unstructured.pytesseract

What it is and what it does

Unstructured.pytesseract is a Python wrapper around Google's Tesseract OCR engine that recognizes and extracts text from images. It handles multiple image formats including jpeg, png, gif, bmp, and tiff, and can work with file paths or array objects. The package supports multilingual OCR, language specification, and timeout controls for long-running operations.

Beyond simple text extraction, it provides structured output modes including bounding box coordinates, confidence scores, orientation detection, and can generate searchable PDFs or HOCR markup. It supports batch processing and allows fine-grained control over Tesseract parameters through config strings. The wrapper requires the external Tesseract OCR engine to be installed separately on your system.

Use it for:

• Extract text from scanned documents or photographs for indexing or archival purposes
• Generate searchable PDFs from image-based documents for easier retrieval
• Detect and extract text in non-English languages by specifying language codes
• Obtain character-level bounding boxes for layout analysis or document structure reconstruction
• Batch process multiple images to extract text with a single tesseract invocation

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Python wrapper for Google's Tesseract OCR engine that extracts text from images in multiple formats and languages, supporting various output types including plain text, bounding boxes, PDFs, and HOCR.

Yes, if you need OCR capabilities in Python and are willing to install the external Tesseract engine. The package is actively maintained, has no known vulnerabilities, uses a permissive license, and provides a clean Python interface to a mature OCR tool. Install friction is low and it supports Python 3.8, 3.9, 3.10, 3.11, and 3.12. Not suitable if you cannot install system-level dependencies or need a pure-Python OCR solution.

Install

unstructured-pytesseract on PyPI

pip install unstructured-pytesseract

uv add unstructured-pytesseract

poetry add unstructured-pytesseract

Installing unstructured.pytesseract

Before you install

Low install friction with only two runtime dependencies (packaging and Pillow). Active maintenance with recent commits and no known vulnerabilities. Requires the external Tesseract OCR engine to be installed separately on the system.

License in practice

Apache License 2.0 is permissive, allowing use in commercial and proprietary projects with minimal restrictions beyond attribution and liability disclaimers.

Quickstart

pip install unstructured.pytesseract

import pytesseract

text = pytesseract.image_to_string('test.png')
print(text)

Google's Tesseract OCR engine must be installed separately on your system; pytesseract is a wrapper that calls the tesseract executable. You may need to set pytesseract.pytesseract.tesseract_cmd to the full path if tesseract is not in your PATH.

Verify before relying

• Whether the package is actively maintained by the original author or has transferred to community maintainers
• Performance characteristics for large-scale batch OCR processing
• Accuracy benchmarks across different image types and languages

Package facts

Evidence: unstructured.pytesseract-0.3.15-py3-none-any.whl

Keywords: python-tesseract, OCR, Python

Tags

More Text Processing packages