python 通过 capstone 反汇编

Capstone是一个轻量级的多平台、多架构的反汇编框架，该模块支持目前所有通用操作系统，反汇编架构几乎全部支持。

capstone使用起来非常简单，如果只需要静态反汇编，则几行代码即可完成该功能了。

from capstone import *

# powerby LyShark
def Disassembly(path,BaseAddr,FileOffset,ReadByte):
    with open(path,"rb") as fp:
        fp.seek(int(FileOffset))
        opcode = fp.read(int(ReadByte))

    md = Cs(CS_ARCH_X86, CS_MODE_32)
    for item in md.disasm(opcode, 0):
        addr = int(BaseAddr) + item.address
        dic = {"Addr": str(addr) , "OpCode": item.mnemonic + " " + item.op_str}
        print(dic)

if __name__ == "__main__":
    # 文件名 内存地址 开始位置 长度
    Disassembly("d://Win32Project.exe",401000,0,1024)

如果需要针对.text节进行反汇编，则需要通过pefile模块找到该节所对应到文件中的位置，并从该位置开始向下反编译即可，代码如下：

from capstone import *
import pefile

# 遍历整个可执行文件并返回汇编代码,有一个小Bug
# powerby LyShark
def FOA_Disassembly(FilePath):
    opcode_list = []
    pe = pefile.PE(FilePath)
    ImageBase = pe.OPTIONAL_HEADER.ImageBase

    for item in pe.sections:
        if str(item.Name.decode('UTF-8').strip(b'\x00'.decode())) == ".text":
            # print("虚拟地址: 0x%.8X 虚拟大小: 0x%.8X" %(item.VirtualAddress,item.Misc_VirtualSize))
            VirtualAddress = item.VirtualAddress
            VirtualSize = item.Misc_VirtualSize
            ActualOffset = item.PointerToRawData
    StartVA = ImageBase + VirtualAddress
    StopVA = ImageBase + VirtualAddress + VirtualSize
    with open(FilePath,"rb") as fp:
        fp.seek(ActualOffset)
        HexCode = fp.read(VirtualSize)

    md = Cs(CS_ARCH_X86, CS_MODE_32)
    for item in md.disasm(HexCode, 0):
        addr = hex(int(StartVA) + item.address)
        dic = {"Addr": str(addr) , "OpCode": item.mnemonic + " " + item.op_str}
        print("[+] 反汇编地址: {} 参数: {}".format(addr,dic))
        opcode_list.append(dic)
    return opcode_list

if __name__ == "__main__":
    ref = FOA_Disassembly("d://Win32Project.exe")
    print(ref)