swarmauri_parser_fitzpdf 0.11.0.dev1

High-performance PDF text parser for Swarmauri using PyMuPDF with aggregated whole-document output.

Swarmauri Parser Fitz PDF

swarmauri_parser_fitzpdf is the Swarmauri PDF parser for high-performance text extraction using PyMuPDF. It opens a PDF, extracts text from every page, and returns a single Swarmauri Document with the aggregated content and source metadata.

Why Use Swarmauri Parser Fitz PDF

• Use PyMuPDF's fast document engine for PDF extraction inside Swarmauri ingestion and indexing pipelines.
• Produce one normalized Document for whole-file workflows such as summarization, classification, or chunking after parse.
• Keep PDF parsing logic aligned with the Swarmauri parser interface used by other loaders and processors.
• Stay flexible if you later need PyMuPDF-specific extraction modes or OCR augmentation upstream.

FAQ

What does this parser return?
A list containing one Swarmauri Document whose content holds the combined extracted text for the PDF.

Does it return one document per page?
No. This parser aggregates all page text into a single document.

Can it parse scanned PDFs with no text layer?
Not by itself. PyMuPDF extracts text objects already present in the document. Scan-only PDFs should be OCR'd first.

What input type does it expect?
A file path string pointing to a local PDF.

Features

• Aggregated PDF text extraction through PyMuPDF.
• Preserves the original source path in document metadata.
• Uses a lightweight Swarmauri parser surface for document pipelines.
• Appropriate for whole-document ingestion, chunking, and retrieval setup.
• Supports Python 3.10, 3.11, 3.12, 3.13, and 3.14.

Installation

uv add swarmauri_parser_fitzpdf

pip install swarmauri_parser_fitzpdf

Usage

from swarmauri_parser_fitzpdf import FitzPdfParser

parser = FitzPdfParser()
documents = parser.parse("reports/quarterly.pdf")

for document in documents:
    print(document.metadata["source"])
    print(document.content[:500])

Examples

Parse a PDF into a single document

from swarmauri_parser_fitzpdf import FitzPdfParser

parser = FitzPdfParser()
docs = parser.parse("whitepapers/roadmap.pdf")

if docs:
    print(len(docs[0].content))

Handle invalid input safely

from swarmauri_parser_fitzpdf import FitzPdfParser

parser = FitzPdfParser()

try:
    docs = parser.parse("missing.pdf")
    if not docs:
        print("Parsing failed or returned no text.")
except ValueError as exc:
    print(exc)

Related Packages

• swarmauri_parser_pypdf2
• swarmauri_parser_pypdftk
• swarmauri_ocr_pytesseract
• swarmauri_parser_fitzpdf

Swarmauri Foundations

• swarmauri
• swarmauri_core
• swarmauri_base
• swarmauri_standard

More Documentation

• PyMuPDF basics
• PyMuPDF text extraction details
• PyMuPDF text recipes

Best Practices

• Use this parser when you want a whole-document text payload rather than page-by-page output.
• Use OCR earlier in the flow for scan-only documents that have no extractable text layer.
• Cache parse output for large PDFs if the same files are processed repeatedly.
• If reading order matters, verify the extracted output on representative documents because PDF text order depends on document structure.

License

This project is licensed under the Apache-2.0 License.