Compare commits

...

5 Commits

Author SHA1 Message Date
kelvinBen 479abe2e3b 1. 添加下载任务线程 3 years ago
kelvinBen 756025d7fd 忽略文件列表中添加xlsx文件 3 years ago
kelvinBen 4b3db5aff7 - 新增通过网络批量下载文件 3 years ago
kelvinBen acc01c3303 - 优化excle文件输出 3 years ago
kelvinBen 1f0fa65606 - 优化iOS壳检测速度 3 years ago
  1. 5
      .gitignore
  2. 43
      app.py
  3. 245
      libs/core/__init__.py
  4. 95
      libs/core/download.py
  5. 23
      libs/core/net.py
  6. 8
      libs/core/parses.py
  7. 33
      libs/task/android_task.py
  8. 169
      libs/task/base_task.py
  9. 76
      libs/task/download_task.py
  10. 77
      libs/task/ios_task.py
  11. 34
      libs/task/net_task.py
  12. 3
      libs/task/web_task.py
  13. 4
      requirements.txt
  14. 14
      update.md

5
.gitignore vendored

@ -1,5 +1,6 @@
result_*.txt
result_*.xls
result_*.xlsx
download/
history/
out/
@ -114,3 +115,7 @@ venv.bak/
# add
.idea/
#
1.py
.vscode/

@ -4,13 +4,20 @@
# Github: https://github.com/kelvinBen/AppInfoScanner
import click
import logging
from libs.core import Bootstrapper
from libs.task.base_task import BaseTask
@click.group(help="Python script for automatically retrieving key information in app.")
def cli():
pass
try:
LOG_FORMAT = "%(message)s" # 日志格式化输出
fp = logging.FileHandler('info.log', mode='w',encoding='utf-8')
fs = logging.StreamHandler()
logging.basicConfig(level=logging.INFO, format=LOG_FORMAT, handlers=[fp, fs]) # 调用
except Exception as e:
logging.error("{}".format(e))
# 创建Android任务
@cli.command(help="Get the key information of Android system.")
@ -23,13 +30,13 @@ def cli():
@click.option("-o", '--output',required=False, type=str,default=None,help="Specify the result set output directory.")
@click.option("-p", '--package',required=False,type=str,default="",help="Specifies the package name information that needs to be scanned.")
def android(inputs: str, rules: str, sniffer: bool, no_resource:bool, all:bool, threads:int, output, package:str) -> None:
try:
bootstrapper = Bootstrapper(__file__, output, all, no_resource)
bootstrapper.init()
bootstrapper = Bootstrapper(rules, sniffer, threads, all ,no_resource)
bootstrapper.init_dir(__file__, output)
BaseTask().start("Android", inputs, package)
BaseTask("Android", inputs, rules, sniffer, threads, package).start()
except Exception as e:
raise e
@cli.command(help="Get the key information of iOS system.")
@click.option("-i", "--inputs", required=True, type=str, help="Please enter IPA file or ELF file to scan or corresponding IPA download address. App store is not supported at present.")
@ -40,13 +47,12 @@ def android(inputs: str, rules: str, sniffer: bool, no_resource:bool, all:bool,
@click.option("-t", '--threads',required=False, type=int,default=10,help="Set the number of concurrency. The larger the concurrency, the faster the speed. The default value is 10.")
@click.option("-o", '--output',required=False, type=str,default=None,help="Specify the result set output directory.")
def ios(inputs: str, rules: str, sniffer: bool, no_resource:bool, all:bool, threads:int, output:str) -> None:
try:
bootstrapper = Bootstrapper(__file__, output, all, no_resource)
bootstrapper.init()
BaseTask("iOS", inputs, rules, sniffer, threads).start()
except Exception as e:
raise e
bootstrapper = Bootstrapper(rules, sniffer, threads, all ,no_resource)
bootstrapper.init_dir(__file__, output)
BaseTask().start("iOS", inputs)
@cli.command(help="Get the key information of Web system.")
@click.option("-i", "--inputs", required=True, type=str, help="Please enter the site directory or site file to scan or the corresponding site download address.")
@ -57,15 +63,14 @@ def ios(inputs: str, rules: str, sniffer: bool, no_resource:bool, all:bool, thre
@click.option("-t", '--threads',required=False, type=int,default=10,help="Set the number of concurrency. The larger the concurrency, the faster the speed. The default value is 10.")
@click.option("-o", '--output',required=False, type=str,default=None,help="Specify the result set output directory.")
def web(inputs: str, rules: str, sniffer: bool, no_resource:bool, all:bool, threads:int, output:str) -> None:
try:
bootstrapper = Bootstrapper(__file__, output, all, no_resource)
bootstrapper.init()
BaseTask("Web", inputs, rules, sniffer, threads).start()
except Exception as e:
raise e
bootstrapper = Bootstrapper(rules, sniffer, threads, all ,no_resource)
bootstrapper.init_dir(__file__, output)
BaseTask().start("Web", inputs)
def main():
cli()
if __name__ == "__main__":

