【一起学Python】第12天:字符串类型String详细使用总结

# 单引号s1 = 'Hello'# 双引号s2 = "World"# 三引号（多行字符串）s3 = '''这是多行字符串'''s4 = """也可以使用双引号"""# 原始字符串（不转义）s5 = r'C:\Users\name'  # 不会把\n当成换行# 字节字符串s6 = b'Hello'  # bytes类型# Unicode字符串（Python 3默认）s7 = 'Hello 世界 🌍'# 空字符串empty = ''empty2 = str()# 字符串拼接s = 'Hello' + ' ' + 'World'print(s)  # 'Hello World'# 字符串重复s = 'Ha' * 3print(s)  # 'HaHaHa'

s = 'Python'# 正向索引print(s[0])   # 'P'print(s[1])   # 'y'print(s[5])   # 'n'# 反向索引print(s[-1])  # 'n' (最后一个)print(s[-2])  # 'o'print(s[-6])  # 'P'# 切片 [start:stop:step]print(s[0:3])    # 'Pyt'print(s[:3])     # 'Pyt' (从开头)print(s[3:])     # 'hon' (到结尾)print(s[:])      # 'Python' (完整复制)# 带步长print(s[::2])    # 'Pto' (每隔一个)print(s[1::2])   # 'yhn'# 反转字符串print(s[::-1])   # 'nohtyP'# 负数切片print(s[-3:])    # 'hon' (最后3个)print(s[:-3])    # 'Pyt' (除了最后3个)# 切片越界不报错print(s[10:])    # '' (空字符串)print(s[:100])   # 'Python'

s = 'Hello World'# 全部大写print(s.upper())  # 'HELLO WORLD'# 全部小写print(s.lower())  # 'hello world'# 首字母大写print(s.capitalize())  # 'Hello world'# 每个单词首字母大写print(s.title())  # 'Hello World'# 大小写互换print(s.swapcase())  # 'hELLO wORLD'# 判断print(s.isupper())  # Falseprint(s.islower())  # Falseprint(s.istitle())  # True

s = 'Hello World, Hello Python'# 查找子串（返回索引）print(s.find('World'))  # 6print(s.find('Java'))   # -1 (未找到)# 从右边查找print(s.rfind('Hello'))  # 13# 查找（未找到抛异常）print(s.index('World'))  # 6# print(s.index('Java'))  # ValueError# 统计出现次数print(s.count('Hello'))  # 2print(s.count('o'))      # 4# 替换print(s.replace('Hello', 'Hi'))  # 'Hi World, Hi Python'# 替换指定次数print(s.replace('Hello', 'Hi', 1))  # 'Hi World, Hello Python'# 判断开头print(s.startswith('Hello'))  # Trueprint(s.startswith('Hi'))     # False# 判断结尾print(s.endswith('Python'))  # Trueprint(s.endswith('Java'))    # False

# split() - 分割字符串s = 'apple,banana,orange'print(s.split(','))  # ['apple', 'banana', 'orange']s = 'one two  three   four'print(s.split())  # 默认按空白分割# ['one', 'two', 'three', 'four']# 限制分割次数s = 'a-b-c-d'print(s.split('-', 2))  # ['a', 'b', 'c-d']# rsplit() - 从右边分割print(s.rsplit('-', 1))  # ['a-b-c', 'd']# splitlines() - 按行分割s = 'line1\nline2\nline3'print(s.splitlines())  # ['line1', 'line2', 'line3']# partition() - 分成三部分s = 'hello-world'print(s.partition('-'))  # ('hello', '-', 'world')# join() - 连接字符串words = ['apple', 'banana', 'orange']print(','.join(words))  # 'apple,banana,orange'print(' '.join(words))  # 'apple banana orange'# 连接数字需要先转字符串numbers = [1, 2, 3]print(','.join(map(str, numbers)))  # '1,2,3'

s = '  Hello World  '# 去除两端空白print(s.strip())   # 'Hello World'# 去除左边空白print(s.lstrip())  # 'Hello World  '# 去除右边空白print(s.rstrip())  # '  Hello World'# 去除指定字符s = '***Hello***'print(s.strip('*'))  # 'Hello's = 'www.example.com'print(s.strip('cmowz.'))  # 'example'# 去除换行符s = 'Hello\n'print(s.rstrip('\n'))  # 'Hello'

s = 'Hello'# 左对齐print(s.ljust(10))       # 'Hello     'print(s.ljust(10, '*'))  # 'Hello*****'# 右对齐print(s.rjust(10))       # '     Hello'print(s.rjust(10, '*'))  # '*****Hello'# 居中print(s.center(10))      # '  Hello   'print(s.center(10, '*')) # '**Hello***'# 填充0（数字）num = '42'print(num.zfill(5))  # '00042'num = '-42'print(num.zfill(5))  # '-0042'

