Python运算符详解与编码基础详解

# 算术运算符示例
a = 10
b = 3
print(a + b)   # 加法：13
print(a - b)   # 减法：7
print(a * b)   # 乘法：30
print(a / b)   # 除法：3.333...
print(a // b)  # 整除：3
print(a % b)   # 取模（求余）：1
print(a ** b)  # 幂运算：1000

# 比较运算符示例
x = 5
y = 10
print(x == y)   # 等于：False
print(x != y)   # 不等于：True
print(x > y)    # 大于：False
print(x < y)    # 小于：True
print(x >= y)   # 大于等于：False
print(x <= y)   # 小于等于：True

# 赋值运算符示例
c = 5      # 基本赋值
c += 3     # 等价于 c = c + 3，结果 c = 8
c -= 2     # 等价于 c = c - 2，结果 c = 6
c *= 4     # 等价于 c = c * 4，结果 c = 24
c /= 3     # 等价于 c = c / 3，结果 c = 8.0
c //= 2    # 等价于 c = c // 2，结果 c = 4.0
c %= 3     # 等价于 c = c % 3，结果 c = 1.0
c **= 2    # 等价于 c = c ** 2，结果 c = 1.0

# 逻辑运算符示例
age = 25
has_license = True
and：两个条件都为真时返回真
can_drive = (age >= 18) and has_license  # True
or：至少一个条件为真时返回真
is_teenager = (age >= 13) or (age <= 19)  # True
not：反转布尔值
is_child = not (age >= 18)  # False

# 位运算符示例
m = 10  # 二进制：1010
n = 4   # 二进制：0100
print(m & n)   # 按位与：0  (0000)
print(m | n)   # 按位或：14 (1110)
print(m ^ n)   # 按位异或：14 (1110)
print(~m)      # 按位取反：-11
print(m << 1)  # 左移一位：20 (10100)
print(m >> 1)  # 右移一位：5  (0101)

# 成员运算符示例
fruits = ["apple", "banana", "cherry"]
text = "Hello World"
print("banana" in fruits)      # True
print("orange" not in fruits)  # True
print("World" in text)         # True
print("Python" not in text)    # True

# 身份运算符示例
list1 = [1, 2, 3]
list2 = [1, 2, 3]
list3 = list1
print(list1 is list2)      # False，值相同但不是同一个对象
print(list1 is list3)      # True，指向同一个对象
print(list1 is not list2)  # True

# Python 3 默认使用 UTF-8 编码
# 可以在文件开头指定编码方式
# -*- coding: utf-8 -*-
包含中文的字符串
chinese_text = "你好，世界！"
print(chinese_text)  # 正常输出：你好，世界！

# 字符串与字节的转换
text = "Python编程"
byte_data = text.encode('utf-8')  # 编码为UTF-8字节
print(byte_data)  # b'Python\xe7\xbc\x96\xe7\xa8\x8b'
decoded_text = byte_data.decode('utf-8')  # 解码为字符串
print(decoded_text)  # Python编程
查看系统默认编码
import sys
print(sys.getdefaultencoding())  # 通常输出：utf-8

# 写入文件（指定编码）
with open('example.txt', 'w', encoding='utf-8') as f:
    f.write("这是UTF-8编码的中文文本")
读取文件（指定相同编码）
with open('example.txt', 'r', encoding='utf-8') as f:
content = f.read()
print(content)  # 这是UTF-8编码的中文文本
处理不同编码的文件
with open('gbk_file.txt', 'r', encoding='gbk') as f:
gbk_content = f.read()
print(gbk_content)

# 1. 编码错误处理
try:
    with open('file.txt', 'r', encoding='utf-8') as f:
        content = f.read()
except UnicodeDecodeError as e:
    print(f"编码错误：{e}")
    # 尝试其他编码
    with open('file.txt', 'r', encoding='gbk') as f:
        content = f.read()
2. 忽略无法解码的字符
with open('file.txt', 'r', encoding='utf-8', errors='ignore') as f:
content = f.read()
3. 替换无法解码的字符
with open('file.txt', 'r', encoding='utf-8', errors='replace') as f:
content = f.read()
4. 检测文件编码（需要安装chardet库）
pip install chardet
import chardet
with open('unknown.txt', 'rb') as f:
raw_data = f.read()
result = chardet.detect(raw_data)
print(f"检测到的编码：{result['encoding']}")
print(f"置信度：{result['confidence']}")