@ -2,118 +2,179 @@
# -*- coding: utf-8 -*-
# Author: kelvinBen
# Github: https://github.com/kelvinBen/AppInfoScanner
import os
import time
import shutil
import platform
import logging
backsmali_file = None
apktool_file = None
strings_file = None
app_history_file= None
domain_history_file = None
result_dir = None
download_dir = None
decode_dir = None
user_add_rules = None
# smali 所在路径
smali_path = ""
# backsmli 所在路径
backsmali_path = ""
# apktool 所在路径
apktool_path = ""
# 系统类型
os_type = ""
# 输出路径
output_path = ""
# 下载完成标记
download_flag = False
net_sniffer_flag = False
all_string_out = False
no_resource_flag = False
excel_row = 1
threads_num = 10
# excel 起始行号
excel_row = 0
class Bootstrapper(object):
def __init__(self, path, out_path, all=False, no_resource= False):
global smali_path
global backsmali_path
global apktool_path
global os_type
global output_path
global script_root_dir
global txt_result_path
global xls_result_path
global strings_path
global history_path
global app_history_path
global domain_history_path
global excel_row
global download_path
def __init__(self, rules, threads, sniffer, all, no_resource):
# backsmali 加载路径
global backsmali_file
# apktool 加载路径
global apktool_file
# string 加载路径
global strings_file
# App 扫描历史文件
global app_history_file
# 域名 扫描历史文件
global domain_history_file
# 结果输出目录
global result_dir
# 临时文件下载目录
global download_dir
# 临时反编译目录
global decode_dir
# 下载完成标记
global download_flag
global out_dir
global all_flag
global resource_flag
all_flag = not all
resource_flag = no_resource
# excel 行号
global excel_row
# 用户自定义规则
global user_add_rules
# 用户指定线程数
global threads_num
# 网络嗅探标记
global net_sniffer_flag
# 输出所有字符传
global all_string_out
# 忽略资源标记
global no_resource_flag
user_add_rules = rules
threads_num = threads
net_sniffer_flag = not sniffer
all_string_out = all
no_resource_flag = no_resource
# 需要创建的目录列表
self.__create_dir_list__= []
# 需要删除目录的列表
self.__remove_dir_list__= []
logging.info("[*] System env: {}".format(platform.system()))
def init_dir(self, app_input_path, user_out_path):
logging.info("[*] init dir...")
# 脚本执行目录
script_root_dir = os.path.dirname(os.path.abspath(app_input_path))
create_time = time.strftime("%Y%m%d%H%M%S", time.localtime())
script_root_dir = os.path.dirname(os.path.abspath(path))
if out_path:
out_dir = out_path
else:
out_dir = script_root_dir
# 加载集成的工具
self.__tools_loading__(script_root_dir)
# 构建持久化目录
self.__build_persistent_path__(script_root_dir)
# 构建结果输出目录
self.__build_result_out__path__(script_root_dir,user_out_path)
# 统一目录构建中心
self.__build_dir__()
# 加载集成的工具
def __tools_loading__(self,script_root_dir):
tools_dir = os.path.join(script_root_dir,"tools")
output_path = os.path.join(out_dir,"out")
history_path = os.path.join(script_root_dir,"history")
backsmali_file = os.path.join(tools_dir,"baksmali.jar")
logging.info("[*] Backsmali Path: {}".format(backsmali_file))
apktool_file = os.path.join(tools_dir, "apktool.jar")
logging.info("[*] Apktool Path: {}".format(apktool_file))
if platform.system() == "Windows":
machine2bits = {'AMD64':64, 'x86_64': 64, 'i386': 32, 'x86': 32}
machine2bits.get(platform.machine())
if platform.machine() == 'i386' or platform.machine() == 'x86':
strings_path = os.path.join(tools_dir,"strings.exe")
strings_file = os.path.join(tools_dir,"strings.exe")
else:
strings_path = os.path.join(tools_dir,"strings64.exe")
strings_file = os.path.join(tools_dir,"strings64.exe")
else:
strings_file ="strings"
logging.info("[*] Strings Path: {}".format(strings_file))
# 构建持久化目录
def __build_persistent_path__(self,script_root_dir):
# 当前用户文档目录
doc_path = os.path.join(os.path.expanduser("~"), 'Documents')
if os.path.exists(doc_path):
app_dir = os.path.join(doc_path,"AppInfoScanner")
else:
strings_path ="strings"
app_dir = os.path.join(script_root_dir,"AppInfoScanner")
# 历史任务加载目录
history_path = os.path.join(app_dir,"history")
app_history_file = os.path.join(history_path,"app_history.txt")
domain_history_file = os.path.join(history_path,"domain_history.txt")
backsmali_path = os.path.join(tools_dir,"baksmali.jar")
apktool_path = os.path.join(tools_dir, "apktool.jar")
download_path = os.path.join(out_dir,"download")
txt_result_path = os.path.join(out_dir,"result_"+str(create_time)+".txt")
xls_result_path = os.path.join(out_dir,"result_"+str(create_time)+".xls")
app_history_path = os.path.join(history_path,"app_history.txt")
domain_history_path = os.path.join(history_path,"domain_history.txt")
def init(self):
if not os.path.exists(out_dir):
os.makedirs(out_dir)
print("[*] Create directory {}".format(out_dir))
if os.path.exists(output_path):
try:
shutil.rmtree(output_path)
except Exception as e:
# 解决windows超长文件名删除问题
if not (platform.system() == "Windows"):
raise e
self.__removed_dirs_cmd__(output_path)
os.makedirs(output_path)
print("[*] Create directory {}".format(output_path))
if not os.path.exists(download_path):
# shutil.rmtree(download_path)
os.makedirs(download_path)
print("[*] Create directory {}".format(download_path))
if not os.path.exists(history_path):
os.makedirs(history_path)
print("[*] Create directory {}".format(history_path))
self.__create_dir_list__.append(app_dir)
self.__create_dir_list__.append(history_path)
# 构建结果输出目录
def __build_result_out__path__(self,script_root_dir,user_out_path):
result_out_dir = script_root_dir
# 用户指定输出目录结果则为输出到指定目录
if user_out_path:
result_out_dir = user_out_path
if os.path.exists(txt_result_path):
os.remove(txt_result_path)
# 统一输出目录
out_dir = os.path.join(result_out_dir,"out")
# 临时结果输出目录
decode_dir = os.path.join(out_dir,"decode")
# 临时文件下载目录
download_dir = os.path.join(out_dir,"download")
# 最终结果输出目录
result_dir = os.path.join(out_dir,"result")
self.__create_dir_list__.append(out_dir)
self.__create_dir_list__.append(decode_dir)
self.__create_dir_list__.append(download_dir)
self.__create_dir_list__.append(result_dir)
self.__remove_dir_list__.append(decode_dir)
# 统一目录构建中心
def __build_dir__(self):
for dir_path in self.__create_dir_list__:
if (os.path.exists(dir_path)) and (dir_path in self.__remove_dir_list__):
# 删除目录
try:
shutil.rmtree(dir_path)
logging.info("[-] Remove Dir: {}".format(dir_path))
except Exception as e:
# 解决windows超长文件名删除问题
if not (platform.system() == "Windows"):
raise e
self.__removed_dirs_cmd__(dir_path)
# 创建目录
if not os.path.exists(dir_path):
os.makedirs(dir_path)
logging.info("[+] Create Dir: {}".format(dir_path))
if os.path.exists(xls_result_path):
os.remove(xls_result_path)
def __removed_dirs_cmd__(self,output_path):
files = os.listdir(output_path)
for file in files:
@ -121,8 +182,12 @@ class Bootstrapper(object):
old_dir = os.path.join(output_path,file)
if not os.path.exists(new_dir):
os.makedirs(new_dir)
logging.info("[+] Create Dir: {}".format(new_dir))
os.chdir(output_path)
cmd = ("robocopy %s %s /purge") % (new_dir, old_dir)
logging.debug("[*] cmd : {}".format(cmd))
os.system(cmd)
os.removedirs(new_dir)
os.removedirs(old_dir)
os.removedirs(old_dir)
logging.info("[-] Remove Dir: {}".format(new_dir))
logging.info("[-] Remove Dir: {}".format(old_dir))

