text-extract-api vs pdf-craft
Document OCR and conversion projects compared
text-extract-api and pdf-craft use OCR to make document content reusable. text-extract-api focuses on extracting text and structured data from multiple file types through a self-hostable service, while pdf-craft centers on converting scanned PDFs into Markdown and EPUB, with translation workflows.
text-extract-api: Extract Text and Data from Documents
A self-hostable API that turns PDFs, images, and Office files into Markdown or structured JSON using OCR and Ollama models. It suits teams that need document processing and PII removal with control over where files are processed.
pdf-craft: Convert Scanned PDFs with DeepSeek OCR
PDF Craft is a Python library and online service for turning scanned books, research papers, and technical documents into editable Markdown or reader-friendly EPUB. Built around DeepSeek OCR, it also supports translation and translated PDF output.
| text-extract-api | pdf-craft | |
|---|---|---|
| Language | Python | Python |
| License | MIT | MIT |
| Stars | 3.2k | 6.4k |
| Forks | 279 | 466 |
| Last analyzed | Oct 3, 2026 | Oct 18, 2026 |
Key differences
- text-extract-api accepts PDFs, images, and Office documents, while pdf-craft focuses on scanned PDFs and book-oriented outputs such as EPUB.
- text-extract-api can produce structured JSON as well as Markdown; pdf-craft offers Markdown and EPUB, plus translated or bilingual outputs and translated PDFs.
- text-extract-api is a Python API and CLI service designed for deployment on your own infrastructure; pdf-craft provides synchronous and asynchronous Python APIs and also has an online version.
- text-extract-api supports prompt-based PII removal and configurable storage profiles, including local files, Google Drive, and Amazon S3; pdf-craft saves extraction results in `.pcex` files for reuse in later workflow steps.
- Both projects are Python and MIT-licensed, and neither is archived; pdf-craft has 6.3k stars and 460 forks, compared with text-extract-api's 3.2k stars and 279 forks.
Choose text-extract-api if you…
- need to process PDFs, images, and Office documents into Markdown or structured JSON.
- want to run document processing on your own infrastructure and configure where results are stored.
- need OCR workflows with optional Ollama processing, asynchronous tasks, caching, or prompt-based PII removal.
Choose pdf-craft if you…
- want to turn scanned books or technical documents into Markdown or EPUB.
- need translation workflows, including bilingual EPUBs or translated text written onto PDF pages.
- prefer a Python library with reusable extraction results and synchronous or asynchronous APIs.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.