『聚合』 从基础到代码实战，带你进阶正则表达式的全方位应用

import re

def validate_email(email):
    pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
    if re.match(pattern, email):
        print(f"{email} 是一个有效的邮箱地址")
    else:
        print(f"{email} 不是一个有效的邮箱地址")

# 测试
validate_email("[email protected]")
validate_email("[email protected]")

import re

html_content = '<a href="https://www.example.com">Visit our website</a>'

# 提取链接
links = re.findall(r'href="([^"]*)"', html_content)

# 输出链接
for link in links:
    print(f"链接: {link}")

import re

text = "今天是2024年2月27日，明天是2024-02-28。"

# 替换日期格式
formatted_text = re.sub(r'(\d{4})-(\d{2})-(\d{2})', r'\2/\3/\1', text)

print(f"替换前: {text}")
print(f"替换后: {formatted_text}")

import re

def check_password_strength(password):
    # 至少8个字符，包含至少一个大写字母、一个小写字母、一个数字和一个特殊字符
    pattern = r'^(?=.*[a-z])(?=.*[A-Z])(?=.*\d)(?=.*[@$!%*?&])[A-Za-z\d@$!%*?&]{8,}$'
    
    if re.match(pattern, password):
        print("密码强度符合要求")
    else:
        print("密码强度不够")

# 测试
check_password_strength("StrongPass123!")
check_password_strength("weakpassword")

import re

text = "请联系客户：+86 13812345678 或者发送邮件至[email protected]"

# 提取手机号码
phone_numbers = re.findall(r'(?:(?:\+|00)86)?1[345789]\d{9}', text)

# 输出手机号码
for number in phone_numbers:
    print(f"手机号码: {number}")

import re

csv_data = "apple,orange,banana,grape"

# 使用正则表达式拆分
items = re.split(r',', csv_data)

# 输出拆分结果
print("拆分后的结果:", items)

import re

def validate_url(url):
    # 简单的URL验证，以http或https开头，后面跟着域名
    pattern = r'^(https?://)?[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}(?:/[^/#?]+)*(?:\?[^#]*)?(?:#(.*))?$'
    
    if re.match(pattern, url):
        print(f"{url} 是一个有效的URL")
    else:
        print(f"{url} 不是一个有效的URL")

# 测试
validate_url("https://www.example.com")
validate_url("ftp://invalid-url.com")

import re

html_content = '<p>This is a <b>sample</b> HTML content.</p>'

# 提取纯文本内容
text_content = re.sub(r'<[^>]+>', '', html_content)

print(f"HTML内容: {html_content}")
print(f"提取后的文本内容: {text_content}")

import re

text = "这个单词是重复重复的，但是它们都是有意义的重复。"

# 匹配连续重复的单词
repeated_words = re.findall(r'\b(\w+)\s+\1\b', text)

# 输出匹配结果
print("连续重复的单词:", repeated_words)

import re

log_data = """
2024-02-27 10:15: Error in module A
2024-02-27 11:30: Warning in module B
2024-02-27 12:45: Info: Application started
"""

# 提取日志信息
log_entries = re.findall(r'(\d{4}-\d{2}-\d{2} \d{2}:\d{2}): (Error|Warning|Info): (.+)', log_data)

# 输出提取结果
for entry in log_entries:
    timestamp, log_level, message = entry
    print(f"{timestamp} - [{log_level}] {message}")

import re

text = "这是一个示例文本，包含一些需要替换的词汇，例如apple和orange。"

# 替换文本中的水果名称
replaced_text = re.sub(r'\b(apple|orange)\b', 'fruit', text)

print(f"替换前: {text}")
print(f"替换后: {replaced_text}")

import re

multiline_text = """
This is line 1.
Another line here.
And a third line.
"""

# 匹配包含"line"的行
matching_lines = re.findall(r'.*line.*', multiline_text, re.MULTILINE)

# 输出匹配结果
for line in matching_lines:
    print(f"匹配的行: {line}")

import re

text = "2024-02-27 08:30: Process A started, Process B started"

# 匹配并捕获时间和进程名称
pattern = r'(\d{4}-\d{2}-\d{2} \d{2}:\d{2}): (Process [A-Z]) started'
matches = re.findall(pattern, text)

# 输出捕获结果
for match in matches:
    timestamp, process_name = match
    print(f"时间: {timestamp}, 进程: {process_name}")

import re

text = "<b>bold text</b> and <i>italic text</i>"

# 贪婪匹配
greedy_match = re.search(r'<.*>', text).group()

# 非贪婪匹配
non_greedy_match = re.search(r'<.*?>', text).group()

print(f"贪婪匹配: {greedy_match}")
print(f"非贪婪匹配: {non_greedy_match}")

import re

def multiply(match):
    number = int(match.group(1))
    return str(number * 2)

text = "Numbers: 2, 5, 8, 12"

# 使用回调函数替换数字
result = re.sub(r'\b(\d+)\b', multiply, text)

print(f"替换前: {text}")
print(f"替换后: {result}")