# 是否全是字母print('Hello'.isalpha())   # Trueprint('Hello123'.isalpha()) # False# 是否全是数字print('123'.isdigit())   # Trueprint('12.3'.isdigit())  # False# 是否全是字母或数字print('Hello123'.isalnum())  # Trueprint('Hello 123'.isalnum()) # False# 是否全是空白print('   '.isspace())  # Trueprint(' a '.isspace())  # False# 是否全是小写print('hello'.islower())  # Trueprint('Hello'.islower())  # False# 是否全是大写print('HELLO'.isupper())  # Trueprint('Hello'.isupper())  # False# 是否是标题格式print('Hello World'.istitle())  # Trueprint('Hello world'.istitle())  # False# 是否是十进制数字print('123'.isdecimal())  # Trueprint('½'.isdecimal())    # False# 是否是数字（包括Unicode数字）print('123'.isnumeric())  # Trueprint('½'.isnumeric())    # Trueprint('Ⅳ'.isnumeric())    # True (罗马数字)# 是否是合法标识符print('variable'.isidentifier())  # Trueprint('123abc'.isidentifier())    # Falseprint('_var'.isidentifier())      # True# 是否可打印print('Hello'.isprintable())  # Trueprint('Hello\n'.isprintable()) # False# 是否是ASCIIprint('Hello'.isascii())  # Trueprint('你好'.isascii())   # False

# 编码为字节s = 'Hello 世界'bytes_utf8 = s.encode('utf-8')print(bytes_utf8)  # b'Hello \xe4\xb8\x96\xe7\x95\x8c'bytes_gbk = s.encode('gbk')print(bytes_gbk)  # b'Hello \xca\xc0\xbd\xe7'# 解码为字符串s = bytes_utf8.decode('utf-8')print(s)  # 'Hello 世界'# 处理编码错误bytes_data = b'\xff\xfe'print(bytes_data.decode('utf-8', errors='ignore'))  # 忽略错误print(bytes_data.decode('utf-8', errors='replace')) # 替换为�

# 旧式格式化（%）name = 'Alice'age = 25print('Name: %s, Age: %d' % (name, age))  # 'Name: Alice, Age: 25'# format() 方法print('Name: {}, Age: {}'.format(name, age))  # 'Name: Alice, Age: 25'print('Name: {0}, Age: {1}'.format(name, age))  # 'Name: Alice, Age: 25'print('Name: {n}, Age: {a}'.format(n=name, a=age))  # 'Name: Alice, Age: 25'# f-string (Python 3.6+，推荐)print(f'Name: {name}, Age: {age}')  # 'Name: Alice, Age: 25'# f-string 表达式x, y = 10, 20print(f'{x} + {y} = {x + y}')  # '10 + 20 = 30'# f-string 格式化pi = 3.141592653589793print(f'π ≈ {pi:.2f}')  # 'π ≈ 3.14'# f-string 调用方法name = 'alice'print(f'Hello, {name.upper()}!')  # 'Hello, ALICE!'# f-string 字典person = {'name': 'Bob', 'age': 30}print(f"Name: {person['name']}, Age: {person['age']}")  # 'Name: Bob, Age: 30'# f-string 调试（Python 3.8+）x = 10print(f'{x=}')  # 'x=10'

# 1. 基本格式化name = 'Alice'age = 25# 位置参数print('{} is {} years old'.format(name, age))# 'Alice is 25 years old'# 索引参数print('{0} is {1} years old'.format(name, age))# 'Alice is 25 years old'# 关键字参数print('{n} is {a} years old'.format(n=name, a=age))# 'Alice is 25 years old'# 2. 数字格式化num = 42# 二进制print('{:b}'.format(num))  # '101010'# 八进制print('{:o}'.format(num))  # '52'# 十六进制print('{:x}'.format(num))  # '2a'print('{:X}'.format(num))  # '2A'# 3. 浮点数格式化pi = 3.141592653589793# 保留小数print('{:.2f}'.format(pi))  # '3.14'print('{:.4f}'.format(pi))  # '3.1416'# 科学计数法print('{:.2e}'.format(1234567))  # '1.23e+06'print('{:.2E}'.format(1234567))  # '1.23E+06'# 百分比print('{:.2%}'.format(0.85))  # '85.00%'# 4. 对齐text = 'Hello'# 左对齐print('{:<10}'.format(text))  # 'Hello     '# 右对齐print('{:>10}'.format(text))  # '     Hello'# 居中print('{:^10}'.format(text))  # '  Hello   '# 填充字符print('{:*<10}'.format(text))  # 'Hello*****'print('{:*>10}'.format(text))  # '*****Hello'print('{:*^10}'.format(text))  # '**Hello***'# 5. 千位分隔符num = 1234567890print('{:,}'.format(num))  # '1,234,567,890'print('{:_}'.format(num))  # '1_234_567_890'# 6. 正负号print('{:+}'.format(42))   # '+42'print('{:+}'.format(-42))  # '-42'print('{: }'.format(42))   # ' 42'# 7. 组合使用price = 1234.5print('{:>10,.2f}'.format(price))  # '  1,234.50'

