Android APK资源分析之Python实现

def get_apk_base_info(self): # 获取apk包的基本信息p = subprocess.Popen(self.aapt_path + " dump badging %s" % self.apkPath, stdout=subprocess.PIPE,                         stderr=subprocess.PIPE,                         stdin=subprocess.PIPE, shell=True)     (output, err) = p.communicate()     package_match = re.compile("package: name='(\S+)' versionCode='(\d+)' versionName='(\S+)'").match(output.decode())    if not package_match:        raise Exception("can't get package,versioncode,version")    package_name = package_match.group(1)    version_code = package_match.group(2)    version_name = package_match.group(3)    launch_activity_match = re.compile("launchable-activity: name='(\S+)'").search(output.decode())    if not launch_activity_match:        raise Exception("can't get launch_activity")    launch_activity = launch_activity_match.group(1)    sdk_version_match = re.compile("sdkVersion:'(\S+)'").search(output.decode())    if not sdk_version_match:        raise Exception("can't get min_sdk_version")    min_sdk_version = sdk_version_match.group(1)    target_sdk_version_match = re.compile("targetSdkVersion:'(\S+)'").search(output.decode())    if not target_sdk_version_match:        raise Exception("can't get target_sdk_version")    target_sdk_version = target_sdk_version_match.group(1)    application_label_match = re.compile("application-label:'([\u4e00-\u9fa5_a-zA-Z0-9-\S]+)'").search(output.decode())    if not application_label_match:        raise Exception("can't get application_label")    application_label = application_label_match.group(1)    return package_name, version_name, version_code,launch_activity,min_sdk_version,target_sdk_version,application_label

def get_apk_size(self):# 得到apk的文件大小     size = round(os.path.getsize(self.apkPath) / (1024 * 1000), 2)     # return str(size) + "M"     return os.path.getsize(self.apkPath)def get_apk_download_size(apk_file_name):     # 获取apk_download_size     zip_file = zipfile.ZipFile(apk_file_name, 'r')     zip_infos = zip_file.infolist()     download_size = 0     for index in range(len(zip_infos)):         zip_info = zip_infos[index]         download_size += zip_info.compress_size     return download_size     

def __get_files_from_apk(apk_file_name, apk_name_without_suffix, mapping_name_without_suffix):# 读取混淆文件    proguard_map = reproguard.read_proguard_apk(mapping_name_without_suffix)    zip_file = zipfile.ZipFile(apk_file_name, 'r')# 获取APK文件内所有文件列表    file_name_list = zip_file.namelist()    # 遍历APK文件下文件列表    for index in range(len(file_name_list)):        file_name = str(file_name_list[index])        # 还原混淆文件        if proguard_map:            entry_name = str(reproguard.replace_path_id(file_name, proguard_map)) if("/" in file_name) else file_name        else:            entry_name = file_name # 获取文件MD5值        md5_str = md5.get_md5_value(file_name)        parent_dir = entry_name[:parent_index] if parent_index >= 0 else ""# 根据文件名获取文件的ZipInfo(压缩文件)        zip_info = zip_file.getinfo(file_name)        file_info = FileInfo(            path=file_name,            entry_name=entry_name,            md5_str=md5_str,            compress_size=zip_info.compress_size,            file_type=file_type,            zip_file=zip_info        )        if "so" == file_type and "libcom.jd.lib" in entry_name:            # aura插件分析            ...... elif "assets/jdreact/" in entry_name:            # React Native分析     ......        elif "dex" == file_type:            # dex分析方法类,获取APK中class数+references methods数......        elif file_util.is_image(entry_name):    # 如果是图片文件,就要分析图片的尺寸,以及判断是否是 非透明通道图.....        zip_file.close()    return apk_file_list, aura_bundles, dex_files, react_modules

