MobSF批量搜索关键字脚本

import requests
import json
# 设置Mobsf API的URL地址和密钥
base_url='http://127.0.0.1:8000/'
api_url = base_url+'api/v1/'
api_key = ''
# 构建API请求的头信息
headers = {'Authorization': api_key}
#curl --url "http://localhost:8000/api/v1/scans?page=1&page_size=10" -H "X-Mobsf-Api-Key:xxxxxxxxx"
# 发送API请求，获取Mobsf前100项扫描结果
r = requests.get(api_url + 'scans?page=1&page_size=90', headers=headers)
#scan_id = r.json()['content'][0]['FILE_NAME']
jslen=len(r.json()['content'])
proxies={'http':'127.0.0.1:8080'}
keywords="guess"
for j in range(jslen):
    appmd5 = r.json()['content'][j]['MD5']
    datas = {'hash': appmd5}
    url = base_url+"find/"
    # 参数拼凑,附件上传格式如picurl参数，其他表单参数值拼成tuple格式：
    proxies = {
        "http": "127.0.0.1:8080"
    }
    headers = {
        "Content-Type": "multipart/form-data; boundary=----WebKitFormBoundaryjvmMdroaobco6uyJ"
    }
    md5 =appmd5
    datas = """------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="md5"\r\n\r\n"""+md5+"""\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="q"\r\n\r\n"""+keywords+"""\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="code"\r\n\r\njava\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="search_type"\r\n\r\ncontent\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="api"\r\n\r\ntrue\r\n\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ--"""
    res = requests.post(url, data=datas, headers=headers)
    if(res.status_code==500):
        continue
    js=json.loads(res.json())
    if (len(js['matches'])>=1):
        print(r.json()['content'][j]['FILE_NAME']+" is matched keywords: "+keywords)
    # else:
    #     print(r.json()['content'][j]['FILE_NAME']+" is not matched")
    for i in range(len(js['matches'])):
        print("   "+js['matches'][i])

自用，大家自行修改

import requests
import json

# 设置 MobSF API 的 URL 地址和密钥
base_url = 'http://127.0.0.1:8000/'
api_url = base_url + 'api/v1/'
api_key = ''
headers = {'Authorization': api_key}

# 发送 API 请求，获取 MobSF 前 90 项扫描结果
response = requests.get(api_url + 'scans?page=1&page_size=90', headers=headers)
scan_results = response.json()['content']

# 搜索关键字
keywords = "HQ9"
proxies = {'http': '127.0.0.1:8080'}
multipart_boundary = '----WebKitFormBoundaryjvmMdroaobco6uyJ'

# 遍历每个扫描结果
for scan in scan_results:
    appmd5 = scan['MD5']
    url = base_url + "find/"

    # 构建 multipart/form-data 数据
    multipart_data = f"""\
{multipart_boundary}\r
Content-Disposition: form-data; name="md5"\r\n\r\n{appmd5}\r
{multipart_boundary}\r
Content-Disposition: form-data; name="q"\r\n\r\n{keywords}\r
{multipart_boundary}\r
Content-Disposition: form-data; name="code"\r\n\r\njava\r
{multipart_boundary}\r
Content-Disposition: form-data; name="search_type"\r\n\r\ncontent\r
{multipart_boundary}\r
Content-Disposition: form-data; name="api"\r\n\r\ntrue\r
{multipart_boundary}--"""

    # 发送 POST 请求进行关键词搜索
    try:
        with requests.post(url, data=multipart_data, headers={
            'Content-Type': f'multipart/form-data; boundary={multipart_boundary}'
        }, proxies=proxies) as res:
            # 检查是否有匹配的关键词
            if res.status_code == 500:
                continue

            result_json = res.json()
            if 'matches' in result_json and len(result_json['matches']) >= 1:
                print(f"{scan['FILE_NAME']} is matched keywords: {keywords}")
                for match in result_json['matches']:
                    print(f"   {match}")
    except requests.RequestException as e:
        print(f"Error processing {scan['FILE_NAME']}: {e}")

主要优化：
简化响应处理：避免在循环中多次调用 r.json()，改为在开始时一次性解析。
上下文管理：使用 with 语句发送 POST 请求，确保请求完成后会自动关闭连接。
字符串格式化：简化 multipart/form-data 的拼接，通过 Python 的格式化方法来动态生成请求数据。
异常处理：增加了 try-except 块，捕获可能的请求异常，防止程序因网络问题崩溃。
这样可以提升代码的性能、可读性和安全性。

2024-11-14：

mobsf添加了鉴权系统，没有api接口，懒得模拟登录获取cookie,已更新

import requests
import json

# MobSF API URL&key
base_url = 'http://127.0.0.1:8000/'
api_url = base_url + 'api/v1/'
#你的API key
api_key = ''

# Define headers for the API request
# 你的cookie
headers = {
    'Authorization': api_key,
    'Cookie': "sessionid=4yvpf33vmdv6azqb7swmkya8cm6nt3qb"
}

# Define proxy
proxies = {
    "http": "http://127.0.0.1:8080"
}

# Set the keyword to search你的关键字
keyword = 'password'

try:
    # Request to get the first 250 scan results
    r = requests.get(api_url + 'scans?page=1&page_size=250', headers=headers)
    r.raise_for_status()
    scan_results = r.json().get('content', [])
    
    for scan in scan_results:
        app_md5 = scan['MD5']
        file_name = scan['FILE_NAME']
        
        # Set data payload for searching
        data_payload = f"""------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="md5"\r\n\r\n{app_md5}\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="q"\r\n\r\n{keyword}\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="code"\r\n\r\njava\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="search_type"\r\n\r\ncontent\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ\r\nContent-Disposition: form-data; name="api"\r\n\r\ntrue\r\n------WebKitFormBoundaryjvmMdroaobco6uyJ--"""
        
        # Define headers for search API
        search_headers = {
            "Content-Type": "multipart/form-data; boundary=----WebKitFormBoundaryjvmMdroaobco6uyJ",
            "Authorization": api_key,
            "Cookie": "sessionid=4yvpf33vmdv6azqb7swmkya8cm6nt3qb"
        }
        
        # Send POST request to search for keyword
        search_url = base_url + "find/"
        res = requests.post(search_url, data=data_payload, headers=search_headers)
        
        # Handle cases with 500 status code and other errors
        if res.status_code == 500:
            print(f"Server error for file: {file_name}")
            continue
        
        # Process response
        response_text = res.text  # get raw response text
        try:
            # Decode the JSON-encoded string twice
            # First to convert the string literal into JSON format, then to parse as JSON
            response_json = json.loads(json.loads(response_text))
            matches = response_json.get('matches', [])
            
            if matches:
                print(f"{file_name} is matched with keyword: {keyword}")
                for match in matches:
                    print("   " + match)
            else:
                pass
        
        except json.JSONDecodeError:
            print(f"Failed to parse JSON response for file: {file_name} - Response: {response_text}")
    print("---------------------------------------------------")
except requests.exceptions.RequestException as e:
    print("Error with API request:", e)

由chatgpt优化