@ -2,27 +2,87 @@
# -*- coding: utf-8 -*-
# Author: kelvinBen
# Github: https://github.com/kelvinBen/AppInfoScanner
from genericpath import exists
import re
import os
import sys
import time
import uuid
import config
import logging
import requests
import threading
import libs.core as cores
from requests.packages import urllib3
from requests.adapters import HTTPAdapter
class DownloadThreads(threading.Thread):
class DownloadThreads(threading.Thread):
def __init__(self,input_path,file_name,cache_path,types):
def __init__(self,threadID, threadName, download_file_queue, download_file_list, types):
threading.Thread.__init__(self)
self.url = input_path
self.threadID = threadID
self.threadName = threadName
self.download_file_queue = download_file_queue
self.download_file_list = download_file_list
self.types = types
self.cache_path = cache_path
self.file_name = file_name
self.cache_path = None
def __start__(self):
# 从队列中取数据,直到队列数据不为空为止
while not self.download_file_queue.empty():
file_or_url = self.download_file_queue.get()
if not file_or_url:
logging.error("[x] Failed to get file!")
continue
self.__auto_update_type__(file_or_url)
def __requset__(self):
# 自动更新文件类型
def __auto_update_type__(self,file_or_url):
uuid_name = str(uuid.uuid1()).replace("-","")
# 文件后缀为apk 或者 类型为 Android 则自动修正为Android类型
if file_or_url.endswith("apk") or self.types == "Android":
types = "Android"
file_name = uuid_name + ".apk"
# 文件后缀为dex 或者 类型为 Android 则自动修正为Android类型
elif file_or_url.endswith("dex") or self.types == "Android":
types = "Android"
file_name = uuid_name + ".dex"
# 文件后缀为ipa 或者 类型为 iOS 则自动修正为iOS类型
elif file_or_url.endswith("ipa") or self.types == "iOS":
types = "iOS"
file_name = uuid_name + ".ipa"
else:
# 路径以http://开头或者以https://开头 且 文件是不存在的自动修正为web类型
if (file_or_url.startswith("http://") or file_or_url.startswith("https://")) and (not os.path.exists(file_or_url)):
types = "WEB"
file_name = uuid_name + ".html"
# 其他情况如:types为WEB 或者目录 或者 单独的二进制文件 等交给后面逻辑处理
if file_or_url.startswith("http://") or file_or_url.startswith("https://"):
# 进行文件下载
self.__file_deduplication__(file_name, uuid_name)
if self.cache_path:
file_path = self.cache_path
self.__download_file__(file_or_url,file_path)
#TODO 标记下载过的文件,避免重复下载
else:
types = self.types
file_path = file_or_url
self.download_file_list.append({"path": file_path, "type": types})
# 防止文件名重复导致文件被复写
def __file_deduplication__(self,file_name, uuid_name):
cache_path = os.path.join(cores.download_dir, file_name)
if not os.path.exists(cache_path):
self.cache_path = cache_path
return
new_uuid_name = str(uuid.uuid1()).replace("-","")
new_file_name = file_name.replace(uuid_name,new_uuid_name)
self.__file_deduplication__(new_file_name,new_uuid_name)
# 文件下载
def __download_file__(self, url, file_path):
try:
session = requests.Session()
session.mount('http://', HTTPAdapter(max_retries=3))
@ -32,17 +92,17 @@ class DownloadThreads(threading.Thread):
urllib3.disable_warnings()
if config.method.upper() == "POST":
resp = session.post(url=self.url,params=config.data ,headers=config.headers,timeout=30)
resp = session.post(url=url, params=config.data, headers=config.headers, timeout=30)
else:
resp = session.get(url=self.url,data=config.data ,headers=config.headers,timeout=30)
resp = session.get(url=url, data=config.data, headers=config.headers, timeout=30)
if resp.status_code == requests.codes.ok:
# 下载二进制文件
if self.types == "Android" or self.types == "iOS":
count = 0
progress_tmp = 0
time1 = time.time()
length = float(resp.headers['content-length'])
with open(self.cache_path, "wb") as f:
with open(file_path, "wb") as f:
for chunk in resp.iter_content(chunk_size = 512):
if chunk:
f.write(chunk)
@ -50,20 +110,23 @@ class DownloadThreads(threading.Thread):
progress = int(count / length * 100)
if progress != progress_tmp:
progress_tmp = progress
print("\r", end="")
print("[*] Download progress: {}%: ".format(progress), "" * (progress // 2), end="")
logging.info("\r", end="")
logging.info("[*] Download progress: {}%: ".format(progress), "" * (progress // 2), end="")
sys.stdout.flush()
f.close()
else:
html = resp.text
with open(self.cache_path,"w",encoding='utf-8',errors='ignore') as f:
with open(file_path,"w",encoding='utf-8',errors='ignore') as f:
f.write(html)
f.close()
cores.download_flag = True
else:
logging.error("[x] {} download fails, status code is {} !!!".format(url, str(resp.status_code)))
except Exception as e:
raise Exception(e)
return
logging.error("[x] {} download fails, the following exception information:".format(url))
logging.exception(e)
def run(self):
threadLock = threading.Lock()
self.__requset__()
self.__start__()

