正则表达式核心语法以及Python的re库中常用方法总结

# match()方法错误示范
text = "邮箱：user.LiLi-103@example.com"
email_pattern = r'^[a-zA-Z0-9.-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
res = re.match(email_pattern, text)
if res:
    print(res.group())   
# 没有输出，因为文本开头是邮箱，而match()方法只从字符串开头匹配正则表达式，res为None
# match()方法正确使用：修改text，或使用search（）方法
text = "user.LiLi-103@example.com"
email_pattern = r'^[a-zA-Z0-9.-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
res = re.match(email_pattern, text)
if res:
    print(res.group())  
# 输出为：user.LiLi-103@example.com

# search（）
text = "abc123def456"
result = re.search(r'\d+', text)  # 查找第一个数字序列
if result:
    print("找到数字:", result.group())  # 输出: 123
else:
    print("未找到数字")

# findall（）
text = "a156b22c333d"
results = re.findall(r'\d+', text)  # 查找所有数字序列
print("所有数字:", results)  # 输出: ['156', '22', '333']

import re
# 替换所有匹配项
text = "Python is great. Python is easy."
result = re.sub(r'Python', 'Java', text)  
print(result)  
# 输出: "Java is great. Java is easy."
# 只替换第一个
result = re.sub(r'Python', 'Java', text, count=1)  
print(result)  
# 输出: "Java is great. Python is easy."

text = "apple?banana,cherry.egg right"
result = re.split(r'[,.? ]', text)  # 按[,.? ]分割
print(result)  
# 输出: ['apple', 'banana', 'cherry', 'egg']
result = re.split(r'[,.? ]', text, maxsplit=1)  # 只分割一次
print(result)  
# 输出: ['apple', 'banana,cherry.egg right']