text = "中文文本"
utf8_bytes = text.encode('utf-8')  # 轉(zhuǎn)為UTF-8字節(jié)流
gbk_str = utf8_bytes.decode('utf-8').encode('gbk', errors='replace')  # 轉(zhuǎn)GBK編碼
print(gbk_str.decode('gbk', errors='ignore'))  # 輸出：中文文本

csv_line = "2023-07-25,192.168.1.1,GET /api/data,200"
# 分割時(shí)處理多余空格
parts = [x.strip() for x in csv_line.split(',', maxsplit=3)]  
print(parts)  # ['2023-07-25', '192.168.1.1', 'GET /api/data', '200']

text = "Python2 is outdated, but Python2 code still exists"
new_text = text.replace("Python2", "Python3", 1)  # 僅替換第一個(gè)匹配項(xiàng)
print(new_text)  # "Python3 is outdated, but Python2 code still exists"

import re

# 預(yù)編譯提升性能（重要?。?
PHONE_PATTERN = re.compile(r'(\+86)?1[3-9]\d{9}')  

text = "聯(lián)系方式：+8613812345678，備用號(hào)15812345678"
matches = PHONE_PATTERN.findall(text)
print(matches)  # ['+86', ''] 分組匹配結(jié)果

log_line = '127.0.0.1 - - [25/Jul/2023:15:30:22 +0800] "GET /index.html HTTP/1.1" 200 2326'

pattern = r'''
    ^(\d+\.\d+\.\d+\.\d+)\s+       # IP地址
    ([\w-]+)\s+                     # 用戶標(biāo)識(shí)
    ([\w-]+)\s+                     # 認(rèn)證用戶
    \[(.*?)\]\s+                    # 時(shí)間戳
    "(.*?)\s+(.*?)\s+HTTP/(\d\.\d)" # 請(qǐng)求信息
    \s+(\d{3})\s+                   # 狀態(tài)碼
    (\d+)                           # 響應(yīng)大小
'''

match = re.compile(pattern, re.X).search(log_line)
if match:
    print(f"IP: {match.group(1)}, 狀態(tài)碼: {match.group(8)}")

def clean_html(raw):
    # 刪除HTML標(biāo)簽但保留內(nèi)容
    cleaner = re.compile(r'<[^>]+>| | |\n')
    # 合并連續(xù)空格
    return re.sub(r'\s{2,}', ' ', cleaner.sub(' ', raw))

dirty_html = "<p>Hello  World!</p>  
"
print(clean_html(dirty_html))  # "Hello World!  "

import re
import json

def extract_json_field(json_str, target_field):
    """
    提取JSON字符串中指定字段的值（處理轉(zhuǎn)義引號(hào)）
    :param json_str: 原始JSON字符串
    :param target_field: 要提取的字段名
    :return: 匹配值列表
    """
    # 匹配字段值：字符串、數(shù)字、布爾、null
    pattern = re.compile(
        rf'"{target_field}"\s*:\s*("(?:\\"|[^"])*"|-?\d+\.?\d*|true|false|null)',
        re.IGNORECASE
    )
    return [json.loads(m.group(1)) if m.group(1).startswith('"') 
            else eval(m.group(1)) 
            for m in pattern.finditer(json_str)]

# 測試用例
sample_json = '''
{"user": "Alice", "data": "{\\"info\\": \\"secret\\"}", "age": 25}
'''
print(extract_json_field(sample_json, "data"))  # 輸出： ['{"info": "secret"}']

import re

def validate_password(password):
    """
    驗(yàn)證密碼復(fù)雜度：
    - 至少1個(gè)大寫字母
    - 至少1個(gè)小寫字母
    - 至少1個(gè)數(shù)字
    - 至少1個(gè)特殊符號(hào)(!@#$%^&*)
    - 長度8-20
    """
    pattern = re.compile(
        r'^(?=.*[A-Z])(?=.*[a-z])(?=.*\d)(?=.*[!@#$%^&*])[\w!@#$%^&*]{8,20}$'
    )
    return bool(pattern.fullmatch(password))

# 測試
print(validate_password("Abc123#"))   # False（長度不足）
print(validate_password("Abcdefg123!"))  # True

def split_chinese_english(text):
    """
    中英文分詞：中文按字分割，英文按單詞分割
    """
    return re.findall(r'\b\w+\b|[\u4e00-\u9fa5]', text)

# 測試
sample = "Hello世界！Python 代碼 2023"
print(split_chinese_english(sample))  # ['Hello世界', 'Python', '代碼', '2023'] 由于\w+匹配的是單詞，而Hello世界是 連在一起的并非單詞所以 沒有達(dá)到分詞的效果


def split_chinese_english(text):
    """
    中英文分詞：中文按字分割，英文按單詞分割
    """
    pattern = r'[a-zA-Z0-9]+|[\u4e00-\u9fa5]'
    return re.findall(pattern, text)


