generate_pdf.py

import os
import re
import markdown
from xhtml2pdf import pisa

def clean_for_pdf(text):
    """Replaces Unicode special characters with standard WinAnsi / Latin-1 compatible representations."""
    replacements = {
        '—': ' - ',
        '–': '-',
        '’': "'",
        '‘': "'",
        '“': '"',
        '”': '"',
        '…': '...',
        '🛡️': '[VULNSCAN]',
        '📑': '[INDEX]',
        '🔌': '[PORT SCAN]',
        '🌐': '[DNS ENUM]',
        '📋': '[WHOIS]',
        '🔒': '[SSL/TLS]',
        '💻': '[TECH DETECT]',
        '🌍': '[SUBDOMAINS]',
        '🔴': '<span class="badge badge-critical">CRITICAL</span>',
        '🟠': '<span class="badge badge-high">HIGH</span>',
        '🟡': '<span class="badge badge-medium">MEDIUM</span>',
        '🔵': '<span class="badge badge-low">LOW</span>',
        '⚪': '<span class="badge badge-info">INFO</span>',
        '✅': '<span style="color:#059669; font-weight:bold;">[PASSED]</span>',
        '❌': '<span style="color:#dc2626; font-weight:bold;">[MISSING]</span>',
        '⚠️': '<span style="color:#d97706; font-weight:bold;">[WARNING]</span>',
        '➔': ' -> ',
        '•': '&bull;',
    }
    for orig, rep in replacements.items():
        text = text.replace(orig, rep)
    return text

def convert_mindmap_to_html():
    return """<div class="diagram-card">
<div class="diagram-header"><strong>CORE ARCHITECTURAL PILLARS &amp; VISION</strong></div>
<table class="pillar-table">
<tr>
<td class="pillar-cell" style="width: 25%;">
<div class="pillar-title">1. Privacy First</div>
<ul class="pillar-list">
<li>100% Local Inference</li>
<li>Zero Cloud Leakage</li>
<li>Ollama Llama-3.2 Native</li>
</ul>
</td>
<td class="pillar-cell" style="width: 25%;">
<div class="pillar-title">2. Automated Recon</div>
<ul class="pillar-list">
<li>27 Port TCP Scanner</li>
<li>Multi-Record DNS Enum</li>
<li>WHOIS &amp; SSL/TLS Expiry</li>
<li>OWASP Security Headers</li>
<li>40+ Subdomain Probing</li>
</ul>
</td>
<td class="pillar-cell" style="width: 25%;">
<div class="pillar-title">3. AI Guardrails</div>
<ul class="pillar-list">
<li>Strict JSON Schema</li>
<li>Evidence Grounded</li>
<li>CVSS &amp; CVE Mapping</li>
<li>Remediation Guidance</li>
</ul>
</td>
<td class="pillar-cell" style="width: 25%;">
<div class="pillar-title">4. User Experience</div>
<ul class="pillar-list">
<li>Glassmorphism Dark UI</li>
<li>Interactive AI Tutor</li>
<li>NDJSON Live Streaming</li>
<li>Print-Ready PDF Reports</li>
</ul>
</td>
</tr>
</table>
</div>"""

def convert_flowchart_to_html():
    return """<div class="diagram-card">
<div class="diagram-header"><strong>SYSTEM ARCHITECTURE &amp; DATA FLOW TOPOLOGY</strong></div>
<table class="flow-table">
<tr>
<td class="flow-box" style="width: 30%;">
<div class="flow-box-title">LAYER 1: CLIENT BROWSER</div>
<div class="flow-box-desc">
- Cyberpunk Glassmorphism UI<br/>
- Real-Time NDJSON Parser<br/>
- Interactive Chat Tutor Modal<br/>
- Report PDF Export Generator
</div>
</td>
<td class="flow-arrow" style="width: 5%;">-></td>
<td class="flow-box" style="width: 30%;">
<div class="flow-box-title">LAYER 2: FASTAPI BACKEND</div>
<div class="flow-box-desc">
- Asynchronous API Gateway<br/>
- 8-Module Reconnaissance Engine<br/>
- Token Compactor &amp; Normalizer<br/>
- Pydantic Schema Validator
</div>
</td>
<td class="flow-arrow" style="width: 5%;">-></td>
<td class="flow-box" style="width: 30%;">
<div class="flow-box-title">LAYER 3: LOCAL AI ENGINE</div>
<div class="flow-box-desc">
- Ollama Daemon (Port 11434)<br/>
- Model: llama3.2:latest<br/>
- Zero-Cloud Network Egress<br/>
- Deterministic JSON Output
</div>
</td>
</tr>
</table>
</div>"""