@ -4,6 +4,7 @@
# Github: https://github.com/kelvinBen/AppInfoScanner
import re
import time
import logging
import threading
import requests
import libs.core as cores
@ -27,20 +28,22 @@ class NetThreads(threading.Thread):
url_ip = domains["url_ip"]
time.sleep(2)
result = self.__get_request_result__(url_ip)
print("[+] Processing URL address:"+url_ip)
logging.info("[+] " + url_ip)
if result != "error":
if self.lock.acquire(True):
cores.excel_row = cores.excel_row + 1
self.worksheet.write(cores.excel_row, 0, label = cores.excel_row)
self.worksheet.write(cores.excel_row, 1, label = url_ip)
self.worksheet.write(cores.excel_row, 2, label = domain)
self.worksheet.cell(row=cores.excel_row, column=1).value = cores.excel_row
self.worksheet.cell(row=cores.excel_row, column=2).value = url_ip
self.worksheet.cell(row=cores.excel_row, column=3).value = domain
if result != "timeout":
self.worksheet.write(cores.excel_row, 3, label = result["status"])
self.worksheet.write(cores.excel_row, 4, label = result["des_ip"])
self.worksheet.write(cores.excel_row, 5, label = result["server"])
self.worksheet.write(cores.excel_row, 6, label = result["title"])
self.worksheet.write(cores.excel_row, 7, label = result["cdn"])
# self.worksheet.write(cores.excel_row, 8, label = "")
self.worksheet.cell(row=cores.excel_row, column=4).value = result["status"]
self.worksheet.cell(row=cores.excel_row, column=5).value = result["des_ip"]
self.worksheet.cell(row=cores.excel_row, column=6).value = result["server"]
self.worksheet.cell(row=cores.excel_row, column=7).value = result["title"]
self.worksheet.cell(row=cores.excel_row, column=8).value = result["cdn"]
self.worksheet.cell(row=cores.excel_row, column=9).value = ""
self.lock.release()
def __get_request_result__(self,url):

@ -6,6 +6,7 @@
import re
import os
import config
import logging
import threading
import libs.core as cores
@ -38,9 +39,8 @@ class ParsesThreads(threading.Thread):
def __get_string_by_iOS__(self,file_path):
output_path = cores.output_path
strings_path = cores.strings_path
temp = os.path.join(output_path,"temp.txt")
cmd_str = ('"%s" "%s" > "%s"') % (str(strings_path),str(file_path),str(temp))
cmd_str = ('"%s" "%s" > "%s"') % (str(cores.strings_file),str(file_path),str(temp))
if os.system(cmd_str) == 0:
with open(temp,"r",encoding='utf-8',errors='ignore') as f:
lines = f.readlines()
@ -59,7 +59,7 @@ class ParsesThreads(threading.Thread):
akAndSkList = re.compile(r'.*accessKeyId.*".*"|.*accessKeySecret.*".*"|.*secret.*".*"').findall(file_content)
for akAndSk in akAndSkList:
self.result_list.append(akAndSk.strip())
print("[+] AK or SK in:",akAndSk.strip())
logging.info("[+] AK or SK in:",akAndSk.strip())
# 遍历所有的字符串
for result in set(results):
@ -80,7 +80,7 @@ class ParsesThreads(threading.Thread):
self.threadLock.acquire()
if cores.all_flag:
print("[+] The string searched for matching rule is: %s" % (resl_str))
logging.info("[+] String : {}".format(resl_str))
self.result_list.append(resl_str)
self.threadLock.release()
continue

