swarmauri_parser_pypdf2 0.8.4.dev3

PyPDF2 Parser for Swarmauri.

Swarmauri Parser PyPDF2

Lightweight PDF parser for Swarmauri that uses PyPDF2 to extract text from each page. Returns a Document per page with metadata describing the source file and page number.

Features

• Handles PDF input from file paths or raw bytes.
• Produces one Document per page, storing text in content and metadata fields (page_number, source).
• Gracefully returns an empty list if PyPDF2 cannot extract text from a page (e.g., scanned PDFs without OCR).

Prerequisites

• Python 3.10 or newer.
• PyPDF2 (installed automatically). For encrypted PDFs, ensure you provide access credentials before parsing.

Installation

# pip
pip install swarmauri_parser_pypdf2

# poetry
poetry add swarmauri_parser_pypdf2

# uv (pyproject-based projects)
uv add swarmauri_parser_pypdf2

Quickstart

from swarmauri_parser_pypdf2 import PyPDF2Parser

parser = PyPDF2Parser()
documents = parser.parse("manuals/device.pdf")

for doc in documents:
    print(doc.metadata["page_number"], doc.content[:120])

Parsing PDF Bytes

from swarmauri_parser_pypdf2 import PyPDF2Parser

with open("statements/bank.pdf", "rb") as f:
    pdf_bytes = f.read()

parser = PyPDF2Parser()
pages = parser.parse(pdf_bytes)
print(len(pages), "pages parsed from bytes")

Tips

• PyPDF2 extracts text only when the PDF contains accessible text objects. For scanned documents, run OCR first (e.g., with swarmauri_ocr_pytesseract).
• Remove or handle password protection before parsing; PyPDF2 cannot decrypt files without the password.
• Combine this parser with Swarmauri chunkers or summarizers to process large documents efficiently.

Want to help?

If you want to contribute to swarmauri-sdk, read up on our guidelines for contributing that will help you get started.