python 源码分析之字节码工具

分析 python 字节码有一个趁手的工具非常重要，找了好久，看来分析 python 源码的博主远远不如 java 的多。 仅仅适用于 python 3。

用法

python parse.py test.py

非常简单直观。

#!/usr/bin/env python
# encoding: utf-8

# parse.py
import dis, marshal, struct, sys, time, types, binascii
import py_compile

def generate(filename):
    if not filename.endswith("py"):
        raise ValueError("filename must be xxx.py")
    py_compile.compile(filename, cfile=filename + "c")

def show_file(fname):
    generate(fname)
    fname += "c"
    f = open(fname, "rb")
    magic = f.read(4)
    moddate = f.read(4)
    filesz = f.read(4)
    modtime = time.asctime(time.localtime(struct.unpack('=L', moddate)[0]))
    filesz = struct.unpack('=L', filesz)
    print ("magic %s" % (binascii.hexlify(magic)))
    print ("moddate %s (%s)" % (binascii.hexlify(moddate), modtime))
    print ("files sz %d" % filesz)
    code = marshal.load(f)
    show_code(code)

def show_code(code, indent=''):
    print ("%scode" % indent)
    indent += '   '
    print ("%sargcount %d" % (indent, code.co_argcount))
    print ("%snlocals %d" % (indent, code.co_nlocals))
    print ("%sstacksize %d" % (indent, code.co_stacksize))
    print ("%sflags %04x" % (indent, code.co_flags))
    show_hex("code", code.co_code, indent=indent)
    dis.disassemble(code)
    print ("%sconsts" % indent)
    for const in code.co_consts:
        if type(const) == types.CodeType:
            show_code(const, indent+'   ')
        else:
            print ("   %s%r" % (indent, const))
    print ("%snames %r" % (indent, code.co_names))
    print ("%svarnames %r" % (indent, code.co_varnames))
    print ("%sfreevars %r" % (indent, code.co_freevars))
    print ("%scellvars %r" % (indent, code.co_cellvars))
    print ("%sfilename %r" % (indent, code.co_filename))
    print ("%sname %r" % (indent, code.co_name))
    print ("%sfirstlineno %d" % (indent, code.co_firstlineno))
    show_hex("lnotab", code.co_lnotab, indent=indent)

def show_hex(label, h, indent):
    h = binascii.hexlify(h)
    if len(h) < 60:
        print ("%s%s %s" % (indent, label, h))
    else:
        print ("%s%s" % (indent, label))
        for i in range(0, len(h), 60):
            print ("%s   %s" % (indent, h[i:i+60]))

if __name__ == "__main__":
    show_file(sys.argv[1])