第十一章 正则表达式 课后练习题

>>> import re
>>>
>>> s = "abc123 90years $hello world!"
>>> p = re.compile(r"^[a-zA-Z]+",re.M)
>>> print(p.match(s).group())
abc

>>> s = "2022 abc123 90years $hello world!"
>>> p = re.compile(r"^\d+",re.M)
>>> print(p.match(s).group())
2022

>>> s = "abc123 90years $hello world!"
>>> p = re.compile(r"^\w+",re.M)
>>> print(p.match(s).group())
abc123

import re
 
s = """abc123
90ww dd123
hello world!
 Hi girl~
 ###test"""
 
p = re.compile(r"^\w+$",re.M)
print(p.findall(s))

>>> word_lst =  ["Abc112_","akkk_222A","_12ABc","123abcA",\
... "test@","!num","he@#he"]
>>> for word in word_lst:
...     if re.match(r"^[a-zA-Z_]\w*$",word):
...             print(word)
...
Abc112_
akkk_222A
_12ABc

import re
 
# p = re.compile(r"[0-9]{4}-[01][0-9]-[0-3][0-9]\s([01][0-9]|2[0-3]):[0-5][0-9]:[0-5][0-9]") # 月份、日期处理没有细致处理
p = re.compile(r"^(?:(?!0000)[0-9]{4}-(?:(?:0[1-9]|1[0-2])-(?:0[1-9]|1[0-9]|2[0-8])|(?:0[13-9]|1[0-2])-(?:29|30)|(?:0[13578]|1[02])-31)|(?:[0-9]{2}(?:0[48]|[2468][048]|[13579][26])|(?:0[48]|[2468][048]|[13579][26])00)-02-29)\s([01][0-9]|2[0-3]):[0-5][0-9]:[0-5][0-9]$") # 网上找到 https://blog.csdn.net/lxcnn/article/details/4362500
 
with open("p11-7.txt") as fp:
	for line in fp:
		if p.match(line):
			print(line.strip())

文档内容：

1970-01-01 00:00:00
2099-12-31 23:59:59
2022-02-22 12:22:33
1234-08-05 24:00:00
1234-08-05 11:00:00
1991-02-31 11:00:00
2022-14-05 11:00:00
2022-03-55 11:00:00
2022-11-05 26:00:00
2022-10-05 12:61:00
2022-12-05 12:00:79

>>> import re
>>> re.match(r'\\home',"\home")
<re.Match object; span=(0, 5), match='\\home'>
>>> re.match(r'\\home',"\home").group()
'\\home'
>>> print(re.match(r'\\home',"\home").group())
\home

10、使用正则提取出字符串中的单词

import re
 
s="I just had to come over and say 'Amazing eyes'. You wearing color contacts?"
p = re.compile(r"\b[a-z]+\b",re.I)
print(p.findall(s))

s = '"http://www.gloryroad.cn' 
p = re.compile(r"((http|ftp|https)://)(([a-zA-Z0-9\._-]+\.[a-zA-Z]{2,6})|([0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}))(:[0-9]{1,4})*(/[a-zA-Z0-9\&%_\./-~-]*)?")
print(p.search(s).group())

12、提取字符串中合法的超链接地址

>>> s = '<a href="http://www.gloryroad.cn">光荣之路官网</a>'
>>> p = re.compile(r"http[s]?://\w+(\.\w+\.\w+)+")
>>> print(p.search(s).group())
http://www.gloryroad.cn

import re
word_list = []
with open("xxx.txt") as file_obj:
    content = file_obj.read()
word_list = re.findall(r"\b[a-z]+\b",content,re.I)
print("word number: ",len(word_list))

14、写一个函数，其中用正则验证密码的强度