跳至正文

字符串处理

创建字符串​

各种方法​

# 单引号
name = 'Python'

# 双引号
message = "Hello, World!"

# 三引号(多行)
text = """첫 번째 줄
두 번째 줄
세 번째 줄"""

poem = '''장미는 빨갛고
제비꽃은 파랗다'''

# 转义序列
quote = "He said, \"Hello!\""
path = "C:\\Users\\Documents"
new_line = "첫 줄\n두 번째 줄"
tab = "이름\t나이"

# 原始字符串(忽略转义)
path = r"C:\Users\Documents"

字符串索引和切片​

索引​

text = "Python"

# 正索引(从左开始: 0, 1, 2...)
print(text[0])   # P
print(text[1])   # y
print(text[5])   # n

# 负索引(从右开始: -1, -2, -3...)
print(text[-1])  # n
print(text[-2])  # o
print(text[-6])  # P

# 错误
# print(text[10])  # IndexError

切片​

text = "Python Programming"

# [开始:结束] - 不包括结束
print(text[0:6])    # Python
print(text[7:18])   # Programming

# 可以省略
print(text[:6])     # Python(从开始)
print(text[7:])     # Programming(到结束)
print(text[:])      # Python Programming(全部)

# 负索引
print(text[-11:])   # Programming
print(text[:-12])   # Python

# 指定步长 [开始:结束:步长]
print(text[::2])    # Pto rgamn(每2个字符)
print(text[::-1])   # gnimmargorP nohtyP(反转)

# 实用示例
url = "https://www.example.com"
domain = url[8:-4]  # www.example
print(domain)

字符串运算​

连接和重复​

# 连接(+)
first = "Hello"
second = "World"
greeting = first + " " + second
print(greeting)  # Hello World

# 重复(*)
line = "=" * 20
print(line)  # ====================

border = "-" * 10
print(f"{border} 제목 {border}")
# ---------- 제목 ----------

# 连接多个字符串
words = ["Python", "is", "awesome"]
sentence = " ".join(words)
print(sentence)  # Python is awesome

比较​

# 相等/不等
print("hello" == "hello")   # True
print("hello" != "Hello")   # True

# 大小比较(字典序)
print("apple" < "banana")   # True
print("apple" < "Apple")    # False(大写字母在前)

# 成员测试
text = "Python Programming"
print("Python" in text)     # True
print("Java" in text)       # False
print("Java" not in text)   # True

字符串方法​

大小写转换​

text = "Hello, Python!"

print(text.upper())        # HELLO, PYTHON!
print(text.lower())        # hello, python!
print(text.capitalize())   # Hello, python!
print(text.title())        # Hello, Python!
print(text.swapcase())     # hELLO, pYTHON!

# 实用示例 - 规范化用户输入
user_input = "  YES  "
if user_input.strip().lower() == "yes":
    print("확인되었습니다")

搜索和检查​

text = "Python Programming"

# 查找
print(text.find("Python"))      # 0(第一个位置)
print(text.find("Java"))        # -1(未找到)
print(text.index("Programming"))  # 7
# print(text.index("Java"))     # ValueError

# 计数
print(text.count("o"))          # 1
print(text.count("m"))          # 3

# 开始/结束检查
print(text.startswith("Python"))  # True
print(text.endswith("ing"))       # True

# 成员检查
print("gram" in text)            # True

字符类型检查​

# 仅字母
print("abc".isalpha())       # True
print("abc123".isalpha())    # False

# 仅数字
print("123".isdigit())       # True
print("12.3".isdigit())      # False

# 字母数字
print("abc123".isalnum())    # True
print("abc 123".isalnum())   # False

# 仅空白
print("   ".isspace())       # True
print("  a  ".isspace())     # False

# 大写/小写
print("ABC".isupper())       # True
print("abc".islower())       # True

# 实用示例 - 密码验证
password = "Pass123"
has_digit = any(c.isdigit() for c in password)
has_upper = any(c.isupper() for c in password)
has_lower = any(c.islower() for c in password)

if len(password) >= 8 and has_digit and has_upper and has_lower:
    print("강한 비밀번호입니다")

删除空白​

text = "   hello world   "

print(text.strip())    # "hello world"(两侧)
print(text.lstrip())   # "hello world   "(左侧)
print(text.rstrip())   # "   hello world"(右侧)

# 删除特定字符
url = "https://example.com/"
print(url.strip("https://"))  # example.com/
print(url.rstrip("/"))         # https://example.com

# 实用示例 - CSV解析
data = "  홍길동,  25,  서울  "
parts = [part.strip() for part in data.split(",")]
print(parts)  # ['홍길동', '25', '서울']

转换和替换​

text = "Hello, Python!"

