Switch to Node.js + Puppeteer for 100% fidelity PDF

Dockerfile

@@ -1,33 +1,27 @@
 
-# Use Python 3.9 as base (stable for WeasyPrint)
-FROM python:3.9-slim
+# Use Node.js 20 on Debian Bullseye (Stable for Puppeteer)
+FROM node:20-bullseye-slim
 
-# 1. Install System Dependencies (The "Construction Team")
-# We install Pango, Cairo, and fonts for CJK support
+# 1. Install Chrome Dependencies
+# Puppeteer requires a lot of system libraries to run Chrome in Docker
 RUN apt-get update && apt-get install -y \
-    libpango-1.0-0 \
-    libpangoft2-1.0-0 \
-    libharfbuzz-subset0 \
-    libjpeg-dev \
-    libopenjp2-7-dev \
-    libxcb1 \
-    fontconfig \
-    fonts-noto-cjk \
+    chromium \
+    fonts-ipafont-gothic fonts-wqy-zenhei fonts-thai-tlwg fonts-kacst fonts-freefont-ttf libxss1 \
+    --no-install-recommends \
     && rm -rf /var/lib/apt/lists/*
 
 # 2. Set working directory
 WORKDIR /app
 
-# 3. Install Python Dependencies
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+# 3. Install Node.js Dependencies
+COPY package.json .
+RUN npm install
 
 # 4. Copy Application Code
 COPY . .
 
-# 5. Expose Port (Hugging Face expects port 7860)
+# 5. Expose Port (Hugging Face expects 7860)
 EXPOSE 7860
 
 # 6. Run the Application
-# Using Gunicorn for production-grade performance
-CMD ["gunicorn", "-b", "0.0.0.0:7860", "app:app"]
+CMD ["node", "server.js"]

app.py

@@ -1,58 +0,0 @@
-
-from flask import Flask, request, send_file
-from weasyprint import HTML, CSS
-from weasyprint.text.fonts import FontConfiguration
-import io
-
-app = Flask(__name__)
-
-# Basic Health Check
-@app.route('/')
-def home():
-    return "Backend Service Running"
-
-@app.route('/api/generate_pdf', methods=['POST'])
-def generate_pdf():
-    try:
-        data = request.json
-        if not data or 'html' not in data:
-            return {"error": "Missing 'html' field"}, 400
-
-        html_content = data['html']
-        
-        # Prepare buffer
-        pdf_buffer = io.BytesIO()
-        
-        # Font Config (We rely on system fonts installed via Dockerfile)
-        # fonts-noto-cjk provides "Noto Sans CJK SC"
-        font_config = FontConfiguration()
-        
-        # CSS to enforce fonts
-        css = CSS(string='''
-            @page { margin: 20mm; }
-            body { font-family: "Noto Sans CJK SC", sans-serif !important; }
-            img { max-width: 100%; height: auto; }
-            pre { white-space: pre-wrap; background: #f5f5f5; padding: 10px; }
-        ''')
-
-        HTML(string=html_content).write_pdf(
-            pdf_buffer, 
-            stylesheets=[css], 
-            font_config=font_config
-        )
-        
-        pdf_buffer.seek(0)
-        
-        return send_file(
-            pdf_buffer,
-            mimetype='application/pdf',
-            as_attachment=True,
-            download_name='export.pdf'
-        )
-
-    except Exception as e:
-        print(f"Error: {e}")
-        return {"error": str(e)}, 500
-
-if __name__ == '__main__':
-    app.run(host='0.0.0.0', port=7860)

package.json

@@ -0,0 +1,15 @@
+
+{
+  "name": "pdf-server",
+  "version": "1.0.0",
+  "description": "Puppeteer PDF Generator for Hugging Face Spaces",
+  "main": "server.js",
+  "dependencies": {
+    "express": "^4.18.2",
+    "puppeteer": "^22.0.0",
+    "cors": "^2.8.5"
+  },
+  "scripts": {
+    "start": "node server.js"
+  }
+}

requirements.txt

@@ -1,4 +0,0 @@
-
-Flask==3.0.0
-WeasyPrint==60.1
-gunicorn==21.2.0

server.js

@@ -0,0 +1,82 @@
+
+const express = require('express');
+const puppeteer = require('puppeteer');
+const cors = require('cors');
+
+const app = express();
+const port = 7860;
+
+// Enable CORS for all origins (or restrict to gemini.google.com)
+app.use(cors());
+
+// Increase payload limit for large HTML
+app.use(express.json({ limit: '50mb' }));
+
+app.get('/', (req, res) => {
+  res.send('Puppeteer PDF Server Running');
+});
+
+app.post('/api/generate_pdf', async (req, res) => {
+  let browser = null;
+  try {
+    const { html } = req.body;
+    if (!html) {
+      return res.status(400).json({ error: 'Missing html content' });
+    }
+
+    // Launch Chrome
+    // We use the installed 'chromium' from apt-get
+    browser = await puppeteer.launch({
+      executablePath: '/usr/bin/chromium',
+      args: [
+        '--no-sandbox',
+        '--disable-setuid-sandbox',
+        '--disable-dev-shm-usage', // Critical for Docker
+        '--font-render-hinting=none' // Better font rendering
+      ],
+      headless: 'new'
+    });
+
+    const page = await browser.newPage();
+    
+    // Set content
+    await page.setContent(html, { waitUntil: 'networkidle0' });
+
+    // Inject styles to ensure 100% width and print media simulation
+    await page.addStyleTag({
+        content: `
+            @page { margin: 20mm; size: A4; }
+            body { -webkit-print-color-adjust: exact; }
+        `
+    });
+
+    // Generate PDF
+    const pdfBuffer = await page.pdf({
+      format: 'A4',
+      printBackground: true,
+      margin: {
+        top: '20mm',
+        bottom: '20mm',
+        left: '10mm',
+        right: '10mm'
+      }
+    });
+
+    await browser.close();
+    browser = null;
+
+    // Send response
+    res.setHeader('Content-Type', 'application/pdf');
+    res.setHeader('Content-Disposition', 'attachment; filename=export.pdf');
+    res.send(pdfBuffer);
+
+  } catch (error) {
+    console.error('PDF Generation Error:', error);
+    if (browser) await browser.close();
+    res.status(500).json({ error: 'Internal Server Error', details: error.message });
+  }
+});
+
+app.listen(port, () => {
+  console.log(`Server listening at http://localhost:${port}`);
+});