基于python实现的高效文件压缩工具：Zstandard、LZ4、Brotli 一站式解决方案

文件压缩已成为提升存储效率、加速网络传输的核心技术。本文介绍一款基于python与Streamlit库构建的多功能压缩工具，支持 Zstandard、LZ4、Brotli 等主流算法，满足不同场景下的性能需求。

多算法支持Zstandard

(Zstd)：压缩比与速度的黄金平衡

LZ4：极致的压缩速度（最高可达 500MB/s）

Brotli：Web 压缩标准（适合文本/HTML 压缩）

Gzip：兼容性最强的通用压缩算法

可以自动识别之前压缩的压缩格式（.zst/.lz4/.gz/.br），进行解压缩，实时压缩时间的一个大概估算，可以尝试调整压缩等级进行控制压缩文件的大小。

大概的使用流程：

步骤1：上传文件

支持任意格式文件（文档/图片/视频等）

实时显示文件大小（精确到 KB 级）

步骤2：算法选择

Zstandard：推荐压缩级别 3-6（平衡性能）

LZ4：压缩级别 1（极速）或 9（高压缩）

Brotli：压缩级别 11（最高质量）

Gzip：压缩级别 6（推荐）

步骤3：执行压缩

实时进度条（显示压缩进度）

压缩比动态显示（百分比计算）

import streamlit as st
import pyzstd
import lz4.frame
import gzip
import brotli
import io
import os
import time
from pathlib import Path
import math
import humanize# 设置页面标题和图标
st.set_page_config(page_title="高级文件压缩工具箱",page_icon="📦",layout="wide"
)# 压缩算法详细信息
COMPRESSION_INFO = {"Zstandard": {"extension": "zst","description": "Zstandard (Zstd) 是Facebook开发的高压缩比算法，提供极高的压缩和解压速度","recommended_levels": "1-22 (推荐3-5)","best_for": "大型文件，需要快速压缩和解压的场景","default_level": 3,"min_level": 1,"max_level": 22},"LZ4": {"extension": "lz4","description": "LZ4 是速度最快的压缩算法，提供极快的压缩和解压速度","recommended_levels": "1-16 (推荐1-4)","best_for": "实时数据流，需要极速压缩的场景","default_level": 1,"min_level": 1,"max_level": 16},"Gzip": {"extension": "gz","description": "Gzip 是应用最广泛的压缩算法，兼容性强","recommended_levels": "0-9 (推荐6-9)","best_for": "网络传输，需要高兼容性的场景","default_level": 6,"min_level": 0,"max_level": 9},"Brotli": {"extension": "br","description": "Brotli 是Google开发的算法，提供最高的压缩比","recommended_levels": "0-11 (推荐9-11)","best_for": "网页内容，需要最大压缩比的场景","default_level": 9,"min_level": 0,"max_level": 11}
}# 侧边栏说明
st.sidebar.title("📦 高级文件压缩工具箱")
st.sidebar.markdown("""
## 支持的压缩格式：
- Zstandard (.zst)
- LZ4 (.lz4)
- Gzip (.gz)
- Brotli (.br)
""")
st.sidebar.markdown("""
## 使用提示：
1. 压缩大型文件（100MB+）时建议使用Zstd
2. 需要最高压缩比时使用Brotli
3. 需要最快速度时使用LZ4
4. 需要兼容性时使用Gzip
""")def get_safe_level(algorithm, level):"""确保压缩级别在有效范围内"""min_level = COMPRESSION_INFO[algorithm]["min_level"]max_level = COMPRESSION_INFO[algorithm]["max_level"]return max(min_level, min(max_level, level))def compress_zstandard(data, level=3):"""使用Zstandard压缩数据"""safe_level = get_safe_level("Zstandard", level)return pyzstd.compress(data, safe_level)def decompress_zstandard(data):"""使用Zstandard解压数据"""return pyzstd.decompress(data)def compress_lz4(data, level=1):"""使用LZ4压缩数据"""safe_level = get_safe_level("LZ4", level)return lz4.frame.compress(data, compression_level=safe_level)def decompress_lz4(data):"""使用LZ4解压数据"""return lz4.frame.decompress(data)def compress_gzip(data, level=6):"""使用Gzip压缩数据"""safe_level = get_safe_level("Gzip", level)buf = io.BytesIO()with gzip.GzipFile(fileobj=buf, mode='wb', compresslevel=safe_level) as f:f.write(data)return buf.getvalue()def decompress_gzip(data):"""使用Gzip解压数据"""with gzip.GzipFile(fileobj=io.BytesIO(data)) as f:return f.read()def compress_brotli(data, level=9):"""使用Brotli压缩数据"""safe_level = get_safe_level("Brotli", level)return brotli.compress(data, quality=safe_level)def decompress_brotli(data):"""使用Brotli解压数据"""return brotli.decompress(data)def get_extension(filename):"""获取文件扩展名（不带点）"""return Path(filename).suffix[1:].lower()def get_mime_type(filename):"""根据文件扩展名获取MIME类型"""extension = Path(filename).suffix.lower()if extension in ['.txt', '.csv', '.log', '.json']:return 