pip install pymupdf

• a high-performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
• PyMuPDF has integrated support for Tesseract-OCR.
• PyMuPDF 1.26.0 documentation

Most Relevant

[get_textpage_ocr()](https://pymupdf.readthedocs.io/en/latest/page.html#Page.get_textpage_ocr:~:text=get_textpage_ocr,-(flags%3D)

[Text Extraction Flags](https://goeden-gab.notion.site/Text-Extraction-Flags-2067c1ad9aee80c0ae3cfd320ea4b501)

[Outputting as Markdown](https://goeden-gab.notion.site/Outputting-as-Markdown-2067c1ad9aee801d9c27c9a9a527ee31)

[PyMuPDF4LLM](https://goeden-gab.notion.site/PyMuPDF4LLM-2067c1ad9aee802d81afd1c61fd36026)

PyMuPDF, LLM & RAG - PyMuPDF 1.26.0 documentation

• Supported file types (with image file types)
• Text - PyMuPDF 1.26.0 documentation