Python字符串替换：str.replace()完全指南及进阶方法

text = "Hello World, Hello Python, Hello Everyone"
 
# 替换所有出现
print(text.replace("Hello", "Hi"))
# Hi World, Hi Python, Hi Everyone
 
# 仅替换前2次出现
print(text.replace("Hello", "Hi", 2))
# Hi World, Hi Python, Hello Everyone
 
# 删除子字符串（替换为空字符串）
messy = "  extra   spaces   here  "
print(messy.replace(" ", ""))
# extraspaceshere

original = "Python is great"
new = original.replace("great", "awesome")
print(original)  # Python is great（未改变）
print(new)       # Python is awesome

import re
 
text = "Python is Great, python is Fun, PYTHON is Everywhere"
 
# 不区分大小写替换
result = re.sub(r'python', 'Java', text, flags=re.IGNORECASE)
print(result)
# Java is Great, Java is Fun, Java is Everywhere

import re
 
# 将数字替换为'#'
text = "Call 555-1234 or 555-5678"
print(re.sub(r'\d', '#', text))
# Call ###-#### or ###-####
 
# 替换完整的电话号码
print(re.sub(r'\d{3}-\d{4}', '[已脱敏]', text))
# Call [已脱敏] or [已脱敏]
 
# 将多个空格替换为单个空格
messy = "too    many     spaces   here"
print(re.sub(r'\s+', ' ', messy))
# too many spaces here

import re
 
# 交换姓和名
names = "Smith, John\nDoe, Jane\nBrown, Bob"
swapped = re.sub(r'(\w+), (\w+)', r'\2 \1', names)
print(swapped)
# John Smith
# Jane Doe
# Bob Brown
 
# 为日期添加格式
dates = "Meeting on 2026-02-10 and 2026-03-15"
formatted = re.sub(r'(\d{4})-(\d{2})-(\d{2})', r'\2/\3/\1', dates)
print(formatted)
# Meeting on 02/10/2026 and 03/15/2026

import re
 
def censor_word(match):
    word = match.group()
    return word[0] + '*' * (len(word) - 1)
 
text = "The password is secret and the code is hidden"
censored = re.sub(r'secret|hidden', censor_word, text)
print(censored)
# The password is s***** and the code is h*****

import re
 
# 仅对特定单词转换为标题大写
def smart_capitalize(match):
    word = match.group()
    minor_words = {'a', 'an', 'the', 'and', 'or', 'but', 'in', 'on', 'at', 'to'}
    if word.lower() in minor_words:
        return word.lower()
    return word.capitalize()
 
title = "the quick BROWN fox AND the lazy DOG"
result = re.sub(r'\b\w+\b', smart_capitalize, title)
print(result)
# the Quick Brown Fox and the Lazy Dog

text = "Hello World! How are you?"
result = text.replace("Hello", "Hi").replace("World", "Earth").replace("you", "they")
print(result)  # Hi Earth! How are they?

import re
 
def multi_replace(text, replacements):
    """使用字典替换多个子字符串。"""
    pattern = re.compile('|'.join(re.escape(k) for k in replacements))
    return pattern.sub(lambda m: replacements[m.group()], text)
 
text = "The cat sat on the mat with another cat"
replacements = {
    'cat': 'dog',
    'mat': 'rug',
    'sat': 'stood',
}
 
print(multi_replace(text, replacements))
# The dog stood on the rug with another dog

# 替换字符: a->@, e->3, o->0
table = str.maketrans('aeo', '@30')
text = "Hello World"
print(text.translate(table))
# H3ll0 W0rld
 
# 删除特定字符
remove_vowels = str.maketrans('', '', 'aeiouAEIOU')
print("Hello World".translate(remove_vowels))
# Hll Wrld
 
# 一次调用中同时替换和删除
table = str.maketrans({'a': '@', 'e': '3', ' ': None})
print("apple pie".translate(table))
# @ppl3pi3

import re
 
def clean_text(text):
    """规范化文本以进行处理。"""
    text = text.strip()
    text = re.sub(r'\s+', ' ', text)           # 合并空白
    text = re.sub(r'[^\w\s.,!?-]', '', text)   # 删除特殊字符
    text = text.lower()
    return text
 
raw = "  Hello!!!   This is    MESSY @#$ text...  "
print(clean_text(raw))
# hello!!! this is messy text...

template = "Dear {name}, your order #{order_id} ships on {date}."
 
data = {
    'name': 'Alice',
    'order_id': '12345',
    'date': 'Feb 15, 2026',
}
 
# 使用str.format_map（比手动替换更好）
result = template.format_map(data)
print(result)
# Dear Alice, your order #12345 ships on Feb 15, 2026.

import re
 
def redact_pii(text):
    """脱敏邮箱、电话号码和SSN。"""
    text = re.sub(r'\b[\w.]+@[\w.]+\.\w+\b', '[邮箱]', text)
    text = re.sub(r'\b\d{3}[-.]?\d{3}[-.]?\d{4}\b', '[电话]', text)
    text = re.sub(r'\b\d{3}-\d{2}-\d{4}\b', '[SSN]', text)
    return text
 
msg = "Contact john@example.com or call 555-123-4567. SSN: 123-45-6789"
print(redact_pii(msg))
# Contact [邮箱] or call [电话]. SSN: [SSN]