import re

text = "這是一個(gè)測試字符串，包含apple和banana。"

# 查看是否包含 'apple' 或 'banana'
if re.search(r'apple|banana', text):
    print("包含 apple 或 banana")
else:
    print("不包含")
說明：
r'apple|banana' 是一個(gè)正則表達(dá)式，表示匹配 “apple” 或者 “banana”
re.search()：只要在字符串中有匹配項(xiàng)就返回 True（或匹配對(duì)象）

text = "訪問網(wǎng)址 www.google.com 或 http://www.baidu.com 獲取信息"
cleaned_text = re.sub(r'www\.|http://', '', text)
print(cleaned_text)
# 輸出: 訪問網(wǎng)址 google.com 或 baidu.com 獲取信息

text = "電話號(hào)碼是1234567890，郵編是100000"
numbers = re.findall(r'\d+', text)
print(numbers)
# 輸出: ['1234567890', '100000']

import string

text = "你好！這是一段,含有很多標(biāo)點(diǎn)？"
pattern = f"[{re.escape(string.punctuation)}]"
cleaned_text = re.sub(pattern, "", text)
print(cleaned_text)
# 輸出: 你好這是一段含有很多標(biāo)點(diǎn)

text = "Hello 你好，世界123"
chinese_chars = re.findall(r'[\u4e00-\u9fa5]+', text)
print(''.join(chinese_chars))
# 輸出: 你好世界

text = "  這是一個(gè)\t帶有很多\n空白的文本  "
cleaned_text = re.sub(r'\s+', ' ', text).strip()
print(cleaned_text)
# 輸出: 這是一個(gè) 帶有很多 空白的文本

深色版本
text = "聯(lián)系我 at example@example.com 或 support@domain.co.cn"
emails = re.findall(r'[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+', text)
print(emails)
# 輸出: ['example@example.com', 'support@domain.co.cn']

text = "訪問 https://example.com 或 http://www.google.com"
urls = re.findall(r'https?://(?:www\.)?\S+', text)
print(urls)
# 輸出: ['https://example.com', 'http://www.google.com']

text = "這!is a 123_測試-text..."
cleaned_text = re.sub(r'[^\u4e00-\u9fa5a-zA-Z0-9]', '', text)
print(cleaned_text)
# 輸出: 這is a 123測試text

text = "Hello World! 你好，World!"
cleaned_text = re.sub(r'[^\w\s]|_', '', text).lower()
print(cleaned_text)
# 輸出: hello world 你好world

import re

text = "我的電話是13812345678，請(qǐng)?jiān)诠ぷ鲿r(shí)間撥打。另一個(gè)號(hào)碼是13987654321"

# 提取所有11位手機(jī)號(hào)
phone_numbers = re.findall(r'1\d{10}', text)

# 格式化為 138-1234-5678 樣式
formatted_numbers = [re.sub(r'(\d{3})(\d{4})(\d{4})', r'\1-\2-\3', num) for num in phone_numbers]

print(formatted_numbers)
# 輸出: ['138-1234-5678', '139-8765-4321']

text = "聯(lián)系方式：138 1234 5678 或 139-1234-5678"

# 去除非數(shù)字字符后提取11位手機(jī)號(hào)
cleaned_numbers = re.findall(r'1\d{10}', re.sub(r'\D', '', text))

# 再格式化輸出
formatted_numbers = [re.sub(r'(\d{3})(\d{4})(\d{4})', r'\1-\2-\3', num) for num in cleaned_numbers]

print(formatted_numbers)
# 輸出: ['138-1234-5678', '139-1234-5678']

formatted_with_code = ['+86 ' + num for num in formatted_numbers]
print(formatted_with_code)
# 輸出: ['+86 138-1234-5678', '+86 139-1234-5678']

def format_chinese_phone(text):
    # 清理非數(shù)字內(nèi)容
    cleaned = re.sub(r'\D', '', text)
    # 提取手機(jī)號(hào)
    phones = re.findall(r'1\d{10}', cleaned)
    # 格式化
    return [re.sub(r'(\d{3})(\d{4})(\d{4})', r'\1-\2-\3', p) for p in phones]

# 使用示例
text = "我的聯(lián)系電話是：138 1234 5678 和 139-8765-4321"
print(format_chinese_phone(text))
# 輸出: ['138-1234-5678', '139-8765-4321']