JAR文件批量反编译处理

前言：

有需要批量反编译文件夹中大量的jar文件，并在反编译的源代码中找到特定的调用，找了一圈试了很多工具，发现比较好的处理方法，这里进行记录，方便后续使用查询

工具：

工具我使用了很多，比较好用的这里推荐procyon-decompiler，地址如下：

https://github.com/mstrobel/procyon

使用方法很简单：

java -jar procyon-decompiler-0.6.0.jar -o /tmp/ test.jar

 使用上述命令即可对单独jar包进行反编译，可以编写python3或者批处理执行，反编译文件夹中所有jar文件

import os
import subprocess
from pathlib import Path

def decompile_jar(jar_path, output_dir):
    try:
        subprocess.run(["java", "-jar", "procyon-decompiler-0.6.0.jar", '-o',output_dir, jar_path], check=True)
        print(f"Decompiled {jar_path} to {output_dir}")
    except subprocess.CalledProcessError as e:
        print(f"Error decompiling {jar_path}: {e}")

def batch_decompile_jars(directory):
    for file in os.listdir(directory):
        if file.endswith(".jar"):
            jar_path = os.path.join(directory, file)
            output_dir = os.path.splitext(jar_path)[0] + "_decompiled"
            Path(output_dir).mkdir(parents=True, exist_ok=True)
            decompile_jar(jar_path, output_dir)

if __name__ == "__main__":
    jarpath = "D:\\lib"
    batch_decompile_jars(jarpath)

上述代码可以批量处理文件夹中文件

然后可以使用如下代码对文件夹内容进行扫描并输出xlsx文件

import os
import zipfile
import re
import openpyxl


def find_class_usages(project_dir, class_names):
    results = {}
    for root, dirs, files in os.walk(project_dir):
        for file in files:
            if file.endswith('.java'):
                try:
                    file_path = os.path.join(root, file)
                    with open(file_path, 'r', encoding='utf-8') as f:
                        content = f.read()
                    for class_name in class_names:
                        pattern = r'\b' + re.escape(class_name) + r'\b'
                        if re.search(pattern, content):
                            print(file_path)
                            if class_name not in results:
                                results[class_name] = []
                            results[class_name].append(file_path)
                except Exception as e:
                    print(file_path + "-->" + str(e))

    return results


def save_to_xlsx(results, output_file):
    workbook = openpyxl.Workbook()
    worksheet = workbook.active
    worksheet['A1'] = 'Class Name'
    worksheet['B1'] = 'Usage Locations'
    row = 2
    for class_name, locations in results.items():
        for location in locations:
            worksheet.cell(row=row, column=1, value=class_name)
            worksheet.cell(row=row, column=2, value=location)
            row += 1
    workbook.save(output_file)

jar_file_path = 'D:\\jar'
project_dir  = "D:\\lib"
jar_path = "D:\\unziplib"

if __name__ == '__main__':
    class_names = ["org.bouncycastle","org.apache.james.mime4j"]
    usage_results = find_class_usages(project_dir, class_names)
    save_to_xlsx(usage_results, "OUT.xlsx")

 很简单，没什么好说的。