import re

# 匹配多种日期格式：2023-12-01, 2023/12/01, 2023.12.01
date_pattern = r"\d{4}[-/.]\d{1,2}[-/.]\d{1,2}"
text = "项目开始日期：2023-12-01，结束日期：2023/12/31，审核日期：2024.01.05"

matches = re.findall(date_pattern, text)
print(matches)  # 输出: ['2023-12-01', '2023/12/31', '2024.01.05']

import re

# 匹配产品型号格式：字母+数字+字母
product_pattern = r"[A-Za-z]\d+[A-Za-z]"
text = "库存产品：A123B, C45D, X6789Y, 123ABC"

matches = re.findall(product_pattern, text)
print(matches)  # 输出: ['A123B', 'C45D', 'X6789Y']

import re

# 提取所有数字
text = "价格：¥129.99，数量：20个，折扣：8.5折"
numbers = re.findall(r"\d+\.?\d*", text)
print(numbers)  # 输出: ['129.99', '20', '8.5']

import re

# 过滤掉所有非字母和数字的字符（包括中文字符）
text = "Hello! World, 你好！123#$%"
clean_text = re.sub(r"[^a-zA-Z0-9\s\u4e00-\u9fa5]", "", text)
print(clean_text)  # 输出: 'Hello World 你好 123'

import re

def validate_username(username):
    pattern = r"^[a-zA-Z][a-zA-Z0-9_]{3,19}$"
    return bool(re.match(pattern, username))

print(validate_username("user123"))    # 输出: True
print(validate_username("123user"))    # 输出: False
print(validate_username("user"))       # 输出: True
print(validate_username("user@123"))   # 输出: False

import re

# 匹配中国大陆手机号码
def validate_phone(phone):
    pattern = r"^1[3-9]\d{9}$"
    return bool(re.match(pattern, phone))

print(validate_phone("13812345678"))   # 输出: True
print(validate_phone("12345678901"))   # 输出: False
print(validate_phone("1381234"))       # 输出: False

import re

# 匹配HTTP/HTTPS URL
url_pattern = r"^https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9()]{1,6}\b([-a-zA-Z0-9()@:%_\+.~#?&//=]*)$"

urls = ["https://www.example.com", "http://test.org", "www.invalid", "http://127.0.0.1"]

for url in urls:
    print(f"{url}: {bool(re.match(url_pattern, url))}")

# 输出:
# https://www.example.com: True
# http://test.org: True
# www.invalid: False
# http://127.0.0.1: True

import re

# 提取HTML标签
html = "<div class='container'><h1>Title</h1><p>Paragraph</p></div>"
html_tags = re.findall(r"<[^>]+>", html)
print(html_tags)  # 输出: ['<div class="container">', '<h1>', '</h1>', '<p>', '</p>', '</div>']

import re

# 测试文本
text = "<div>内容1</div><div>内容2</div>"

# 贪婪匹配
greedy_pattern = r"<div>.*</div>"
greedy_match = re.findall(greedy_pattern, text)
print("贪婪匹配结果:", greedy_match)  # 输出: ['<div>内容1</div><div>内容2</div>']

# 非贪婪匹配
lazy_pattern = r"<div>.*?</div>"
lazy_match = re.findall(lazy_pattern, text)
print("非贪婪匹配结果:", lazy_match)  # 输出: ['<div>内容1</div>', '<div>内容2</div>']

import re

# 测试文本
html = "<p class=\"intro\">这是介绍段落</p><p>这是普通段落</p>"

# 非贪婪匹配提取标签内容
pattern = r"<p[^>]*>(.*?)</p>"
contents = re.findall(pattern, html)
print("提取的内容:", contents)  # 输出: ['这是介绍段落', '这是普通段落']

import re

# 日志文本
log = "2023-05-01 10:15:30 ERROR: Failed to connect to database\n2023-05-01 10:16:45 WARNING: Low disk space"

# 使用非贪婪匹配提取日志级别和消息
greedy_pattern = r"(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}) (.*): (.*)"
lazy_pattern = r"(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}) (.*?): (.*)"

# 对于这种情况，贪婪和非贪婪匹配结果相同，但非贪婪模式在复杂情况下更可靠
matches = re.findall(lazy_pattern, log)
for match in matches:
    print(f"时间: {match[0]}, 级别: {match[1]}, 消息: {match[2]}")

import re

def validate_password(password):
    # 至少8位，包含大小写字母和数字
    pattern = r"^(?=.*[a-z])(?=.*[A-Z])(?=.*\d).{8,}$"
    return bool(re.match(pattern, password))

print(validate_password("Password123"))  # 输出: True
print(validate_password("password"))     # 输出: False
print(validate_password("PASSWORD123"))  # 输出: False
print(validate_password("Pass1"))        # 输出: False

import re

# 只匹配完整的单词"cat"
text = "The cat sat on the cathedral"
matches = re.findall(r"\bcat\b", text)
print(matches)  # 输出: ['cat']

# 匹配所有包含"cat"的单词
matches_all = re.findall(r"cat", text)
print(matches_all)  # 输出: ['cat', 'cat']

import re

url = "https://www.example.com/path/to/page"
pattern = r"^https?:\/\/(www\.)?([a-zA-Z0-9.-]+)"

match = re.match(pattern, url)
if match:
    domain = match.group(2)  # 提取第二个捕获组
    print(f"域名: {domain}")  # 输出: 域名: example.com

import re

date_text = "2023-12-01"
pattern = r"^(?P<year>\d{4})-(?P<month>\d{2})-(?P<day>\d{2})$"

match = re.match(pattern, date_text)
if match:
    year = match.group("year")
    month = match.group("month")
    day = match.group("day")
    print(f"年: {year}, 月: {month}, 日: {day}")  # 输出: 年: 2023, 月: 12, 日: 01

import re

# 去除文本中重复的单词
text = "这这是是一个个重重复复的的文文本文本"
# 匹配任意字符重复两次
result = re.sub(r"(.)\1", r"\1", text)
print(result)  # 输出: 这是一个重复的文本

# 英文示例
en_text = "the the quick quick brown fox"
# 匹配完整单词重复
en_result = re.sub(r"\b(\w+)\s+\1\b", r"\1", en_text)
print(en_result)  # 输出: the quick brown fox

import re
import time

# 编译正则表达式
email_pattern = re.compile(r"[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}")

# 测试文本
text = "联系邮箱：admin@example.com, support@test.org, user123@gmail.com"

# 使用编译后的正则表达式
start_time = time.time()
matches = email_pattern.findall(text)
end_time = time.time()

print(f"匹配结果: {matches}")
print(f"耗时: {(end_time - start_time) * 1000:.4f} 毫秒")

# 对于频繁使用的正则表达式，编译可以显著提高性能

import re

# 使用正则表达式分割字符串
text = "apple,orange;banana grape\tpear"
# 按逗号、分号、空格或制表符分割
result = re.split(r"[,;\s\t]+", text)
print(result)  # 输出: ['apple', 'orange', 'banana', 'grape', 'pear']

# 保留分隔符的示例
date_text = "2023-12-01 2023/12/02 2023.12.03"
# 按日期分隔符分割并保留分隔符
result_with_separators = re.split(r"([-/.])", date_text)
print(result_with_separators)  # 输出: ['2023', '-', '12', '-', '01 2023', '/', '12', '/', '02 2023', '.', '12', '.', '03']