def convert_sequence_to_html():
    return """<div class="diagram-card">
<div class="diagram-header"><strong>END-TO-END EXECUTION LIFECYCLE SEQUENCE</strong></div>
<table class="data-table" style="margin: 0;">
<thead>
<tr>
<th style="width: 8%;">Step</th>
<th style="width: 26%;">Origin -> Destination</th>
<th style="width: 38%;">Action / Payload</th>
<th style="width: 28%;">Security Context</th>
</tr>
</thead>
<tbody>
<tr><td><strong>01</strong></td><td>Analyst -> Frontend</td><td>Input Target Domain (e.g. <code>example.com</code>)</td><td>User initiates external reconnaissance</td></tr>
<tr><td><strong>02</strong></td><td>Frontend -> FastAPI</td><td><code>POST /api/recon</code></td><td>Asynchronous target dispatch</td></tr>
<tr><td><strong>03</strong></td><td>FastAPI -> Target Network</td><td>Parallel TCP Probing, DNS, SSL, Headers, WHOIS</td><td>Non-destructive defensive scanning</td></tr>
<tr><td><strong>04</strong></td><td>FastAPI -> Frontend</td><td>Full Recon JSON Payload (200 OK)</td><td>Visual module cards rendered</td></tr>
<tr><td><strong>05</strong></td><td>Frontend -> FastAPI</td><td><code>POST /api/analyze</code></td><td>Token compaction (&lt; 1,500 tokens)</td></tr>
<tr><td><strong>06</strong></td><td>FastAPI -> Ollama</td><td>Structured Prompt + JSON Schema Contract</td><td>Local CPU/GPU inference execution</td></tr>
<tr><td><strong>07</strong></td><td>FastAPI -> Frontend</td><td>NDJSON Progress Stream (15% -> 50% -> 100%)</td><td>Live streaming UI state update</td></tr>
<tr><td><strong>08</strong></td><td>Frontend</td><td>Render Findings Matrix &amp; PDF Report</td><td>Actionable remediation formulated</td></tr>
</tbody>
</table>
</div>"""

def convert_threat_to_html():
    return """<div class="diagram-card">
<div class="diagram-header"><strong>APPLICATION THREAT MODEL &amp; TRUST BOUNDARIES</strong></div>
<table class="data-table" style="margin: 0;">
<thead>
<tr>
<th style="width: 22%;">Threat Vector</th>
<th style="width: 28%;">Potential Risk</th>
<th style="width: 25%;">Target Component</th>
<th style="width: 25%;">Mitigating Security Control</th>
</tr>
</thead>
<tbody>
<tr><td><strong>SSRF Injection</strong></td><td>Probing internal loopbacks or AWS metadata</td><td>Recon Socket &amp; DNS Engine</td><td>Strict hostname URI parsing &amp; protocol filter</td></tr>
<tr><td><strong>Prompt Injection</strong></td><td>Manipulating LLM output via crafted banners</td><td>Ollama Inference Worker</td><td>Fixed JSON Schema &amp; Evidence Grounding</td></tr>
<tr><td><strong>LLM Context DoS</strong></td><td>Huge banner payloads causing OOM / Hang</td><td>Token Compactor</td><td><code>MAX_RECON_CHARS = 12000</code> Buffer Capping</td></tr>
<tr><td><strong>Data Exfiltration</strong></td><td>Target recon telemetry leaking to 3rd parties</td><td>Network Perimeter</td><td>100% Offline Local Ollama Binding</td></tr>
<tr><td><strong>XSS in Reports</strong></td><td>Malicious script execution via target headers</td><td>Browser Frontend</td><td>Escaped DOM text rendering &amp; strict sanitization</td></tr>
</tbody>
</table>
</div>"""