@ -5,6 +5,7 @@
import os
import re
import config
import logging
import hashlib
from queue import Queue
import libs.core as cores
@ -12,14 +13,14 @@ import libs.core as cores
class AndroidTask(object):
def __init__(self,path,package):
self.path = path
def __init__(self, file_path, package):
self.input_file_path = file_path
self.package = package
self.file_queue = Queue()
self.shell_flag=False
self.packagename=""
self.comp_list=[]
self.file_identifier=[]
self.shell_flag = False
self.packagename = ""
self.comp_list = []
self.file_identifier = []
def start(self):
# 检查java环境是否存在
@ -37,8 +38,6 @@ class AndroidTask(object):
return {"comp_list":self.comp_list,"shell_flag":self.shell_flag,"file_queue":self.file_queue,"packagename":self.packagename,"file_identifier":self.file_identifier}
def __decode_file__(self,file_path):
apktool_path = str(cores.apktool_path)
backsmali_path = str(cores.backsmali_path)
base_out_path = str(cores.output_path)
filename = os.path.basename(file_path)
suffix_name = filename.split(".")[-1]
@ -46,7 +45,7 @@ class AndroidTask(object):
if suffix_name == "apk":
name = filename.split(".")[0]
output_path = os.path.join(base_out_path,name)
self.__decode_apk__(file_path,apktool_path,output_path)
self.__decode_apk__(file_path,output_path)
elif suffix_name == "dex":
f = open(file_path,'rb')
md5_obj = hashlib.md5()
@ -60,7 +59,7 @@ class AndroidTask(object):
output_path = os.path.join(base_out_path,dex_md5)
if not os.path.exists(output_path):
os.makedirs(output_path)
self.__decode_dex__(file_path,backsmali_path,output_path)
self.__decode_dex__(file_path,output_path)
else:
return "error"
@ -75,23 +74,25 @@ class AndroidTask(object):
continue
# 分解apk
def __decode_apk__(self,file_path,apktool_path,output_path):
cmd_str = ('java -jar "%s" d -f "%s" -o "%s" --only-main-classe') % (str(apktool_path),str(file_path),str(output_path))
def __decode_apk__(self,file_path,output_path):
cmd_str = ('java -jar "%s" d -f "%s" -o "%s" --only-main-classe') % (cores.apktool_file,str(file_path),str(output_path))
logging.debug("[*] cmd {}".format(cmd_str))
if os.system(cmd_str) == 0:
self.__shell_test__(output_path)
self.__scanner_file_by_apktool__(output_path)
else:
print("[-] Decompilation failed, please submit error information at https://github.com/kelvinBen/AppInfoScanner/issues")
logging.error("[x] Decompilation failed, please submit error information at https://github.com/kelvinBen/AppInfoScanner/issues")
raise Exception(file_path + ", Decompilation failed.")
# 分解dex
def __decode_dex__(self,file_path,backsmali_path,output_path):
cmd_str = ('java -jar "%s" d "%s"') % (str(backsmali_path),str(file_path))
def __decode_dex__(self,file_path,output_path):
cmd_str = ('java -jar "%s" d "%s"') % (cores.backsmali_file,str(file_path))
logging.debug("[*] cmd {}".format(cmd_str))
if os.system(cmd_str) == 0:
self.__get_scanner_file__(output_path)
else:
print("[-] Decompilation failed, please submit error information at https://github.com/kelvinBen/AppInfoScanner/issues")
logging.error("[x] Decompilation failed, please submit error information at https://github.com/kelvinBen/AppInfoScanner/issues")
raise Exception(file_path + ", Decompilation failed.")

