A very simple news crawler with a funny name

A Python-based tool that converts PDF files into editable Word documents, preserving text, images, and layout. Uses PyPDF2, PyMuPDF (fitz), python-docx, and Pillow to accurately transfer content from PDF to .docx. Ideal for transforming complex PDFs into Word format for easy editing.

Automation manager

💡 You can easily extract photos 📸 from an Excel 📊 cell using this Python script. But wait, there's more! These photos can also be saved with names created by given cells. To discover how to make the most of this powerful tool, follow the steps below or watch the video guide. Happy extracting! ✨🔍

Python-based desktop tool, "PDF Manipulation Tool," offers a comprehensive suite for managing PDFs. It enables users to extract text (with/without OCR), split, merge, encrypt, and decrypt PDFs. Additionally, it converts images to PDF, extracts embedded images, and intelligently extracts tabular data, streamlining various PDF-related tasks.

Upload a CAD PDF to extract text and automatically generate a concise engineering summary using a local LLM.

Script to crop and unrotate multiple images from a scanned image

Bitcoin Meme Miner: Satirical tool to find images on the Bitcoin blockchain, proving censorship is futile in the OP_RETURN wars. 🧙‍♂️🐒📸

Image extraction and bias analysis

A Python tool to extract images from PDF files with filtering and organization.

Bitcoin Meme Miner: Satirical tool to find images on the Bitcoin blockchain, proving censorship is futile in the OP_RETURN wars. 🧙♂️🐒📸

A robust, privacy-focused command-line utility that intelligently removes CamScanner watermarks from PDF documents and exports clean results to multiple formats including PDF, PNG, and multi-page TIFF.

Herramienta de escritorio multiplataforma para extraer, rotar y exportar páginas de PDF a múltiples formatos (PDF, ZIP, imágenes). Creada con Python y Flet.

A lightweight Python service for converting PDF files into images using pdftoppm. It generates one PNG image per page in the PDF.

Extract content from PDF's and convert or create new documents from the content in multiple output formats.

financeQA is a modular Retrieval-Augmented Generation (RAG) system for finance question answering. It features document preprocessing, image and table extraction, vector database indexing, and OpenAI-powered chat interfaces, designed for robust financial data analysis and evaluation.

useful for searching for images in a recursive fashion given starting url