def ReadDexHeader_(self, file_dir):# 以二进制形式读取文件    f = open(file_dir, 'rb')    m = mmap.mmap(f.fileno(), 0, access=mmap.ACCESS_READ)    self.mmap = m    ....省略DEX部分内容读取    # dex中用到的所有的字符串内容的大小    string_ids_size = struct.unpack('<L', m[0x38:0x3C])[0]    # dex中用到的所有的字符串内容的偏移值    string_ids_off = struct.unpack('<L', m[0x3C:0x40])[0]    # dex中的类型数据结构的大小    type_ids_size = struct.unpack('<L', m[0x40:0x44])[0]    # dex中的类型数据结构的偏移值    type_ids_off = struct.unpack('<L', m[0x44:0x48])[0]    # dex中的原型数据信息数据结构的大小    proto_ids_size = struct.unpack('<L', m[0x48:0x4C])[0]    # dex中的原型数据信息数据结构的偏移值    proto_ids_off = struct.unpack('<L', m[0x4C:0x50])[0]    # dex中的字段信息数据结构的大小    field_ids_size = struct.unpack('<L', m[0x50:0x54])[0]    # dex中的字段信息数据结构的偏移值    field_ids_off = struct.unpack('<L', m[0x54:0x58])[0]    # dex中的方法信息数据结构的大小    method_ids_size = struct.unpack('<L', m[0x58:0x5C])[0]    # dex中的方法信息数据结构的偏移值    method_ids_off = struct.unpack('<L', m[0x5C:0x60])[0]    # dex中的类信息数据结构的大小    class_defs_size = struct.unpack('<L', m[0x60:0x64])[0]    # dex中的类信息数据结构的偏移值    class_defs_off = struct.unpack('<L', m[0x64:0x68])[0]    # dex中数据区域的结构信息的大小    data_size = struct.unpack('<L', m[0x68:0x6C])[0]    # dex中数据区域的结构信息的偏移值    data_off = struct.unpack('<L', m[0x6C:0x70])[0]    # 此变量用于存放读取到的dex头部    header_data = dict({})    header_data['string_ids_size'] = string_ids_size    header_data['string_ids_off'] = string_ids_off    header_data['type_ids_size'] = type_ids_size    header_data['type_ids_off'] = type_ids_off    header_data['proto_ids_size'] = proto_ids_size    header_data['proto_ids_off'] = proto_ids_off    header_data['field_ids_size'] = field_ids_size    header_data['field_ids_off'] = field_ids_off    header_data['method_ids_size'] = method_ids_size    header_data['method_ids_off'] = method_ids_off    header_data['class_defs_size'] = class_defs_size    header_data['class_defs_off'] = class_defs_off    header_data['data_size'] = data_size    header_data['data_off'] = data_off    self.header = header_data

from PIL import Imagetry:       image_bytes = io.BytesIO(zip_file.read(file_name))       img = Image.open(image_bytes)       # print(img.format)        # JPEG       # 图片尺寸,单位像素       image_size = img.size       # (801, 1200)       filename_without_suffix, image_type = file_util.get_file_type(entry_name)      # mode图片模式,有9种，分别为1，L，P，RGB，RGBA(有alpha通道)，CMYK，YCbCr，I，F       if img.mode != "RGBA":            if image_type == ".png" and not filename_without_suffix.endswith(".9") \                             and zip_info.compress_size >= 10*1024:                 non_alpha = True   except OSError:        pass   finally:        file_info.image_size = image_size        file_info.non_alpha = non_alpha        apk_file_list.append(file_info)   continue

 def read_resource_txt_file(mapping_name):resource_txt_path = mapping_name + "/AndroidJD-Phone/hotfix/R.txt"    # R.txt解析结果    resource_def_map = dict({})    unused_res_set = set({})    try:        r_txt_file = open(resource_txt_path, "r")        line = r_txt_file.readline()        while line:            columns = line.split(" ")            if len(columns )>= 4:                resource_name = "R."+columns[1]+"."+columns[2]                if not columns[0].endswith("[]") and columns[3].startswith("0x"):                    if columns[3].startswith("0x01"):                        print("ignore system resource %s", resource_name)                    else:                        res_id = __parse_resource_id(columns[3].strip())                        if res_id:                            resource_def_map[res_id] = resource_name                            if not ignore_resource(resource_name):                                unused_res_set.add(resource_name)                else:                    # print("ignore resource %s", resource_name)# styleable资源读取                        ........line = r_txt_file.readline()    except Exception as e:        raise Exception(resource_txt_path+" file Error,", e)    finally:        return resource_def_map, styleable_map, unused_res_set

