','alex make love')) #e,只到找到第一个匹配然后返回一个包含匹配信息的对象,该对象可以通过调用group()方法得到匹配的字符串,如果字符串没有匹配，则返回None。


print(re.search("\d+\.?\d*","1.3 aa3.44aaa").group())
print(re.search("\d+\.?\d*","asdfsadf"))

print(re.search("\d+\.?\d*"," 1.3 aa3.44aaa"))
print(re.match("\d+\.?\d*"," 1.3 aa3.44aaa"))

msg="egon:18-male=10"
print(msg.split(':'))

print(re.split('[:=-]',msg))


msg='<a href="https://pan.baidu.com/s/1skWyTT7" target="_blank"><strong><span style="color: #ff0000;">原理图：https://pan.baidu.com/s/1skWyTT7</span></strong></a><a href="https://www.baidu/com">"点我啊"</a>'
print(re.findall('href=".*?"',msg))