def convert_gantt_to_html():
    return """<div class="diagram-card">
<div class="diagram-header"><strong>DEVELOPMENT ROADMAP &amp; MILESTONES</strong></div>
<table class="data-table" style="margin: 0;">
<thead>
<tr>
<th style="width: 16%;">Phase / Quarter</th>
<th style="width: 36%;">Deliverable Milestone</th>
<th style="width: 26%;">Core Focus Area</th>
<th style="width: 22%;">Status</th>
</tr>
</thead>
<tbody>
<tr><td><strong>2026 - Q3</strong></td><td>Active Subprocess Nuclei Template Integration</td><td>Core Scanner Engine</td><td><span class="badge badge-high">IN PROGRESS</span></td></tr>
<tr><td><strong>2026 - Q3</strong></td><td>CVE Live Database NVD API Synchronization</td><td>Vulnerability Intelligence</td><td><span class="badge badge-low">PLANNED</span></td></tr>
<tr><td><strong>2026 - Q4</strong></td><td>Model Switcher UI (Mistral 7B / Qwen 2.5)</td><td>AI Intelligence Layer</td><td><span class="badge badge-low">PLANNED</span></td></tr>
<tr><td><strong>2026 - Q4</strong></td><td>Automated Bash/Ansible Remediation Scripts</td><td>Automation &amp; Fixes</td><td><span class="badge badge-low">PLANNED</span></td></tr>
<tr><td><strong>2027 - Q1</strong></td><td>Multi-Scan SQLite / PostgreSQL Database</td><td>Enterprise Architecture</td><td><span class="badge badge-info">PROPOSED</span></td></tr>
<tr><td><strong>2027 - Q1</strong></td><td>Automated Server-Side PDF Export Engine</td><td>Reporting Infrastructure</td><td><span class="badge badge-info">COMPLETED</span></td></tr>
<tr><td><strong>2027 - Q2</strong></td><td>Webhook Alerting (Discord / Slack / Telegram)</td><td>Integrations &amp; SIEM</td><td><span class="badge badge-info">PROPOSED</span></td></tr>
</tbody>
</table>
</div>"""

def build_pdf(md_file="PROJECT_REPORT.md", pdf_file="VULNSCAN_Project_Report.pdf"):
    if not os.path.exists(md_file):
        print(f"Error: {md_file} does not exist.")
        return False
        
    with open(md_file, "r", encoding="utf-8") as f:
        raw_text = f.read()

    # Isolate main body starting cleanly from Section 1 (Executive Summary)
    exec_idx = raw_text.find("## 1. Executive Summary")
    if exec_idx != -1:
        md_body = raw_text[exec_idx:]
    else:
        md_body = raw_text

    # Clean characters
    md_body = clean_for_pdf(md_body)

    # Extract Mermaid diagrams and replace with non-markdown token placeholders
    diagram_replacements = {}
    diagram_counter = 0

    def extract_mermaid(match):
        nonlocal diagram_counter
        placeholder = f"XMERMAIDDIAG{diagram_counter}X"
        content = match.group(1).strip()
        if content.startswith('mindmap'):
            diagram_replacements[placeholder] = convert_mindmap_to_html()
        elif content.startswith('flowchart'):
            diagram_replacements[placeholder] = convert_flowchart_to_html()
        elif content.startswith('sequenceDiagram'):
            diagram_replacements[placeholder] = convert_sequence_to_html()
        elif content.startswith('graph'):
            diagram_replacements[placeholder] = convert_threat_to_html()
        elif content.startswith('gantt'):
            diagram_replacements[placeholder] = convert_gantt_to_html()
        else:
            diagram_replacements[placeholder] = f'<div class="diagram-card"><pre class="diagram-code">{content}</pre></div>'
        diagram_counter += 1
        return f"\n\n{placeholder}\n\n"

    md_body = re.sub(r'```mermaid(.*?)```', extract_mermaid, md_body, flags=re.DOTALL)