# 測試
sample = "Hello世界！Python代碼2023"
print(split_chinese_english(sample)) # ['Hello', '世', '界', 'Python', '代', '碼', '2023']


def split_chinese_english(text):
    # 先將英文和數(shù)字部分提取出來
    english_num_pattern = re.compile(r'[a-zA-Z0-9]+')
    english_num_matches = english_num_pattern.findall(text)
    # 去除英文和數(shù)字部分，只保留中文和其他字符
    chinese_text = english_num_pattern.sub('', text)
    # 對(duì)中文部分進(jìn)行分詞
    chinese_words = jieba.lcut(chinese_text)
    result = []
    index = 0
    for char in text:
        if re.match(r'[a-zA-Z0-9]', char):
            if index < len(english_num_matches) and text.startswith(english_num_matches[index], text.index(char)):
                result.append(english_num_matches[index])
                index += 1
        elif char in ''.join(chinese_words):
            for word in chinese_words:
                if text.startswith(word, text.index(char)):
                    result.append(word)
                    break
    return result


# 測試
sample = "Hello世界！Python代碼2023"
print(split_chinese_english(sample)) # ['Hello', '世界', '！', 'Python', '代碼', '2023']

import re
from urllib.parse import urlparse

# 預(yù)編譯提升性能
URL_PATTERN = re.compile(
    r'https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+(?:[/?#][^\s"]*)?',
    re.IGNORECASE
)

def extract_urls_large_file(file_path):
    """流式讀取大文件提取URL"""
    with open(file_path, 'r', encoding='utf-8') as f:
        for line in f:
            yield from (urlparse(url).geturl() for url in URL_PATTERN.findall(line))

# 使用示例
# for url in extract_urls_large_file("bigfile.log"):
#     print(url)

def convert_date_format(text):
    """將MM/DD/YYYY格式轉(zhuǎn)為YYYY-MM-DD"""
    return re.sub(
        r'\b(0?[1-9]|1[0-2])/(0?[1-9]|[12]\d|3[01])/(\d{4})\b',
        lambda m: f"{m.group(3)}-{m.group(1).zfill(2)}-{m.group(2).zfill(2)}",
        text
    )

# 測試
print(convert_date_format("Date: 7/25/2023, 12/31/2024"))  
# 輸出：Date: 2023-07-25, 2024-12-31

def highlight_sql_injection(text):
    """高亮常見SQL注入關(guān)鍵詞"""
    keywords = r'union|select|insert|delete|update|drop|--|\/\*'
    return re.sub(
        f'(python字符串正則匹配,python字符串正則替換,python字符串正則替換)', 
        lambda m: f'\033[31m{m.group(1)}\033[0m', 
        text, 
        flags=re.IGNORECASE
    )

# 測試
sample = "SELECT * FROM users WHERE id=1 UNION SELECT password FROM admins"
print(highlight_sql_injection(sample))

class FastMatcher:
    def __init__(self):
        self.patterns = {
            'email': re.compile(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b'),
            'phone': re.compile(r'\+?\d{1,3}[-. ]?\(?\d{3}\)?[-. ]?\d{3}[-. ]?\d{4}'),
            'hashtag': re.compile(r'#\w+')
        }
    
    def match_all(self, text):
        return {k: p.findall(text) for k, p in self.patterns.items()}

# 使用示例
matcher = FastMatcher()
print(matcher.match_all("Contact: test@example.com #info 123-456-7890"))

def parse_nonstandard_csv(csv_str):
    """解析帶逗號(hào)的CSV字段（使用正則）"""
    return re.findall(
        r'(?:^|,)(?:"((?:[^"]|"")*)"|([^",]*))', 
        csv_str
    )

# 測試
sample = '1, "Quote, test", "Escaped ""Double Quote"""'
print([tuple(filter(None, m)) for m in parse_nonstandard_csv(sample)])
# 輸出：[('1',), ('Quote, test',), ('Escaped "Double Quote"',)]

from datetime import datetime

def convert_log_timestamp(log_line):
    """轉(zhuǎn)換[25/Jul/2023:15:30:22 +0800]到ISO格式"""
    def repl(m):
        dt = datetime.strptime(m.group(1), "%d/%b/%Y:%H:%M:%S %z")
        return dt.isoformat()
    
    return re.sub(
        r'\[(\d{2}/\w{3}/\d{4}:\d{2}:\d{2}:\d{2} [+\-]\d{4})\]',
        repl,
        log_line
    )

# 測試
log = '[25/Jul/2023:15:30:22 +0800] "GET /" 200'
print(convert_log_timestamp(log))  
# 輸出：2023-07-25T15:30:22+08:00 "GET /" 200

class SimpleTemplate:
    def __init__(self, template):
        self.pattern = re.compile(r'\{\{(\w+)\}\}')
        self.template = template

    def render(self, **context):
        return self.pattern.sub(
            lambda m: str(context.get(m.group(1), '')),  self.template
        )

# 使用示例
tpl = SimpleTemplate("Hello, {{name}}! Your score: {{score}}")
print(tpl.render(name="Alice", score=95))
# 輸出：Hello, Alice! Your score: 95