# 替换
print(text.replace("Python", "World"))  # Hello, World!
print(text.replace("l", "L"))           # HeLLo, Python!
print(text.replace("l", "L", 1))        # HeLlo, Python!(仅1个)

# 分割
words = text.split(", ")
print(words)  # ['Hello', 'Python!']

csv = "홍길동,25,서울"
data = csv.split(",")
print(data)   # ['홍길동', '25', '서울']

# 连接
words = ["Python", "is", "fun"]
sentence = " ".join(words)
print(sentence)  # Python is fun

# 用特定字符连接
print("-".join(words))  # Python-is-fun

# 分割行
text = """첫 줄
두 번째 줄
세 번째 줄"""
lines = text.splitlines()
print(lines)  # ['첫 줄', '두 번째 줄', '세 번째 줄']

对齐​

# 左对齐
print("Python".ljust(10))      # "Python    "
print("Python".ljust(10, "-")) # "Python----"

# 右对齐
print("Python".rjust(10))      # "    Python"
print("Python".rjust(10, "0")) # "0000Python"

# 居中对齐
print("Python".center(10))     # "  Python  "
print("Python".center(10, "*"))# "**Python**"

# 实用示例 - 表格输出
print("이름".ljust(10) + "나이".rjust(5))
print("홍길동".ljust(10) + "25".rjust(5))
print("김철수".ljust(10) + "30".rjust(5))

字符串格式化​

f-string(Python 3.6+,推荐)​

name = "홍길동"
age = 25
height = 175.5

# 基本使用
print(f"이름: {name}, 나이: {age}")

# 表达式
print(f"내년 나이: {age + 1}")
print(f"키(cm): {height}")

# 格式说明符
price = 1234567
print(f"가격: {price:,}원")        # 가격: 1,234,567원

pi = 3.14159265
print(f"원주율: {pi:.2f}")         # 원주율: 3.14

# 对齐和宽度
print(f"{'Python':>10}")          # "    Python"
print(f"{'Python':<10}")          # "Python    "
print(f"{'Python':^10}")          # "  Python  "
print(f"{'Python':*^10}")         # "**Python**"

# 数字进制
num = 255
print(f"10진수: {num}")           # 10진수: 255
print(f"16진수: {num:x}")         # 16진수: ff
print(f"8진수: {num:o}")          # 8진수: 377
print(f"2진수: {num:b}")          # 2진수: 11111111

format()方法​

# 基于位置
print("이름: {}, 나이: {}".format("홍길동", 25))

# 指定索引
print("{1}, {0}".format("World", "Hello"))  # Hello, World

# 指定名称
print("이름: {name}, 나이: {age}".format(name="홍길동", age=25))

# 指定格式
print("가격: {:,}원".format(1234567))
print("비율: {:.1%}".format(0.856))

%格式化(旧式)​

name = "홍길동"
age = 25

print("이름: %s, 나이: %d" % (name, age))
print("비율: %.2f%%" % 85.678)

实际示例​

电子邮件验证​

def validate_email(email):
    """简单的电子邮件验证"""
    # 检查是否包含@
    if "@" not in email:
        return False

    # 按@分割
    parts = email.split("@")
    if len(parts) != 2:
        return False

    local, domain = parts

    # 验证本地部分和域名
    if not local or not domain:
        return False

    # 检查域名是否包含.
    if "." not in domain:
        return False

    return True

# 测试
emails = [
    "user@example.com",      # ✅
    "invalid.email",         # ❌
    "@example.com",          # ❌
    "user@",                 # ❌
]

for email in emails:
    result = "유효" if validate_email(email) else "무효"
    print(f"{email}: {result}")