    # Convert markdown to html
    html_content = markdown.markdown(md_body, extensions=['tables', 'fenced_code'])

    # Re-insert diagram components into HTML
    for placeholder, diag_html in diagram_replacements.items():
        html_content = html_content.replace(f"<p>{placeholder}</p>", diag_html)
        html_content = html_content.replace(placeholder, diag_html)

    # Format screenshots
    cwd = os.getcwd().replace("\\", "/")
    html_content = re.sub(
        r'<img([^>]+)src="screenshots/([^"]+)"([^>]*)>',
        rf'<div class="screenshot-box"><img src="{cwd}/screenshots/\2" style="width: 440pt; height: auto;" /><div class="screenshot-label">System Visual Proof: \2</div></div>',
        html_content
    )

    html_doc = f"""<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>VULNSCAN Technical Architecture Report</title>
<style>
    @page cover_page {{
        size: a4 portrait;
        margin: 1.5cm;
        @frame content_frame {{
            left: 1.5cm; right: 1.5cm; top: 1.5cm; bottom: 1.5cm;
        }}
    }}

    @page main_page {{
        size: a4 portrait;
        margin: 2.0cm 1.5cm 1.8cm 1.5cm;
        @frame header_frame {{
            -pdf-frame-content: page_header;
            left: 1.5cm; right: 1.5cm; top: 0.8cm; height: 1cm;
        }}
        @frame content_frame {{
            left: 1.5cm; right: 1.5cm; top: 1.9cm; bottom: 1.8cm;
        }}
        @frame footer_frame {{
            -pdf-frame-content: page_footer;
            left: 1.5cm; right: 1.5cm; bottom: 0.7cm; height: 1cm;
        }}
    }}

    .cover-container {{
        page: cover_page;
        page-break-after: always;
    }}

    .main-body {{
        page: main_page;
    }}

    body {{
        font-family: Helvetica, Arial, sans-serif;
        color: #1e293b;
        font-size: 8.5pt;
        line-height: 1.4;
    }}
    
    .header-content {{
        font-size: 7pt;
        color: #64748b;
        border-bottom: 1px solid #cbd5e1;
        padding-bottom: 3px;
        font-family: Helvetica, Arial, sans-serif;
    }}
    
    .footer-content {{
        font-size: 7pt;
        color: #94a3b8;
        border-top: 1px solid #e2e8f0;
        padding-top: 3px;
        font-family: Helvetica, Arial, sans-serif;
    }}

    /* ── Cover Page Elements ── */
    .cover-hero {{
        background-color: #0f172a;
        color: #ffffff;
        padding: 22pt 18pt;
        border-radius: 6pt;
        margin-bottom: 16pt;
        border-left: 6pt solid #38bdf8;
    }}
    
    .cover-tag {{
        color: #38bdf8;
        font-size: 7.5pt;
        font-weight: bold;
        text-transform: uppercase;
        letter-spacing: 1.5px;
        margin-bottom: 5pt;
    }}
    
    .cover-title {{
        font-size: 20pt;
        font-weight: bold;
        color: #ffffff;
        line-height: 1.2;
        margin-bottom: 5pt;
    }}
    
    .cover-subtitle {{
        font-size: 10pt;
        color: #94a3b8;
        line-height: 1.35;
    }}
    
    .meta-box {{
        border: 1px solid #cbd5e1;
        border-radius: 4pt;
        padding: 10pt 14pt;
        background-color: #f8fafc;
        margin-bottom: 14pt;
    }}
    
    .meta-table {{
        width: 100%;
        border-collapse: collapse;
    }}
    
    .meta-table td {{
        border: none;
        padding: 3.5pt 5pt;
        font-size: 8pt;
        vertical-align: top;
    }}
    
    .meta-table td strong {{
        color: #0f172a;
    }}
    
    .abstract-box {{
        background-color: #f0f9ff;
        border: 1px solid #bae6fd;
        border-left: 4pt solid #0284c7;
        padding: 10pt 12pt;
        border-radius: 4pt;
        font-size: 8pt;
        line-height: 1.45;
        color: #0369a1;
        margin-bottom: 14pt;
    }}