@ -5,6 +5,7 @@
import os
import re
import config
import logging
import threading
from queue import Queue
import libs.core as cores
@ -13,110 +14,154 @@ from libs.task.web_task import WebTask
from libs.task.net_task import NetTask
from libs.core.parses import ParsesThreads
from libs.task.android_task import AndroidTask
from libs.task.download_task import DownloadTask
from libs.core.download import DownloadThreads
class BaseTask(object):
thread_list =[]
result_dict = {}
app_history_list=[]
domain_history_list=[]
# 统一初始化入口
def __init__(self, types="Android", inputs="", rules="", sniffer=True, threads=10, package=""):
self.types = types
self.path = inputs
if rules:
config.filter_strs.append(r'.*'+str(rules)+'.*')
self.sniffer = not sniffer
self.threads = threads
self.package = package
def __init__(self):
if cores.user_add_rules:
config.filter_strs.append(r'.*'+str(cores.user_add_rules)+'.*')
self.file_queue = Queue()
# 文件下载队列
self.download_file_queue = Queue()
# 文件下载列表
self.download_file_list = []
self.thread_list = []
self.app_history_list= []
self.domain_history_list = []
self.result_dict = {}
# 统一调度平台
def start(self):
print("[*] AI is analyzing filtering rules......")
# 统一启动
def start(self, types="Android", user_input_path="", package=""):
# 如果输入路径为目录,且类型非web,则自动检索DEX、IPA、APK等文件
if not(types == "Web") and os.path.isdir(user_input_path):
self.__scanner_specified_file__(user_input_path)
# 如果输入的路径为txt, 则加载txt中的内容实现批量操作
elif user_input_path.endswith("txt"):
with open(user_input_path) as f:
lines = f.readlines()
for line in lines:
# http:// 或者 https:// 开头 或者 apk/dex/ipa结尾的文件且文件存在
if (line.startswith("http://") or line.startswith("https://")) or ((line.endswith("apk") or line.endswith(".dex") or line.endswith("ipa")) and os.path.exists(line)):
self.download_file_queue.put(line)
f.close()
else:
# 如果是文件或者类型为web的目录
self.download_file_queue.put(user_input_path)
# 获取历史记录
self.__history_handle__()
# 长度小于1需重新选择目录
if self.download_file_queue.qsize() < 1:
raise Exception('[x] The specified DEX, IPA and APK files are not found. Please re-enter the directory to be scanned!')
print("[*] The filtering rules obtained by AI are as follows: %s" % (set(config.filter_no)) )
# 统一文件下载中心
self.__download_file_center__(types)
for download_file in self.download_file_list:
file_path = download_file["path"]
types = download_file["type"]
# 控制中心
self.__control_center__(file_path, types)
# 统一文件下载中心
def __download_file_center__(self,types):
# 杜绝资源浪费
if self.download_file_queue.qsize() < cores.threads_num:
threads_num = self.download_file_queue.qsize()
else:
threads_num = cores.threads_num
for threadID in range(1, threads_num):
threadName = "Thread - " + str(int(threadID))
thread = DownloadThreads(threadID, threadName, self.download_file_queue, self.download_file_list, types)
thread.start()
thread.join()
# 控制中心
def __control_center__(self, file_path, types):
logging.info("[*] Processing {}".format(file_path))
logging.info("[*] AI is analyzing filtering rules......")
# 处理历史记录
self.__history_handle__()
logging.info("[*] The filtering rules obtained by AI are as follows: {}".format(set(config.filter_no)))
# 任务控制中心
task_info = self.__tast_control__()
task_info = self.__tast_control__(file_path, types)
if len(task_info) < 1:
return
return
# 文件队列
file_queue = task_info["file_queue"]
# 是否存在壳
shell_flag = task_info["shell_flag"]
# 组件列表(仅适用于Android)
comp_list = task_info["comp_list"]
# 报名信息(仅适用于Android)
packagename = task_info["packagename"]
# 文件标识符
file_identifier = task_info["file_identifier"]
if shell_flag:
print('[-] \033[3;31m Error: This application has shell, the retrieval results may not be accurate, Please remove the shell and try again!')
logging.error('[x] This application has shell, the retrieval results may not be accurate, Please remove the shell and try again!')
return
# 线程控制中心
print("[*] ========= Searching for strings that match the rules ===============")
logging.info("[*] ========= Searching for strings that match the rules ===============")
self.__threads_control__(file_queue)
# 等待线程结束
for thread in self.thread_list:
thread.join()
# 结果输出中心
self.__print_control__(packagename,comp_list,file_identifier)
def __tast_control__(self):
# 任务控制中心
def __tast_control__(self, file_path, types):
task_info = {}
# 自动根据文件后缀名称进行修正
cache_info = DownloadTask().start(self.path,self.types)
cacar_path = cache_info["path"]
types = cache_info["type"]
if (not os.path.exists(cacar_path) and cores.download_flag):
print("[-] File download failed! Please download the file manually and try again.")
# 通过网络下载的文件如果不存在就直接返回任务控制中心
if (not os.path.exists(file_path) and cores.download_flag):
logging.error("[x] {} download failed! Please download the file manually and try again.".format(file_path))
return task_info
# 调用Android 相关处理逻辑
if types == "Android":
task_info = AndroidTask(cacar_path,self.package).start()
task_info = AndroidTask(file_path, self.package).start()
# 调用iOS 相关处理逻辑
elif types == "iOS":
task_info = iOSTask(cacar_path).start()
task_info = iOSTask(file_path).start()
# 调用Web 相关处理逻辑
else:
task_info = WebTask(cacar_path).start()
task_info = WebTask(file_path).start()
return task_info
# 线程控制中心
def __threads_control__(self,file_queue):
for threadID in range(1,self.threads):
for threadID in range(1, cores.threads_num):
name = "Thread - " + str(int(threadID))
thread = ParsesThreads(threadID,name,file_queue,self.result_dict,self.types)
thread.start()
self.thread_list.append(thread)
def __print_control__(self,packagename,comp_list,file_identifier):
txt_result_path = cores.txt_result_path
xls_result_path = cores.xls_result_path
all_flag = cores.all_flag
if self.sniffer:
print("[*] ========= Sniffing the URL address of the search ===============")
NetTask(self.result_dict,self.app_history_list,self.domain_history_list,file_identifier,self.threads).start()
# 信息输出中心
def __print_control__(self,packagename,comp_list,file_identifier):
if cores.net_sniffer_flag:
logging.info("[*] ========= Sniffing the URL address of the search ===============")
NetTask(self.result_dict,self.app_history_list,self.domain_history_list,file_identifier).start()
if packagename:
print("[*] ========= The package name of this APP is: ===============")
print(packagename)
logging.info("[*] ========= The package name of this APP is: ===============")
logging.info(packagename)
if len(comp_list) != 0:
print("[*] ========= Component information is as follows :===============")
logging.info("[*] ========= Component information is as follows :===============")
for json in comp_list:
print(json)
logging.info(json)
if all_flag:
if cores.all_flag:
value_list = []
with open(txt_result_path,"a+",encoding='utf-8',errors='ignore') as f:
for key,value in self.result_dict.items():
@ -127,11 +172,12 @@ class BaseTask(object):
value_list.append(result)
f.write("\t"+result+"\r")
f.close()
print("[*] For more information about the search, see TXT file result: %s" %(txt_result_path))
logging.info("[>] For more information about the search, see TXT file result: {}".format(cores.txt_result_path))
if self.sniffer:
print("[*] For more information about the search, see XLS file result: %s" %(xls_result_path))
if cores.net_sniffer_flag:
logging.info("[>] For more information about the search, see XLS file result: {}".format(cores.xls_result_path))
# 获取历史记录
def __history_handle__(self):
domain_history_path = cores.domain_history_path
app_history_path = cores.app_history_path
@ -158,5 +204,14 @@ class BaseTask(object):
if domain_count >= cout:
config.filter_no.append(".*" + domain)
f.close()
# 扫描指定后缀文件
def __scanner_specified_file__(self, base_dir, file_suffix=['dex','ipa','apk']):
files = os.listdir(base_dir)
for file in files:
dir_or_file_path = os.path.join(base_dir,file)
if os.path.isdir(dir_or_file_path):
self.__scanner_specified_file__(dir_or_file_path,file_suffix)
else:
if dir_or_file_path.split(".")[-1] in file_suffix:
self.download_file_queue.put(dir_or_file_path)