# 方法1：+ 运算符s1 = 'Hello's2 = 'World'result = s1 + ' ' + s2print(result)  # 'Hello World'# 方法2：join()（推荐，更高效）words = ['Hello', 'World']result = ' '.join(words)print(result)  # 'Hello World'# 方法3：f-stringname = 'Alice'age = 25result = f'{name} is {age} years old'print(result)  # 'Alice is 25 years old'# 方法4：format()result = '{} is {} years old'.format(name, age)print(result)  # 'Alice is 25 years old'# 方法5：% 格式化result = '%s is %d years old' % (name, age)print(result)  # 'Alice is 25 years old'# ⚠️ 性能对比：大量拼接时# ❌ 低效result = ''for i in range(1000):    result += str(i)  # 每次创建新字符串# ✅ 高效result = ''.join(str(i) for i in range(1000))

s = 'Hello'# 方法1：切片（最简单）print(s[::-1])  # 'olleH'# 方法2：reversed() + join()print(''.join(reversed(s)))  # 'olleH'# 方法3：递归def reverse_recursive(s):    if len(s) <= 1:        return s    return reverse_recursive(s[1:]) + s[0]print(reverse_recursive(s))  # 'olleH'

s = 'hello'# 方法1：set + join（不保持顺序）print(''.join(set(s)))  # 'helo' (顺序不定)# 方法2：保持顺序def remove_duplicates(s):    seen = set()    result = []    for char in s:        if char not in seen:            seen.add(char)            result.append(char)    return ''.join(result)print(remove_duplicates(s))  # 'helo'# 方法3：dict.fromkeys()（Python 3.7+保持顺序）print(''.join(dict.fromkeys(s)))  # 'helo'

import res = 'My email is alice@example.com and bob@test.com'# 查找所有邮箱emails = re.findall(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b', s)print(emails)  # ['alice@example.com', 'bob@test.com']# 替换result = re.sub(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b',                 '[EMAIL]', s)print(result)  # 'My email is [EMAIL] and [EMAIL]'# 分割s = 'apple, banana; orange|grape'result = re.split(r'[,;|]', s)print(result)  # ['apple', ' banana', ' orange', 'grape']# 匹配pattern = r'^[A-Za-z0-9]+$'print(re.match(pattern, 'Hello123'))  # Match对象print(re.match(pattern, 'Hello 123')) # None

def validate_email(email):    """验证邮箱格式"""    import re    pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'    return bool(re.match(pattern, email))print(validate_email('alice@example.com'))  # Trueprint(validate_email('invalid.email'))      # Falsedef validate_phone(phone):    """验证手机号（中国）"""    import re    pattern = r'^1[3-9]\d{9}$'    return bool(re.match(pattern, phone))print(validate_phone('13812345678'))  # Trueprint(validate_phone('12345678901'))  # Falsedef validate_password(password):    """验证密码强度（至少8位，包含大小写字母和数字）"""    if len(password) < 8:        return False    has_upper = any(c.isupper() for c in password)    has_lower = any(c.islower() for c in password)    has_digit = any(c.isdigit() for c in password)    return has_upper and has_lower and has_digitprint(validate_password('Abc12345'))  # Trueprint(validate_password('abc12345'))  # False (无大写)

def word_count(text):    """统计单词数"""    words = text.split()    return len(words)def char_count(text, ignore_space=True):    """统计字符数"""    if ignore_space:        text = text.replace(' ', '')    return len(text)def most_common_word(text):    """找出最常见的单词"""    from collections import Counter    words = text.lower().split()    counter = Counter(words)    return counter.most_common(1)[0]text = 'hello world hello python hello'print(word_count(text))  # 5print(char_count(text))  # 25print(most_common_word(text))  # ('hello', 3)

def caesar_cipher(text, shift=3):    """凯撒密码加密"""    result = []    for char in text:        if char.isalpha():            start = ord('A') if char.isupper() else ord('a')            shifted = (ord(char) - start + shift) % 26 + start            result.append(chr(shifted))        else:            result.append(char)    return ''.join(result)def caesar_decipher(text, shift=3):    """凯撒密码解密"""    return caesar_cipher(text, -shift)text = 'Hello World'encrypted = caesar_cipher(text, 3)print(encrypted)  # 'Khoor Zruog'decrypted = caesar_decipher(encrypted, 3)print(decrypted)  # 'Hello World'