Python PDF form extractor example

import { pythonExtension } from "@trigger.dev/python/extension";
import { defineConfig } from "@trigger.dev/sdk";

export default defineConfig({
  runtime: "node",
  project: "<your-project-ref>",
  // Your other config settings...
  build: {
    extensions: [
      pythonExtension({
        // The path to your requirements.txt file
        requirementsFile: "./requirements.txt",
        // The path to your Python binary
        devPythonBinaryPath: `venv/bin/python`,
        // The paths to your Python scripts to run
        scripts: ["src/python/**/*.py"],
      }),
    ],
  },
});

import { task } from "@trigger.dev/sdk";
import { python } from "@trigger.dev/python";

export const processPdfForm = task({
  id: "process-pdf-form",
  run: async (payload: { pdfUrl: string }, io: any) => {
    const { pdfUrl } = payload;
    const args = [pdfUrl];

    const result = await python.runScript("./src/python/extract-pdf-form.py", args);

    // Parse the JSON output from the script
    let formData;
    try {
      formData = JSON.parse(result.stdout);
    } catch (error) {
      throw new Error(`Failed to parse JSON output: ${result.stdout}`);
    }

    return {
      formData,
      stderr: result.stderr,
      exitCode: result.exitCode,
    };
  },
});

PyMuPDF==1.23.8
requests==2.31.0

import fitz  # PyMuPDF
import requests
import os
import json
import sys
from urllib.parse import urlparse

def download_pdf(url):
    """Download PDF from URL to a temporary file"""
    response = requests.get(url)
    response.raise_for_status()

    # Get filename from URL or use default
    filename = os.path.basename(urlparse(url).path) or "downloaded.pdf"
    filepath = os.path.join("/tmp", filename)

    with open(filepath, 'wb') as f:
        f.write(response.content)
    return filepath

def extract_form_data(pdf_path):
    """Extract form data from a PDF file."""
    doc = fitz.open(pdf_path)
    form_data = {}

    for page_num, page in enumerate(doc):
        fields = page.widgets()
        for field in fields:
            field_name = field.field_name or f"unnamed_field_{page_num}_{len(form_data)}"
            field_type = field.field_type_string
            field_value = field.field_value

            # For checkboxes, convert to boolean
            if field_type == "CheckBox":
                field_value = field_value == "Yes"

            form_data[field_name] = {
                "type": field_type,
                "value": field_value,
                "page": page_num + 1
            }

    return form_data

def main():
    if len(sys.argv) < 2:
        print(json.dumps({"error": "PDF URL is required as an argument"}), file=sys.stderr)
        return 1

    url = sys.argv[1]

    try:
        pdf_path = download_pdf(url)
        form_data = extract_form_data(pdf_path)

        # Convert to JSON for structured output
        structured_output = json.dumps(form_data, indent=2)
        print(structured_output)
        return 0
    except Exception as e:
        print(json.dumps({"error": str(e)}), file=sys.stderr)
        return 1

if __name__ == "__main__":
    sys.exit(main())