@ -7,40 +7,72 @@ import re
import time
import config
import hashlib
import logging
from queue import Queue
import libs.core as cores
from libs.core.download import DownloadThreads
class DownloadTask(object):
def __init__(self):
self.download_file_queue = Queue()
self.thread_list = []
def start(self,path,types):
def start(self, path, types):
self.__local_or_remote__(path, types)
for threadID in range(1, cores.threads_num):
name = "Thread - " + str(int(threadID))
thread = DownloadThreads(threadID,name,self.download_file_queue)
thread.start()
thread.join()
# 判断文件是本地加载还是远程加载
def __local_or_remote__(self,path,types):
# 添加文件后缀判断
self.__update_type__(path)
# 处理本地文件
if not(path.startswith("http://") or path.startswith("https://")):
if not os.path.isdir(path): # 不是目录
return {"path":path,"type":types}
else: # 目录处理
return {"path":path,"type":types}
else:
self.__net_header__(path,types)
# self.download_file_queue.put(path)
# 处理网络请求
def __net_header__(self, path, types):
create_time = time.strftime("%Y%m%d%H%M%S", time.localtime())
if path.endswith("apk"):
if path.endswith("apk") or types == "Android":
types = "Android"
file_name = create_time+ ".apk"
elif path.endswith("ipa"):
elif path.endswith("ipa") or types == "iOS":
types = "iOS"
file_name = create_time + ".ipa"
else:
if types == "Android":
types = "Android"
types = "WEB"
file_name = create_time + ".html"
logging.info("[*] Detected that the task is not local, preparing to download file......")
cache_path = os.path.join(cores.download_dir, file_name)
self.download_file_queue.put({"path":path, "cache_path":cache_path, "types":types})
# thread = DownloadThreads(path,file_name,cache_path,types)
# thread.start()
# thread.join()
return {"path":cache_path,"type":types}
def __update_type__(self, path, types, file_name=None):
create_time = time.strftime("%Y%m%d%H%M%S", time.localtime())
if path.endswith("apk") or types == "Android":
types = "Android"
if not file_name:
file_name = create_time+ ".apk"
elif types == "iOS":
types = "iOS"
elif path.endswith("ipa") or types == "iOS":
types = "iOS"
if not file_name:
file_name = create_time + ".ipa"
else:
types = "WEB"
file_name = create_time + ".html"
if not(path.startswith("http://") or path.startswith("https://")):
if not os.path.isdir(path): # 不是目录
return {"path":path,"type":types}
else: # 目录处理
return {"path":path,"type":types}
else:
print("[*] Detected that the task is not local, preparing to download file......")
cache_path = os.path.join(cores.download_path, file_name)
thread = DownloadThreads(path,file_name,cache_path,types)
thread.start()
thread.join()
print()
return {"path":cache_path,"type":types}
types = "WEB"
if not file_name:
file_name = create_time + ".html"
return types,file_name

@ -3,8 +3,6 @@
# Author: kelvinBen
# Github: https://github.com/kelvinBen/AppInfoScanner
import os
import re
import shutil
import zipfile
import binascii
import platform
@ -23,45 +21,31 @@ class iOSTask(object):
file_path = self.path
if file_path.split(".")[-1] == 'ipa':
self.__decode_ipa__(cores.output_path)
self.__scanner_file_by_ipa__(cores.output_path)
elif self.__get_file_header__(file_path):
self.file_queue.put(file_path)
else:
raise Exception("Retrieval of this file type is not supported. Select IPA file or Mach-o file.")
return {"shell_flag":self.shell_flag,"file_queue":self.file_queue,"comp_list":[],"packagename":None,"file_identifier":self.file_identifier}
def __get_file_header__(self,file_path):
hex_hand = 0x0
crypt_load_command_hex = "2C000000"
macho_name = os.path.split(file_path)[-1]
self.file_identifier.append(macho_name)
with open(file_path,"rb") as macho_file:
macho_file.seek(hex_hand,0)
macho_file.seek(0x0,0)
magic = binascii.hexlify(macho_file.read(4)).decode().upper()
macho_magics = ["CFFAEDFE","CEFAEDFE","BEBAFECA","CAFEBABE"]
if magic in macho_magics:
self.__shell_test__(macho_file,hex_hand)
hex_str = binascii.hexlify(macho_file.read()).decode().upper()
if crypt_load_command_hex in hex_str:
macho_file.seek(int(hex_str.index("2C000000")/2)+20,0)
cryptid = binascii.hexlify(macho_file.read(4)).decode()
if cryptid == "01000000":
self.shell_flag = True
macho_file.close()
return True
macho_file.close()
return False
def __shell_test__(self,macho_file,hex_hand):
while True:
magic = binascii.hexlify(macho_file.read(4)).decode().upper()
if magic == "2C000000":
macho_file.seek(hex_hand,0)
encryption_info_command = binascii.hexlify(macho_file.read(24)).decode()
cryptid = encryption_info_command[-8:len(encryption_info_command)]
if cryptid == "01000000":
self.shell_flag = True
break
hex_hand = hex_hand + 4
def __scanner_file_by_ipa__(self,output):
scanner_file_suffix = ["plist","js","xml","html"]
scanner_dir = os.path.join(output,"Payload")
self.__get_scanner_file__(scanner_dir,scanner_file_suffix)
def __get_scanner_file__(self,scanner_dir,file_suffix):
dir_or_files = os.listdir(scanner_dir)
@ -84,41 +68,24 @@ class iOSTask(object):
self.file_queue.put(dir_file_path)
def __decode_ipa__(self,output_path):
scanner_file_suffix = ["plist","js","xml","html"]
scanner_dir = os.path.join(output_path,"Payload")
with zipfile.ZipFile(self.path,"r") as zip_files:
zip_file_names = zip_files.namelist()
zip_files.extract(zip_file_names[0],output_path)
try:
new_zip_file = zip_file_names[0].encode('cp437').decode('utf-8')
except UnicodeEncodeError:
new_zip_file = zip_file_names[0].encode('utf-8').decode('utf-8')
old_zip_dir = self.__get_parse_dir__(output_path,zip_file_names[0])
new_zip_dir = self.__get_parse_dir__(output_path,new_zip_file)
os.rename(old_zip_dir,new_zip_dir)
for zip_file in zip_file_names:
old_ext_path = zip_files.extract(zip_file,output_path)
start = str(old_ext_path).index("Payload")
dir_path = old_ext_path[start:len(old_ext_path)]
old_ext_path = os.path.join(output_path,dir_path)
for zip_file_name in zip_file_names:
try:
new_zip_file = zip_file.encode('cp437').decode('utf-8')
if platform.system() == "Windows":
new_file_name = zip_file_name.encode('cp437').decode('GBK')
else:
new_file_name = zip_file_name.encode('cp437').decode('utf-8')
except UnicodeEncodeError:
new_zip_file = zip_file.encode('utf-8').decode('utf-8')
new_ext_path = os.path.join(output_path,new_zip_file)
if platform.system() == "Windows":
new_ext_path = new_ext_path.replace("/","\\")
if not os.path.exists(new_ext_path):
dir_path = os.path.dirname(new_ext_path)
if not os.path.exists(dir_path):
os.makedirs(dir_path)
shutil.move(old_ext_path, new_ext_path)
if os.path.exists(old_ext_path):
os.remove(old_ext_path)
new_file_name = zip_file_name.encode('utf-8').decode('utf-8')
new_ext_file_path = os.path.join(output_path,new_file_name)
ext_file_path = zip_files.extract(zip_file_name,output_path)
os.rename(ext_file_path,new_ext_file_path)
self.__get_scanner_file__(scanner_dir,scanner_file_suffix)
def __get_parse_dir__(self,output_path,file_path):
start = file_path.index("Payload/")

