PDF

---
name: pdf
description: |
  Trigger when working with PDF files: reading, extracting text, generating
  PDFs, or manipulating existing documents. Phrases: "read PDF", "extract
  from PDF", "generate PDF", "parse PDF".
allowed-tools:
  - Bash(command *)
  - Read
  - Write
  - Edit
---

# PDF

Read, extract, and generate PDF documents. Handles text extraction, form
filling, generation, and manipulation.

## Prerequisites

- For reading: `pdftotext` (poppler-utils) or Python `PyPDF2`
- For generation: `weasyprint`, `puppeteer`, or `pdfkit`

## Steps

### Extract text from PDF

```bash
# Using poppler (fastest)
pdftotext input.pdf output.txt

# Using Python
python3 -c "
import PyPDF2
reader = PyPDF2.PdfReader('input.pdf')
for page in reader.pages:
    print(page.extract_text())
"
```

### Generate PDF from HTML

```bash
# Using weasyprint
python3 -c "
from weasyprint import HTML
HTML(filename='report.html').write_pdf('report.pdf')
"

# Using puppeteer
node -e "
const puppeteer = require('puppeteer');
(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  await page.goto('file:///path/to/report.html');
  await page.pdf({ path: 'report.pdf', format: 'A4' });
  await browser.close();
})();
"
```

### Merge PDFs

```python
from PyPDF2 import PdfMerger
merger = PdfMerger()
merger.append("file1.pdf")
merger.append("file2.pdf")
merger.write("merged.pdf")
merger.close()
```

## Notes

- Always check if the PDF is text-based or scanned (image-based)
- For scanned PDFs, use OCR: `tesseract` or `pytesseract`
- Large PDFs: process page by page to avoid memory issues