Python：bz2 库高级用法举例和应用详解

import bz2

# 原始字符串数据
data = "This is a string to be compressed using bz2."
# 压缩数据
compressed_data = bz2.compress(data.encode('utf-8'))  # 将字符串编码为字节，再进行压缩
print(f"Compressed Data: {compressed_data}")

# 解压缩数据
decompressed_data = bz2.decompress(compressed_data).decode('utf-8')  # 解压缩后再解码为字符串
print(f"Decompressed Data: {decompressed_data}")

import bz2

# 压缩文件
def compress_file(input_file, output_file):
    with open(input_file, 'rb') as file_in:
        with bz2.BZ2File(output_file, 'wb') as file_out:
            file_out.write(file_in.read())  # 读取原文件数据并写入压缩文件

compress_file('example.txt', 'example.txt.bz2')  # 压缩example.txt文件

# 解压缩文件
def decompress_file(input_file, output_file):
    with bz2.BZ2File(input_file, 'rb') as file_in:
        with open(output_file, 'wb') as file_out:
            file_out.write(file_in.read())  # 读取压缩文件数据并写入解压缩后的文件

decompress_file('example.txt.bz2', 'example_decompressed.txt')  # 解压缩example.txt.bz2文件

import bz2

# 创建压缩器和解压缩器对象
compressor = bz2.BZ2Compressor()
decompressor = bz2.BZ2Decompressor()

# 待压缩的字符串数据
data = "This string will be compressed in chunks using bz2."

# 分块压缩数据
chunk_size = 10
compressed_chunks = []
for i in range(0, len(data), chunk_size):
    chunk = data[i:i + chunk_size].encode('utf-8')  # 将字符串块编码为字节
    compressed_chunks.append(compressor.compress(chunk))  # 压缩块并添加到压缩块列表中
compressed_chunks.append(compressor.flush())  # 刷新最后的压缩数据
compressed_data = b''.join(compressed_chunks)
print(f"Compressed Data: {compressed_data}")

# 分块解压缩数据
decompressed_chunks = []
index = 0
while index < len(compressed_data):
    chunk = compressed_data[index:index + chunk_size * 2]  # 假设每个块大小不超过原始块 * 2
    decompressed_chunks.append(decompressor.decompress(chunk))  # 解压缩块并添加到解压缩块列表中
    index += chunk_size * 2
decompressed_data = b''.join(decompressed_chunks).decode('utf-8')  # 将解压缩块连接起来并解码为字符串
print(f"Decompressed Data: {decompressed_data}")