'text/plain'elif extension in ['.jpg', '.jpeg']:return 'image/jpeg'elif extension == '.png':return 'image/png'elif extension == '.pdf':return 'application/pdf'elif extension == '.zip':return 'application/zip'else:return 'application/octet-stream'def process_file(uploaded_file, action, algorithm=None, level=None, original_filename=None):"""处理文件压缩/解压操作"""file_data = uploaded_file.getvalue()file_size = len(file_data)max_file_size = 200 * 1024 * 1024  # 200MB# 显示处理进度progress_bar = st.progress(0)status_text = st.empty()# 大文件处理if file_size > max_file_size:status_text.warning(f"文件较大（{humanize.naturalsize(file_size)}），处理可能需要较长时间...")def update_progress(percent):progress_bar.progress(percent)if percent < 100:status_text.text(f"处理中: {percent:.0f}%")# 处理压缩操作if action == "压缩":output_filename = f"{Path(uploaded_file.name).stem}.{COMPRESSION_INFO[algorithm]['extension']}"# 估算压缩时间和大小（基于文件大小和算法）estimation_factor = {"Zstandard": 0.0001 * level + 0.00005,"LZ4": 0.00003 * level + 0.00001,"Gzip": 0.0002 * level + 0.0001,"Brotli": 0.0005 * level + 0.0002}estimated_time = file_size * estimation_factor[algorithm]st.info(f"预计压缩时间: {estimated_time:.2f}秒")start_time = time.time()if algorithm == "Zstandard":processed_data = compress_zstandard(file_data, level)elif algorithm == "LZ4":processed_data = compress_lz4(file_data, level)elif algorithm == "Gzip":processed_data = compress_gzip(file_data, level)elif algorithm == "Brotli":processed_data = compress_brotli(file_data, level)else:raise ValueError(f"不支持的格式: {algorithm}")end_time = time.time()actual_time = end_time - start_time# 在压缩数据前加上原始文件名header = f"ORIGINAL_FILENAME:{uploaded_file.name}\n".encode('utf-8')processed_data = header + processed_datacompression_ratio = (1 - len(processed_data) / file_size) * 100return output_filename, processed_data, actual_time, compression_ratio, None# 处理解压操作elif action == "解压":# 检查是否有原始文件名信息filename_header = b"ORIGINAL_FILENAME:"if file_data.startswith(filename_header):header_end = file_data.find(b"\n")original_filename = file_data[len(filename_header):header_end].decode('utf-8')file_data = file_data[header_end+1:]file_ext = get_extension(uploaded_file.name)start_time = time.time()if file_ext == "zst":processed_data = decompress_zstandard(file_data)elif file_ext == "lz4":processed_data = decompress_lz4(file_data)elif file_ext == "gz":processed_data = decompress_gzip(file_data)elif file_ext == "br":processed_data = decompress_brotli(file_data)else:st.error("无法检测压缩格式!")return None, None, None, None, Noneend_time = time.time()actual_time = end_time - start_time# 使用原始文件名（如果存在）或生成新文件名if original_filename:output_filename = original_filenameelse:# 移除所有已知压缩后缀base_name = Path(uploaded_file.name).stemwhile base_name.lower().endswith(('.zst', '.lz4', '.gz', '.br')):base_name = Path(base_name).stemoutput_filename = base_namereturn output_filename, processed_data, actual_time, None, len(processed_data)def main():st.title("📦 高级文件压缩/解压工具箱")# 创建标签页tab_compress, tab_decompress, tab_info = st.tabs(["压缩文件", "解压文件", "压缩算法说明"])# 算法信息页面with tab_info:st.subheader("压缩算法对比指南")cols = st.columns(4)for i, (algo, info) in enumerate(COMPRESSION_INFO.items()):with cols[i]:st.markdown(f"### {algo}")st.markdown(f"**文件后缀**: .