    .toc-box {{
        border: 1px solid #cbd5e1;
        border-radius: 4pt;
        background-color: #ffffff;
        padding: 8pt 12pt;
    }}

    .toc-title {{
        font-size: 9pt;
        font-weight: bold;
        color: #0f172a;
        margin-bottom: 5pt;
        text-transform: uppercase;
        letter-spacing: 1px;
    }}

    .toc-table {{
        width: 100%;
        border-collapse: collapse;
    }}

    .toc-table td {{
        border: none;
        padding: 2.5pt 0;
        font-size: 7.8pt;
        color: #334155;
    }}

    /* ── Content Headings ── */
    h1 {{
        color: #0f172a;
        font-size: 13.5pt;
        font-weight: bold;
        border-bottom: 2px solid #0284c7;
        padding-bottom: 3pt;
        margin-top: 14pt;
        margin-bottom: 6pt;
        page-break-after: avoid;
        -pdf-keep-with-next: true;
    }}
    
    h2 {{
        color: #0369a1;
        font-size: 10.5pt;
        font-weight: bold;
        border-bottom: 1px solid #e2e8f0;
        padding-bottom: 2pt;
        margin-top: 12pt;
        margin-bottom: 5pt;
        page-break-after: avoid;
        -pdf-keep-with-next: true;
    }}
    
    h3 {{
        color: #334155;
        font-size: 9pt;
        font-weight: bold;
        margin-top: 9pt;
        margin-bottom: 3pt;
        page-break-after: avoid;
        -pdf-keep-with-next: true;
    }}
    
    p {{
        margin-bottom: 5pt;
        text-align: justify;
    }}
    
    ul, ol {{
        margin-top: 2pt;
        margin-bottom: 5pt;
        padding-left: 14pt;
    }}
    
    li {{
        margin-bottom: 1.5pt;
    }}
    
    table {{
        width: 100%;
        border-collapse: collapse;
        margin: 6pt 0 8pt 0;
        font-size: 7.5pt;
        page-break-inside: avoid;
    }}
    
    th, td {{
        border: 1px solid #cbd5e1;
        padding: 4pt 5pt;
        text-align: left;
        vertical-align: top;
    }}
    
    th {{
        background-color: #0f172a;
        color: #ffffff;
        font-weight: bold;
        font-size: 7.2pt;
        text-transform: uppercase;
        -pdf-keep-with-next: true;
    }}
    
    tr:nth-child(even) td {{
        background-color: #f8fafc;
    }}
    
    pre, code {{
        font-family: Courier, monospace;
        font-size: 7pt;
    }}
    
    code {{
        background-color: #f1f5f9;
        color: #0f172a;
        padding: 1pt 3pt;
        border-radius: 2pt;
    }}
    
    pre {{
        background-color: #0f172a;
        color: #f8fafc;
        border-radius: 4pt;
        padding: 6pt 8pt;
        margin: 6pt 0;
        line-height: 1.3;
        page-break-inside: avoid;
    }}
    
    blockquote {{
        border-left: 3pt solid #0284c7;
        background-color: #f0f9ff;
        padding: 5pt 8pt;
        margin: 6pt 0;
        color: #0369a1;
        font-style: italic;
        page-break-inside: avoid;
    }}
    
    hr {{
        border: none;
        border-top: 1px solid #e2e8f0;
        margin: 8pt 0;
    }}
    
    .badge {{
        display: inline-block;
        padding: 1.5pt 4pt;
        border-radius: 2pt;
        font-size: 6pt;
        font-weight: bold;
        text-transform: uppercase;
        font-family: Helvetica, Arial, sans-serif;
    }}
    
    .badge-critical {{ background-color: #fee2e2; color: #dc2626; border: 1px solid #f87171; }}
    .badge-high     {{ background-color: #fef3c7; color: #d97706; border: 1px solid #fbbf24; }}
    .badge-medium   {{ background-color: #ffedd5; color: #ea580c; border: 1px solid #fb923c; }}
    .badge-low      {{ background-color: #e0f2fe; color: #0284c7; border: 1px solid #38bdf8; }}
    .badge-info     {{ background-color: #f1f5f9; color: #475569; border: 1px solid #94a3b8; }}