文本掩码​

def mask_phone(phone):
    """掩码电话号码"""
    if len(phone) == 11:
        return phone[:3] + "****" + phone[7:]
    elif len(phone) == 10:
        return phone[:3] + "***" + phone[6:]
    return phone

def mask_email(email):
    """掩码电子邮件"""
    local, domain = email.split("@")
    if len(local) <= 2:
        masked_local = local[0] + "*"
    else:
        masked_local = local[0] + "*" * (len(local) - 2) + local[-1]
    return f"{masked_local}@{domain}"

# 使用
print(mask_phone("01012345678"))    # 010****5678
print(mask_email("hong@example.com"))  # h**g@example.com

字符串分析器​

def analyze_string(text):
    """详细的字符串分析"""
    return {
        "길이": len(text),
        "단어수": len(text.split()),
        "대문자": sum(1 for c in text if c.isupper()),
        "소문자": sum(1 for c in text if c.islower()),
        "숫자": sum(1 for c in text if c.isdigit()),
        "공백": sum(1 for c in text if c.isspace()),
        "특수문자": sum(1 for c in text if not c.isalnum() and not c.isspace())
    }

text = "Hello Python 2024! Welcome to coding."
result = analyze_string(text)

print("=== 문자열 분석 ===")
for key, value in result.items():
    print(f"{key}: {value}")

URL解析器​

def parse_url(url):
    """解析URL"""
    # 分离协议
    if "://" in url:
        protocol, rest = url.split("://", 1)
    else:
        protocol = "http"
        rest = url

    # 分离路径
    if "/" in rest:
        domain, path = rest.split("/", 1)
        path = "/" + path
    else:
        domain = rest
        path = "/"

    # 分离端口
    if ":" in domain:
        domain, port = domain.split(":")
    else:
        port = "80" if protocol == "http" else "443"

    return {
        "프로토콜": protocol,
        "도메인": domain,
        "포트": port,
        "경로": path
    }

url = "https://www.example.com:8080/api/users"
result = parse_url(url)

for key, value in result.items():
    print(f"{key}: {value}")

Unicode和编码​

使用Unicode​

# 韩文
text = "안녕하세요"
print(len(text))  # 5

# 表情符号
emoji = "😀🎉"
print(len(emoji))  # 2

# Unicode码点
print(ord("A"))      # 65
print(chr(65))       # A
print(ord("가"))     # 44032
print(chr(44032))    # 가

编码/解码​

text = "안녕하세요"

# 编码(字符串→字节)
utf8_bytes = text.encode("utf-8")
print(utf8_bytes)  # b'\xec\x95\x88\xeb\x85\x95...'

euckr_bytes = text.encode("euc-kr")
print(euckr_bytes)

# 解码(字节→字符串)
decoded = utf8_bytes.decode("utf-8")
print(decoded)  # 안녕하세요

常见问题​

Q1. 字符串是不可变的吗?​

A: 是的,字符串是不可变的(immutable)。

text = "hello"
# text[0] = "H"  # ❌ TypeError

# 创建新字符串
text = "H" + text[1:]  # ✅ "Hello"

Q2. +与join,哪个更快?​

A: 连接许多字符串时join更快。

# ❌ 慢(创建许多字符串)
result = ""
for i in range(1000):
    result += str(i)

# ✅ 快
result = "".join(str(i) for i in range(1000))

Q3. 如何处理多行字符串中的缩进?​

A: 使用textwrap模块

from textwrap import dedent

text = dedent("""
    첫 번째 줄
    두 번째 줄
    세 번째 줄
""").strip()

print(text)
# 첫 번째 줄
# 두 번째 줄
# 세 번째 줄

Q4. 需要正则表达式吗?​

A: 对于复杂的模式匹配是必需的。

import re

# 简单情况:字符串方法
email = "user@example.com"
if "@" in email and "." in email:
    print("이메일 형식")

# 复杂情况:正则表达式
pattern = r"^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$"
if re.match(pattern, email):
    print("유효한 이메일")

下一步​

您已经掌握了字符串处理!

要点总结:
✅ 索引和切片
✅ 各种字符串方法
✅ 字符串格式化(f-string)
✅ 搜索、转换、验证
✅ 实际示例

下一步: 在列表和元组中学习集合!