Python正则表达式专项练习「私教练习」答案

题目：https://blog.csdn.net/qq_33254766/article/details/135070656

1. 找到文本中的所有日期

   text = "重要日期：2023-12-25, 2024-01-01"
   dates = re.findall(r'\d{4}-\d{2}-\d{2}', text)
   assert dates == ["2023-12-25", "2024-01-01"]
   

2. 验证电子邮件地址

   email = "example@test.com"
   is_valid = bool(re.match(r'^[\w\.-]+@[\w\.-]+\.\w+$', email))
   assert is_valid is True
   

3. 分割日志文件

   log = "INFO:2023-12-17:This is log 1\nERROR:2023-12-18:This is log 2"
   entries = re.split(r'\n', log)
   assert entries == ["INFO:2023-12-17:This is log 1", "ERROR:2023-12-18:This is log 2"]
   

4. 匹配电话号码

   phone = "(123) 456-7890"
   is_phone = bool(re.match(r'\(\d{3}\)\s\d{3}-\d{4}', phone))
   assert is_phone is True
   

5. 提取URL

   text = "Visit https://example.com and http://test.org"
   urls = re.findall(r'https?://\S+', text)
   assert urls == ["https://example.com", "http://test.org"]
   

6. 验证密码强度

   password = "Aa1!aa11"
   is_strong = bool(re.match(r'(?=.*[a-z])(?=.*[A-Z])(?=.*\d)(?=.*[@$!%*?&])[A-Za-z\d@$!%*?&]{8,}', password))
   assert is_strong is True
   

7. 寻找重复的单词

   text = "This is a test test text"
   duplicate = re.search(r'\b(\w+)\s+\1\b', text)
   assert duplicate.group() == "test test"
   

8. 提取括号内的内容

   text = "This is a (sample) text"
   content = re.findall(r'\((.*?)\)', text)
   assert content == ["sample"]
   

9. 识别货币金额

   text = "The price is $100.00 or €50"
   amounts = re.findall(r'[$€]\d+(?:\.\d{2})?', text)
   assert amounts == ["$100.00", "€50"]
   

10. 识别时间格式

    text = "The current time is 14:30:15 or sometimes 09:45"
    times = re.findall(r'\b\d{1,2}:\d{2}(?::\d{2})?\b', text)
    assert times == ["14:30:15", "09:45"]
    

11. 验证车牌号

    plate = "ABC-1234"
    is_plate = bool(re.match(r'^[A-Z]{3}-\d{4}$', plate))
    assert is_plate is True
    

12. 匹配IPv4地址

    ip = "192.168.1.1"
    is_ipv4 = bool(re.match(r'^\d{1,3}(\.\d{1,3}){3}$', ip))
    assert is_ipv4 is True
    

13. 提取HTML标签内容

    html = "<div>Hello World!</div>"
    content = re.findall(r'<div>(.*?)</div>', html)
    assert content == ["Hello World!"]
    

14. 匹配Markdown链接

    markdown = "This is a [link](http://example.com)"
    link_text = re.findall(r'\[([^\]]+)\]\((http[s]?://\S+)\)', markdown)
    assert link_text == [("link", "http://example.com")]
    

15. 识别代码注释

    code = "// This is a comment\nint x = 0; /* block comment */"
    comments = re.findall
    
    

(r’//.?$|/*.?*/', code, re.DOTALL | re.MULTILINE)
assert comments == [“// This is a comment”, “/* block comment */”]
```

16. 匹配科学计数法数字

    number = "1.23e10"
    is_scientific = bool(re.match(r'^-?\d+(\.\d+)?e[-+]?\d+$', number))
    assert is_scientific is True
    

17. 解析复杂日志格式

    log = "[2023-12-17 10:00:00, INFO] This is an information."
    pattern = r'\[(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}), (\w+)\] (.+)'
    match = re.search(pattern, log)
    assert match.groups() == ("2023-12-17 10:00:00", "INFO", "This is an information.")
    

18. 匹配嵌套括号内容

    text = "This is a (nested (example) text) string"
    nested_content = re.findall(r'\(([^()]|\([^()]*\))*\)', text)
    assert nested_content == ["(nested (example) text)"]
    

19. 验证XML/HTML标签结构

    html = "<tag>content</tag>"
    is_valid_html = bool(re.match(r'<([a-z]+)>(.*?)</\1>', html))
    assert is_valid_html is True
    

20. 提取嵌入式语言元素

    html = "<style>body { background-color: #fff; }</style>"
    style_content = re.findall(r'<style>(.*?)</style>', html, re.DOTALL)
    assert style_content == ["body { background-color: #fff; }"]
    

这些题目旨在通过实践提高对Python中正则表达式的理解和应用。每个题目都包含了一个具体的例子和一个assert语句，以便验证你的正则表达式是否正确。