Python字符串操作：常用方法和高级技巧

# 使用单引号或双引号
s1 = 'Hello'
s2 = "World"

# 使用三引号创建多行字符串
s3 = '''This is a
multi-line string'''

# 使用转义字符
s4 = 'It\'s a beautiful day'

# 原始字符串，忽略转义字符
s5 = r'C:\Users\Username\Documents'

# 字节字符串
s6 = b'Hello'  # 只包含ASCII字符

# 使用str()函数
s7 = str(42)  # 将其他类型转换为字符串

# 使用 + 运算符
first_name = 'John'
last_name = 'Doe'
full_name = first_name + ' ' + last_name  # 'John Doe'

# 使用 += 运算符
greeting = 'Hello'
greeting += ' World'  # 'Hello World'

# 使用 join() 方法
words = ['Python', 'is', 'awesome']
sentence = ' '.join(words)  # 'Python is awesome'

# 使用格式化字符串
name = 'Alice'
age = 30
info = f'{name} is {age} years old'  # 'Alice is 30 years old'

# 使用 str.format() 方法
template = '{} is {} years old'
info = template.format(name, age)  # 'Alice is 30 years old'

laugh = 'Ha' * 3  # 'HaHaHa'
line = '-' * 20   # '--------------------'

text = 'Hello, World!'
length = len(text)  # 13

s = 'Python Programming'

# 索引（正向和反向）
print(s[0])    # 'P'
print(s[-1])   # 'g'

# 基本切片
print(s[7:18])  # 'Programming'
print(s[:6])    # 'Python'
print(s[7:])    # 'Programming'

# 带步长的切片
print(s[::2])   # 'Pto rgamn'
print(s[::-1])  # 'gnimmargorP nohtyP' (反转字符串)

# 使用切片修改字符串
new_s = s[:6] + ' is ' + s[7:]  # 'Python is Programming'

s = 'Hello, World!'

print(s.upper())       # 'HELLO, WORLD!'
print(s.lower())       # 'hello, world!'
print(s.capitalize())  # 'Hello, world!'
print(s.title())       # 'Hello, World!'
print(s.swapcase())    # 'hELLO, wORLD!'

# 检查大小写
print('HELLO'.isupper())  # True
print('hello'.islower())  # True
print('Title Case'.istitle())  # True

s = 'Python is amazing and Python is powerful'

# 查找
print(s.find('Python'))      # 0
print(s.find('Python', 10))  # 25 (从索引10开始查找)
print(s.rfind('Python'))     # 25 (从右侧开始查找)

# index() 方法类似于 find()，但在未找到时会引发 ValueError
try:
    print(s.index('Java'))
except ValueError:
    print("'Java' not found in the string")

# 计数
print(s.count('Python'))  # 2

# 替换
print(s.replace('Python', 'Java'))  # 'Java is amazing and Java is powerful'
print(s.replace('Python', 'Java', 1))  # 'Java is amazing and Python is powerful'

# 分割
s = 'apple,banana,orange,grape'
fruits = s.split(',')  # ['apple', 'banana', 'orange', 'grape']

# 限制分割次数
print('a,b,c,d'.split(',', 2))  # ['a', 'b', 'c,d']

# 按行分割
multiline = '''Line 1
Line 2
Line 3'''
lines = multiline.splitlines()  # ['Line 1', 'Line 2', 'Line 3']

# 连接
new_s = '-'.join(fruits)  # 'apple-banana-orange-grape'

# 使用空字符串连接
letters = ['H', 'e', 'l', 'l', 'o']
word = ''.join(letters)  # 'Hello'

s = '   Hello, World!   '

print(s.strip())    # 'Hello, World!'
print(s.lstrip())   # 'Hello, World!   '
print(s.rstrip())   # '   Hello, World!'

# 去除指定字符
s = '...Python...'
print(s.strip('.'))   # 'Python'
print(s.lstrip('.'))  # 'Python...'
print(s.rstrip('.'))  # '...Python'

s = 'Python'

print(s.ljust(10))        # 'Python    '
print(s.rjust(10))        # '    Python'
print(s.center(10))       # '  Python  '

# 使用指定字符填充
print(s.ljust(10, '-'))   # 'Python----'
print(s.rjust(10, '*'))   # '****Python'
print(s.center(10, '='))  # '==Python=='

# 使用 zfill() 在数字字符串左边填充零
print('42'.zfill(5))      # '00042'

name = 'Alice'
age = 30

print('My name is %s and I am %d years old.' % (name, age))
# 'My name is Alice and I am 30 years old.'

# 使用字典
print('%(name)s is %(age)d years old.' % {'name': 'Bob', 'age': 25})
# 'Bob is 25 years old.'

print('My name is {} and I am {} years old.'.format(name, age))
# 'My name is Alice and I am 30 years old.'

# 使用索引
print('The {1} {0} {2}'.format('brown', 'quick', 'fox'))
# 'The quick brown fox'

# 使用命名参数
print('The {adj} {noun}'.format(adj='happy', noun='programmer'))
# 'The happy programmer'

# 格式化选项
pi = 3.14159
print('Pi is approximately {:.2f}'.format(pi))  # 'Pi is approximately 3.14'

name = 'Charlie'
age = 35
print(f'My name is {name} and I am {age} years old.')
# 'My name is Charlie and I am 35 years old.'

# 在f-string中使用表达式
print(f'2 + 2 = {2 + 2}')  # '2 + 2 = 4'

# 格式化选项
import datetime
now = datetime.datetime.now()
print(f'Current time: {now:%Y-%m-%d %H:%M:%S}')
# 例如：'Current time: 2023-04-13 15:30:45'

# 字典序比较
print('apple' < 'banana')  # True
print('Python' == 'python')  # False

# 忽略大小写比较
s1 = 'python'
s2 = 'PYTHON'
print(s1.lower() == s2.lower())  # True

text = 'Python is amazing'
print('Python' in text)  # True
print('Java' not in text)  # True

filename = 'document.txt'
print(filename.startswith('doc'))  # True
print(filename.endswith('.txt'))  # True

# 使用元组检查多个选项
print(filename.endswith(('.txt', '.pdf', '.doc')))  # True

# 转换为字节
s = 'Hello, World!'
b = s.encode('utf-8')
print(b)  # b'Hello, World!'

# 从字节转换回字符串
s2 = b.decode('utf-8')
print(s2)  # 'Hello, World!'

# 处理不同编码
s_unicode = '你好，世界！'
b_gbk = s_unicode.encode('gbk')
s_from_gbk = b_gbk.decode('gbk')
print(s_from_gbk)  # '你好，世界！'

import re

text = "The quick brown fox jumps over the lazy dog"

# 查找所有单词
words = re.findall(r'\w+', text)
print(words)  # ['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog']

# 替换
new_text = re.sub(r'fox', 'cat', text)
print(new_text)  # "The quick brown cat jumps over the lazy dog"

# 分割
parts = re.split(r'\s+', text)
print(parts)  # ['The', 'quick', 'brown', 'fox', 'jumps', 'over', 'the', 'lazy', 'dog']

# 示例：高效地构建大字符串
def build_string(n):
    parts = []
    for i in range(n):
        parts.append(f"Part {i}")
    return ' '.join(parts)

large_string = build_string(10000)