war3 rep file handler

W3GFileHandler.py

#!/usr/bin/env python
# *-*coding:utf-8*-*

import os
import zlib
import binascii

class W3GFileHandler(object):
    
    def __init__(self, file):
        self.w3g_file = open(file)
        self.w3g_header = None
    
    def file_read(self, head=None, end=None):
        self.w3g_file_readed = self.w3g_file.read()
        return self.w3g_file_readed[head:end]
    
    def file_write(self, path, data):
        data_store_file = open(path, 'w')
        data_store_file.write(data)
        data_store_file.close()
            
    def file_close(self):
        self.w3g_file.close()

class W3GFileHeaderHandler(W3GFileHandler):
    
    def catch_header(self):
        """header一般为开始的68个字节"""
        self.w3g_header = self.file_read(0, 68)
        
    def first_string(self):
        """header的1-28字节为固定字符串"""
        rsp = self.w3g_header[0:28]
        print "固定字符串: ", rsp
        return rsp
    
    def header_size(self):
        """header的29-32字节为header部分的总字节数"""
        rsp = binascii.b2a_hex(self.w3g_header[31:27:-1])
        print "Header的字节数: ", int(rsp, 16)
        return int(rsp, 16)
    
    def compressed_size(self):
        """header的33-36字节为压缩的数据块的大小"""
        rsp = binascii.b2a_hex(self.w3g_header[35:31:-1])
        print "压缩数据块的压缩数据总字节数: ", int(rsp, 16)
        return int(rsp, 16)
    
    def rep_header_version(self):
        """header的37-40字节为录像版本标识"""
        rsp = binascii.b2a_hex(self.w3g_header[39:35:-1])
        print "录像版本标识: ", int(rsp, 16)
        return int(rsp, 16)
        
    def decompressed_size(self):
        """header的41-44字节为压缩的数据块的大小"""
        rsp = binascii.b2a_hex(self.w3g_header[43:39:-1])
        print "压缩数据块解压缩后的总字节数: ", int(rsp, 16)
        return int(rsp, 16)
    
    def compressed_num(self):
        """header的45-48字节为数据块的个数"""
        rsp = binascii.b2a_hex(self.w3g_header[47:43:-1])
        print "压缩数据块的个数: ", int(rsp, 16)
        return int(rsp, 16)
    
    def some_string(self):
        """header的49-52字节为一个标识字符串"""
        rsp = self.w3g_header[51:47:-1]
        print "一个字符串标识: ", rsp
        return rsp

    def version_number(self):
        """header的53-56字节为版本号"""
        rsp = binascii.b2a_hex(self.w3g_header[55:51:-1])
        print "版本号: ", int(rsp, 16)
        return int(rsp, 16)
    
    def build_number(self):
        """header的57-58字节为构建号"""
        rsp = binascii.b2a_hex(self.w3g_header[57:55:-1])
        print "构建号: ", int(rsp, 16)
        return int(rsp, 16)
    
    def flags(self):
        """header的59-60字节为游戏模式，单人或多人"""
        rsp = binascii.b2a_hex(self.w3g_header[59:57:-1])
        print "单人或多人游戏: ", int(rsp, 16)
        return int(rsp, 16)

    def rep_length_in_msec(self):
        """header的61-64字节为游戏时长，单位毫秒"""
        rsp = binascii.b2a_hex(self.w3g_header[63:59:-1])
        print "录像时长: ", int(rsp, 16)
        return int(rsp, 16)

    def header_crc32(self):
        """header的65-68字节为CRC32校验码"""
        rsp = binascii.b2a_hex(self.w3g_header[67:63:-1])
        print "Header部分CRC32校验码: ", int(rsp, 16)
        return int(rsp, 16)
    
    def get_all_header_info(self):
        print "[×] 开始获取数据Header [*]"
        self.catch_header()
        self.first_string()
        self.header_size()
        self.compressed_size()
        self.rep_header_version()
        self.decompressed_size()
        self.compressed_num()
        self.some_string()
        self.version_number()
        self.build_number()
        self.flags()
        self.rep_length_in_msec()
        self.header_crc32()
        print "[×] 已获取数据Header [*]"
        
class W3GFileDataHandler(W3GFileHandler):
    
    def catch_data(self):
        """header一般为从69到最末的字节"""
        self.w3g_data = self.file_read(67)
        
    def _decompress(self, compressed_data):
        """创建一个zlib decompressobj，flush后才能进行decompress"""
        decomp_obj = zlib.decompressobj()
        decomp_obj.flush()
        decompressed_data = decomp_obj.decompress(compressed_data)
        return decompressed_data
        

    def decompress_and_conbine(self, data_num):
        offset = 0
        data_decompressed = ''
        
        for i in range(data_num):
            header_begin = offset
            header_end = offset + 2
            size_end = offset + 4
            data_header = binascii.b2a_hex(self.w3g_data[header_end:header_begin:-1])
            data_block_size = binascii.b2a_hex(self.w3g_data[size_end:header_end:-1])
            data_compressed_size = int(data_header, 16)
            data_begin = offset + 9
            data_end = offset + 9 + data_compressed_size
            data_compressed = self.w3g_data[data_begin:data_end]
            print "数据块header从字节 %d 到 %d, 压缩的数据块大小: %d" % \
                            (offset+1, offset+8, int(data_block_size, 16))
            print "数据块从字节 %d 到 %d" % (data_begin, data_end)
            print "压缩数据Header，即该数据块大小: ", data_compressed_size
            data_decompressed += self._decompress(data_compressed)
            offset += data_compressed_size + 8
        
        self.file_write('/root/decompress_data', data_decompressed)
        print len(data_decompressed)
            
    def get_all_data_info(self, num):
        print "[×] 开始获取数据块 [*]"
        self.catch_data()
        self.decompress_and_conbine(num)
        print "[×] 已获取数据块 [*]"            
            
if __name__ == '__main__':
    file_path = u"****.w3g"
    w3g_header = W3GFileHeaderHandler(file_path)
    w3g_data = W3GFileDataHandler(file_path)
    w3g_header.get_all_header_info()
    w3g_data_num = w3g_header.compressed_num()
    w3g_data.get_all_data_info(w3g_data_num)
    w3g_header.file_close()
    w3g_data.file_close()