    /* ── Diagram Card Components ── */
    .diagram-card {{
        background-color: #ffffff;
        border: 1px solid #cbd5e1;
        border-radius: 4pt;
        margin: 8pt 0;
        page-break-inside: avoid;
    }}
    
    .diagram-header {{
        background-color: #0f172a;
        color: #38bdf8;
        padding: 4pt 7pt;
        font-size: 7.2pt;
        font-weight: bold;
        letter-spacing: 0.5px;
    }}

    .pillar-table, .flow-table {{
        width: 100%;
        border: none;
        margin: 0;
    }}

    .pillar-cell {{
        border: 1px solid #e2e8f0;
        padding: 5pt;
        vertical-align: top;
        background-color: #f8fafc;
    }}

    .pillar-title {{
        font-size: 7.2pt;
        font-weight: bold;
        color: #0284c7;
        margin-bottom: 3pt;
        border-bottom: 1px solid #cbd5e1;
        padding-bottom: 1.5pt;
    }}

    .pillar-list {{
        margin: 0;
        padding-left: 9pt;
        font-size: 6.8pt;
        color: #334155;
    }}

    .pillar-list li {{
        margin-bottom: 1.5pt;
    }}

    .flow-box {{
        background-color: #f8fafc;
        border: 1px solid #cbd5e1;
        padding: 5pt;
        vertical-align: top;
    }}

    .flow-box-title {{
        font-size: 7.2pt;
        font-weight: bold;
        color: #0284c7;
        margin-bottom: 2pt;
    }}

    .flow-box-desc {{
        font-size: 6.8pt;
        color: #475569;
        line-height: 1.3;
    }}

    .flow-arrow {{
        text-align: center;
        vertical-align: middle;
        font-size: 10pt;
        color: #0284c7;
        font-weight: bold;
        border: none;
    }}
    
    .screenshot-box {{
        margin: 8pt 0;
        text-align: center;
        border: 1px solid #cbd5e1;
        background-color: #ffffff;
        padding: 5pt;
        border-radius: 4pt;
        page-break-inside: avoid;
    }}
    
    .screenshot-label {{
        font-size: 7pt;
        color: #64748b;
        font-style: italic;
        margin-top: 3pt;
    }}
    
    .signoff-box {{
        margin-top: 14pt;
        border-top: 1.5px solid #cbd5e1;
        padding-top: 8pt;
        page-break-inside: avoid;
    }}
</style>
</head>
<body>
    <!-- Running Header (Pages 2+) -->
    <div id="page_header" class="header-content">
        <table style="width: 100%; border: none; margin: 0;">
            <tr>
                <td style="text-align: left; border: none; padding: 0; font-weight: bold; color: #0284c7;">
                    [VULNSCAN] - Technical Architecture &amp; Security Report
                </td>
                <td style="text-align: right; border: none; padding: 0; color: #64748b;">
                    CONFIDENTIAL | SOC &amp; BLUE TEAM
                </td>
            </tr>
        </table>
    </div>
    
    <!-- Running Footer (Pages 2+) -->
    <div id="page_footer" class="footer-content">
        <table style="width: 100%; border: none; margin: 0;">
            <tr>
                <td style="text-align: left; border: none; padding: 0;">
                    VULNSCAN AI Platform • Author: Natto Muni Chakma (MRNATTO)
                </td>
                <td style="text-align: right; border: none; padding: 0; font-weight: bold;">
                    Page <pdf:pagenumber> of <pdf:pagecount>
                </td>
            </tr>
        </table>
    </div>

    <!-- ═══ COVER PAGE ═══ -->
    <div class="cover-container">
        <div class="cover-hero">
            <div class="cover-tag">DEFENSIVE CYBERSECURITY &amp; RECONNAISSANCE PLATFORM</div>
            <div class="cover-title">VULNSCAN: AI-Assisted Vulnerability Scanner</div>
            <div class="cover-subtitle">Comprehensive Technical Project &amp; Security Architecture Report</div>
        </div>

