DeepseekScanner deepseek+python实现代码审计实战

//支持只扫描指定的文件后缀比如.php 只扫描.php文件 也可以扫描全部的文件类型def scan_directory(directory, file_types=None, scan_all=False):    try:        if scan_all:            files_to_scan = [os.path.join(root, file) for root, _, files in os.walk(directory) for file in files]        else:            files_to_scan = [os.path.join(root, file) for root, _, files in os.walk(directory) for file in files if                             any(file.endswith(ft) for ft in file_types)]        # Saving results to file        scan_results = []        filename = f"scan_results.txt"        directory = "./"        filepath = os.path.join(directory, filename)        for file_path in tqdm(files_to_scan, desc="Scanning files"):            file_scan_results = scan_file(file_path, scan_results, directory)            if file_scan_results is not None and len(file_scan_results) > 0:                save_results_to_file(filepath, file_scan_results)    except Exception as e:        print(e)

//从项目中的各个目录提取代码文件后，开始对代码进行切片发送给deepseek做安全审计def scan_file(file_path, scan_results, directory):    try:        with open(file_path, 'r') as file:            content = file.readlines()        total_chunks = (len(content) - 1) // 100 + 100        file_scan_results = []        for chunk_start in range(0, len(content), 100):            chunk_end = min(chunk_start + 100, len(content))            code_chunk = ''.join(content[chunk_start:chunk_end])            response = analyze_security(code_chunk)            if hasattr(response, 'content'):                results = response.content            elif isinstance(response, dict) and 'content' in response:                results = response['content']            else:                results = response            if results:                # Split the result into individual issues using "@@@@", it can be unreliable depending on the output of the model                individual_results = results.split('@@@@')                for result in individual_results:                    if "存在风险" in result:                        try:                            _, line_numbers, issue_description, code_snippet = result.split(' | ', 3)                            adjusted_line_numbers = line_numbers.strip()                            issue_description = issue_description.strip()                            code_snippet = code_snippet.strip()                            file_scan_results.append(                                (file_path, adjusted_line_numbers, issue_description, code_snippet))                        except ValueError:                            continue        # Append this file's results to the main scan_results        # scan_results.extend(file_scan_results)        return file_scan_results    except Exception as e:        print(e)    return None

//严格定义prompt为资深安全专家实现代码安全审计def analyze_security(content):    try:        completion = client.chat.completions.create(            model="deepseek-chat",  # field is not currently used in LM studio            messages=[                {"role": "system", "content": '''你是一个安全专家严格分析以下代码片段，检查其中是否存在安全漏洞，请详细分析'''},                {"role": "user", "content": content}            ],            temperature=0.7,        )        return completion.choices[0].message    except Exception as e:        print(e)    return None

//对项目中的所有代码进行安全审计python scanner.py E:\work\sqli-secound-order --all