@ -2,32 +2,29 @@
# -*- coding: utf-8 -*-
# Author: kelvinBen
# Github: https://github.com/kelvinBen/AppInfoScanner
import re
import xlwt
import socket
import config
from queue import Queue
import libs.core as cores
from openpyxl import Workbook
from libs.core.net import NetThreads
import requests
class NetTask(object):
value_list = []
domain_list=[]
def __init__(self,result_dict,app_history_list,domain_history_list,file_identifier,threads):
def __init__(self,result_dict,app_history_list,domain_history_list,file_identifier):
self.result_dict = result_dict
self.app_history_list = app_history_list
self.domain_history_list = domain_history_list
self.file_identifier = file_identifier
self.domain_queue = Queue()
self.threads = int(threads)
self.thread_list = []
self.domain_history_list = domain_history_list
def start(self):
xls_result_path = cores.xls_result_path
workbook = xlwt.Workbook(encoding = 'utf-8')
workbook = Workbook()
worksheet = self.__creating_excel_header__(workbook)
self.__write_result_to_txt__()
@ -40,17 +37,12 @@ class NetTask(object):
workbook.save(xls_result_path)
def __creating_excel_header__(self,workbook):
worksheet = workbook.add_sheet("Result",cell_overwrite_ok=True)
worksheet.write(0,0, label = "Number")
worksheet.write(0,1, label = "IP/URL")
worksheet.write(0,2, label = "Domain")
worksheet.write(0,3, label = "Status")
worksheet.write(0,4, label = "IP")
worksheet.write(0,5, label = "Server")
worksheet.write(0,6, label = "Title")
worksheet.write(0,7, label = "CDN")
# worksheet.write(0,8, label = "Finger")
return worksheet
worksheet = workbook.create_sheet("Result",0)
excel_headers = ["Number","IP/URL","Domain","Status","IP","Server","Title","CDN","Finger"]
for head_cell in excel_headers:
column = excel_headers.index(head_cell) + 1
worksheet.cell(row=1, column=column).value = head_cell
return worksheet
def __write_result_to_txt__(self):
txt_result_path = cores.txt_result_path
@ -97,7 +89,7 @@ class NetTask(object):
append_file_flag = False
def __start_threads__(self,worksheet):
for threadID in range(0,self.threads) :
for threadID in range(0, cores.threads_num):
name = "Thread - " + str(threadID)
thread = NetThreads(threadID,name,self.domain_queue,worksheet)
thread.start()

@ -4,6 +4,7 @@
# Github: https://github.com/kelvinBen/AppInfoScanner
import os
import config
import hashlib
from queue import Queue
class WebTask(object):
@ -39,7 +40,7 @@ class WebTask(object):
else:
if len(dir_file.split("."))>1:
if dir_file.split(".")[-1] in file_suffix:
with open(file_path,'rb') as f:
with open(dir_file_path,'rb') as f:
dex_md5 = str(hashlib.md5().update(f.read()).hexdigest()).upper()
self.file_identifier.append(dex_md5)
self.file_queue.put(dir_file_path)

@ -1,3 +1,5 @@
requests
click
xlwt
xlwt
pillow
openpyxl

@ -1,7 +1,15 @@
### V1.0.9
- 新增IPA批量操作
- 优化iOS壳检测速度
- 优化iPA文件解压效率
- 优化日志输出
- 修复内容过长无法输出到excle
### V1.0.8
- 添加AK和SK的检测
- 添加检测规则提交入口
- 添加.gitignore文件
- 新增AK和SK的检测
- 新增检测规则提交入口
- 新增.gitignore文件
- 优化txt结果集输出方式
- 修复目录中包含空格无法解析的问题
- 修复WEB页面或者目录扫描的问题

Loading…
Cancel
Save