        <div class="meta-box">
            <table class="meta-table">
                <tr>
                    <td style="width: 25%;"><strong>Primary Author:</strong></td>
                    <td style="width: 35%;">Natto Muni Chakma (MRNATTO)</td>
                    <td style="width: 20%;"><strong>Document Version:</strong></td>
                    <td style="width: 20%;">1.0.0 (Release)</td>
                </tr>
                <tr>
                    <td><strong>Role / Specialization:</strong></td>
                    <td>Security Analyst / SOC &amp; Blue Team</td>
                    <td><strong>Document Date:</strong></td>
                    <td>August 2026</td>
                </tr>
                <tr>
                    <td><strong>Repository:</strong></td>
                    <td>github.com/NATTOMR/AI-Assisted-Vulnerability-Scanner</td>
                    <td><strong>Classification:</strong></td>
                    <td><span class="badge badge-high">RESTRICTED // INTERNAL</span></td>
                </tr>
                <tr>
                    <td><strong>AI Engine:</strong></td>
                    <td>Ollama Llama-3.2 (100% Local Inference)</td>
                    <td><strong>Web Framework:</strong></td>
                    <td>FastAPI + Modern Vanilla JS</td>
                </tr>
            </table>
        </div>

        <div class="abstract-box">
            <strong>EXECUTIVE ABSTRACT:</strong><br/>
            This document delivers an in-depth architectural and operational breakdown of <strong>VULNSCAN</strong>, an enterprise-grade, privacy-first cybersecurity reconnaissance and vulnerability assessment platform. By coupling an automated 8-module external reconnaissance engine with local, zero-leakage Large Language Model (LLM) inference, VULNSCAN enables security operators and student analysts to enumerate target attack surfaces, evaluate potential vulnerabilities, and generate standardized compliance reports without transmitting sensitive infrastructure details to third-party cloud AI vendors.
        </div>

        <div class="toc-box">
            <div class="toc-title">Table of Contents Overview</div>
            <table class="toc-table">
                <tr>
                    <td style="width: 50%;">1. Executive Summary</td>
                    <td style="width: 50%;">7. System Screenshots &amp; Visual Proofs</td>
                </tr>
                <tr>
                    <td>2. Project Vision &amp; Objectives</td>
                    <td>8. Threat Modeling &amp; Security Posture</td>
                </tr>
                <tr>
                    <td>3. System Architecture &amp; Data Flow</td>
                    <td>9. Performance &amp; Engineering Challenges</td>
                </tr>
                <tr>
                    <td>4. Passive &amp; Active Reconnaissance Engine</td>
                    <td>10. Future Roadmap &amp; Enhancement Milestones</td>
                </tr>
                <tr>
                    <td>5. Local AI Vulnerability Analysis Engine</td>
                    <td>11. Conclusion</td>
                </tr>
                <tr>
                    <td>6. User Interface &amp; Dashboard Experience</td>
                    <td></td>
                </tr>
            </table>
        </div>
    </div>

    <!-- ═══ MAIN REPORT BODY ═══ -->
    <div class="main-body">
        {html_content}

        <!-- Sign-off Section -->
        <div class="signoff-box">
            <table style="width: 100%; border: none; margin: 0;">
                <tr>
                    <td style="width: 50%; border: none; padding: 0;">
                        <strong>Document Prepared By:</strong><br/>
                        Natto Muni Chakma (MRNATTO)<br/>
                        <em>Security Analyst &amp; Core Maintainer</em>
                    </td>
                    <td style="width: 50%; border: none; padding: 0; text-align: right;">
                        <strong>Status:</strong> APPROVED &amp; VERIFIED<br/>
                        <em>VULNSCAN Security Systems Group</em>
                    </td>
                </tr>
            </table>
        </div>
    </div>

</body>
</html>"""

    with open(pdf_file, "wb") as f:
        pisa_status = pisa.CreatePDF(html_doc, dest=f)

    if pisa_status.err:
        print(f"Error creating PDF: {pisa_status.err}")
        return False
    else:
        size_kb = os.path.getsize(pdf_file) / 1024
        print(f"SUCCESS: {pdf_file} generated! Size: {size_kb:.1f} KB")
        return True

if __name__ == "__main__":
    build_pdf()