从基础到进阶详解Python中字符串分割的常见方法

str.split(sep=None, maxsplit=-1)

s = "apple banana orange"
print(s.split())  # 默认按空格分割
# 输出: ['apple', 'banana', 'orange']

s = "apple,banana,orange"
print(s.split(','))  # 按逗号分割
# 输出: ['apple', 'banana', 'orange']

s = "apple,banana,orange,grape"
print(s.split(',', maxsplit=2))  # 最多分割2次
# 输出: ['apple', 'banana', 'orange,grape']

s = "apple,banana,orange,grape"
print(s.rsplit(',', maxsplit=1))  # 从右向左最多分割1次
# 输出: ['apple,banana,orange', 'grape']

str.partition(sep)

s = "apple,banana,orange"
left, sep, right = s.partition(',')
print(left, sep, right)
# 输出: apple , banana,orange

s = "Hello\nWorld\nPython"
print(s.splitlines())
# 输出: ['Hello', 'World', 'Python']

import re
re.split(pattern, string, maxsplit=0, flags=0)

import re

s = "apple,banana;orange|grape"
parts = re.split(r'[,;|]', s)  # 按逗号、分号、竖线分割
print(parts)
# 输出: ['apple', 'banana', 'orange', 'grape']

s = "apple   banana  orange"
parts = re.split(r'\s+', s)  # 按1个或多个空格分割
print(parts)
# 输出: ['apple', 'banana', 'orange']

s = "appleDBbananaDBorange"
parts = re.split(r'(DB)', s)  # 使用捕获组 (DB) 保留分隔符
print(parts)
# 输出: ['apple', 'DB', 'banana', 'DB', 'orange']

s = "appleDBbananaDBorange"
parts = [part for part in re.split(r'(DB)', s) if part != 'DB']  # 过滤掉 DB
print(parts)
# 输出: ['apple', 'banana', 'orange']

import re

csv_data = "Name,Age,City\nAlice,25,New York\nBob,30,London"
lines = csv_data.splitlines()  # 按行分割
for line in lines[1:]:  # 跳过标题行
    fields = re.split(r',(?=(?:[^\"]*\"[^\"]*\")*[^\"]*$)', line)  # 处理带引号的CSV
    print(fields)
# 输出:
# ['Alice', '25', 'New York']
# ['Bob', '30', 'London']

import re

url = "https://www.example.com/search?q=python&lang=en&page=1"
query = url.split('?')[1]  # 提取查询部分
params = re.split(r'&', query)  # 按 & 分割参数
print(params)
# 输出: ['q=python', 'lang=en', 'page=1']

log = "2023-01-01 12:00:00 ERROR: File not found"
date, time, level, message = log.split(' ', maxsplit=3)  # 最多分割3次
print(date, time, level, message)
# 输出: 2023-01-01 12:00:00 ERROR: File not found