{info['extension']}")st.markdown(f"**压缩级别**: {info['recommended_levels']}")st.markdown(f"**最佳适用**: {info['best_for']}")st.info(info['description'])st.subheader("性能对比")st.image("https://raw.githubusercontent.com/facebook/zstd/dev/doc/images/Cspeed2.png", caption="Zstandard压缩性能对比", width=600)st.image("https://cran.r-project.org/web/packages/brotli/vignettes/compression-comparison.png",caption="Brotli压缩比对比", width=600)st.markdown("""**性能总结**:- ⚡ **最快速度**: LZ4- 🗜️ **最高压缩比**: Brotli (高质量)- ⚖️ **最佳平衡**: Zstandard- 🔌 **最广泛兼容**: Gzip""")# 压缩页面with tab_compress:st.subheader("压缩文件")with st.expander("上传说明", expanded=True):st.info("1. 上传需要压缩的文件（支持任何格式）\n2. 选择压缩算法和压缩级别\n3. 点击压缩按钮")uploaded_file = st.file_uploader("选择要压缩的文件", type=None, key="compress")if uploaded_file:file_size = len(uploaded_file.getvalue())st.success(f"已上传文件: {uploaded_file.name} ({humanize.naturalsize(file_size)})")# 选择压缩算法algorithm = st.selectbox("选择压缩算法",list(COMPRESSION_INFO.keys()),key="algo_select",help="选择合适的压缩算法：LZ4速度最快，Brotli压缩比最高")# 显示算法详情algo_info = COMPRESSION_INFO[algorithm]with st.expander(f"{algorithm}算法详情", expanded=True):st.markdown(f"**描述**: {algo_info['description']}")st.markdown(f"**推荐压缩级别**: {algo_info['recommended_levels']}")st.markdown(f"**最佳适用场景**: {algo_info['best_for']}")# 压缩级别滑块level = st.slider("压缩级别", algo_info["min_level"], algo_info["max_level"], value=algo_info["default_level"],key="comp_level",help="级别越高压缩比越大，但需要更多时间和资源")# 压缩估算if st.button("估算压缩效果", key="estimate"):# 简化的估算逻辑（实际压缩比会因文件类型而异）estimation_ratios = {"Zstandard": max(5, 100 - level * 3),"LZ4": max(10, 100 - level * 2),"Gzip": max(15, 100 - level * 4),"Brotli": max(20, 100 - level * 5)}estimated_ratio = estimation_ratios[algorithm]estimated_size = math.ceil(file_size * (estimated_ratio/100))st.info(f"估算压缩效果：压缩到 {humanize.naturalsize(estimated_size)} (压缩比约{100-estimated_ratio:.1f}%)")# 开始压缩if st.button("开始压缩", key="compress_btn", type="primary"):output_filename, processed_data, comp_time, comp_ratio, _ = process_file(uploaded_file, "压缩", algorithm=algorithm, level=level)if processed_data:comp_size = len(processed_data)st.success(f"文件压缩成功！耗时: {comp_time:.2f}秒")col1, col2 = st.columns(2)col1.metric("原始大小", humanize.naturalsize(file_size))col2.metric("压缩后大小", humanize.naturalsize(comp_size), f"{file_size - comp_size}减少", delta_color="inverse")st.info(f"压缩比: {comp_ratio:.2f}%")st.download_button(label="下载压缩文件",data=processed_data,file_name=output_filename,mime=get_mime_type(output_filename))# 解压页面with tab_decompress:st.subheader("解压文件")with st.expander("上传说明", expanded=True):st.info("1. 上传之前通过本工具压缩的文件（自动恢复原始文件名）\n2. 也支持其他.zst/.lz4/.gz/.br文件")uploaded_file = st.file_uploader("选择要解压的文件", type=["zst", "lz4", "gz", "br"], key="decompress")if uploaded_file:file_ext = get_extension(uploaded_file.name)st.info(f"文件格式: {file_ext.upper()}")if st.button("开始解压", key="decompress_btn", type="primary"):output_filename, processed_data, decomp_time, _, decomp_size = process_file(uploaded_file, "解压")if processed_data:orig_size = len(uploaded_file.getvalue())st.success(f"文件解压成功！耗时: {decomp_time:.2f}秒")col1, col2 = st.columns(2)col1.metric("压缩大小", humanize.naturalsize(orig_size))col2.metric("解压后大小", humanize.naturalsize(decomp_size), f"{decomp_size - orig_size}增加")st.download_button(label="下载解压文件",data=processed_data,file_name=output_filename,mime=get_mime_type(output_filename))if __name__ == "__main__":main()