# 遍历smali代码,获取引用资源的res_iddef read_smali_files(smali_path, resource_def_map, styleable_map, r_class_proguard_map):    resource_def_set = set({})    try:        if file_util.is_readable(smali_path):            smali_file = open(smali_path, "r")        smali_line = smali_file.readline().strip()        while smali_line:            line = smali_line.lstrip('\t')            if line and line.strip().startswith("const "):                  columns = line.split(",")                  if len(columns) == 2:                      res_id = __parse_resource_id(columns[1].strip())                      if res_id and (res_id in resource_def_map.keys()):                          # print(resource_def_map[res_id])                             resource_def_set.add(resource_def_map[res_id])            elif line.startswith("sget "):                # styleable资源引用在smali代码中呈现                .....smali_line: = smali_file.readline()    except Exception as e:        raise Exception("read_smali_files Error,", e)    return resource_def_set# 遍历res/目录下xml文件def decode_resources(apk_path_dir, res_guard_map):    non_value_reference_map = dict({})    resource_res_used_set = set({})    if not apk_path_dir.endswith("/"):        apk_path_dir += "/"    res_dir = apk_path_dir+"res/"    if not os.path.exists(res_dir):        res_dir = apk_path_dir + 'r/'    for paths, sub_paths, files in os.walk(res_dir):        path_dirs = paths.split("/")        resource_dir = path_dirs[len(path_dirs)-1]        res_type = str(resource_dir).split('-')[0]        if res_type and "values" in res_type:            for file in files:                # 解析values下xml文件,并返回引用资源ID列表                value_references_set = xml_decoder(os.path.join(paths, file), res_guard_map)                for resource in value_references_set:                    resource_res_used_set.add(resource)        elif res_type:            for file in files:                if file_util.is_legal_file(os.path.join(paths, file)) and file.endswith(".xml") \                        and not ignore_resource(os.path.join(paths, file)):                    # 非values xml引用res资源                    res_used_set = xml_decoder(os.path.join(paths, file), res_guard_map)                    resource = "R." + str(res_type) + "." + file[:file.rfind(".")]                    if resource in res_guard_map.keys():                        before_resource = res_guard_map[resource].split("R."+res_type+".")[1].replace('.', '_')                        res_guard_resource = "R."+res_type+"." + before_resource                        resource = res_guard_resource                    if resource in non_value_reference_map.keys():                        reference_set = non_value_reference_map.get(resource)                        for item in res_used_set:                            reference_set.add(item)                        non_value_reference_map[resource] = reference_set                    else:                        non_value_reference_map[resource] = res_used_set# AndroidManifest.xml文件读取,并返回引用的资源ID列表    manifest_path = apk_path_dir + "AndroidManifest.xml"    if not file_util.is_legal_file(manifest_path):        logging.warning("File %s is illegal!" % manifest_path)        return    manifest_ref_set = xml_decoder(manifest_path, res_guard_map)    for reference in manifest_ref_set:        resource_res_used_set.add(reference)    return resource_res_used_set, non_value_reference_map

def find_asset_file(asset_dir): if asset_dir and os.path.exists(asset_dir) and os.path.isdir(asset_dir):        for paths, sub_paths, files in os.walk(asset_dir):            for file in files:                asset_file_sub_dir = paths.split(asset_dir)[1]                # assets目录下图片资源均放入unused_asset_set                unused_asset_set.add(os.path.join(asset_file_sub_dir, file))



# 遍历smali代码,获取引用资源的res_iddef read_smali_files(smali_path):    if file_util.is_readable(smali_path):        smali_file = open(smali_path, "r")        smali_line = smali_file.readline()        while smali_line:            line = smali_line.strip()            if line and line.startswith("const"):                # smali代码中引用资源ID                do something...            elif line.startswith("sget"):                # smali代码中引用资源ID数组,例如int[] styleable                do something...            elif line.startswith("const-string"):                # 查找smali代码中引用asset资源                columns = line.split(",")                if len(columns) == 2:                    asset_file_name = columns[1].strip()                    if asset_file_name:                        for path in unused_res_set:                            if path.endswith(asset_file_name):                                unused_res_set.remove(path)            smali_line = smali_file.readline()