PDF text extraction & classification
Fast Rust library for PDF classification (text/scanned) and text extraction to Markdown, with optional OCR and bindings for Python/Node/WASM.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose it for deep-learning-based end-to-end PDF/Office-to-markdown conversion with layout/table understanding; heavier than a Rust library.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
choose it for high-accuracy PDF-to-markdown using a Python model pipeline if you don't need Rust speed or classification.
Convert PDF to markdown + JSON quickly with high accuracy
choose it if you need a JVM/Java PDF parser for AI pipelines; not a lightweight Rust drop-in.
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
choose it when OCR on scanned/complex documents via vision models outweighs speed; it is not for local text PDFs.
OCR & Document Extraction using vision models
choose it as a Rust parser for more general document types, but it lacks pdf-inspector's classification focus.
A fast, helpful, and open-source document parser
choose it for very detailed character/rect/line inspection in Python, at the cost of classification and markdown.
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
choose it for polyglot text extraction across many formats, but not specialized for PDF classification/routing.
A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured data from 101 formats (115 file extensions) plus code intelligence for 371 code languages. 15 language bindings — Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript — plus CLI, REST API, and MCP server.
choose it if you need JS/Node document-to-structured-data, but it is heavier and not a native-library swap.
Transforms PDF, Documents and Images into Enriched Structured Data
choose it for scanned book PDFs where OCR-based conversion is the main goal; not a fast text-PDF inspector.
PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.
choose it for an on-premises, OCR-free markdown/structured extraction toolkit with benchmark harness.
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
choose it for a very fast Python/Rust PDF library that also creates/edits PDFs, if you don't need classification.
The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0.
choose it for a RAG-focused pipeline with chunking and enrichment, not a lean classification library.
Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.
choose it for a research-grade document-image parsing model, not a lightweight local library.
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
choose it for a mature, AGPL-licensed Python PDF library with text extraction and manipulation, but no classification.
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
choose it for an AI-powered document-to-Markdown/JSON toolkit from IBM, heavier and Python-based.
Get your documents ready for gen AI
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
older comprehensive extraction toolkit; still useful but unmaintained for 1.7 years.
A Comprehensive Toolkit for High-Quality PDF Content Extraction
previous-generation, archived lib focused solely on table extraction; not a general PDF inspector.
Camelot: PDF Table Extraction for Humans
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
a Windows desktop PDF editor with OCR, not a library to embed.
Free and open-source PDF editor for Windows. View, annotate, OCR, merge, split, edit text, draw, sign, fill forms, print, flatten, and open password-protected PDFs without a subscription. Install or run portable. GPLv3
a separate extraction API server wrapping OCRs; not a library for integration.
Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown
a CLI for LandingAI's agentic document extraction service; not a local library.
The official CLI for Agentic Document Extraction (ADE) by LandingAI — parse documents and extract schema-shaped data from your terminal
These projects were analysed and named pdf-inspector among their alternatives. The relationship is not symmetric — how pdf-inspector rates them is a separate judgement, made when pdf-inspector is analysed in its own right.
calls pdf-inspector “Choose for fast Rust-based PDF inspection and classification (scanned vs text) if your focus is document routing, not manipulation.”
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
calls pdf-inspector “choose when building in Rust and need fast PDF classification, scan detection, and text extraction”
Community maintained fork of pdfminer - we fathom PDF
calls pdf-inspector “Rust library for text extraction and scanned/text classification; choose if you need a lightweight text-only extractor.”
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
calls pdf-inspector “Lightweight Rust library for PDF inspection and text extraction; choose for routing/classification, but no editing.”
A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files