maxun

Kadoa is an AI-powered, no-code platform for web data extraction. It allows users to scrape web data, monitor changes, and integrate insights into workflows. Kadoa supports smart navigation and autonomous operation for accurate and up-to-date data collection. It caters to various use cases, including e-commerce and AI training.

PDFAnnotations is a tool for turning PDF highlights into structured notes. It is a privacy-first, local-browser tool designed for creating a second brain. The tool allows one-click export to Notion, Obsidian, and Markdown with clean formatting. It also features smart filters to sort and export by color or annotation type.

Reworkd is an AI-powered platform that optimizes web data extraction. It generates and repairs scraping code, adapting to website changes automatically. Reworkd's no-code interface allows companies to scale their web data extraction without building individual scraping bots. It offers a community-driven initiative for AI democratization.

Deep-text-recognition-benchmark is a PyTorch implementation for text recognition using deep learning methods. It provides a four-stage STR framework suitable for most existing STR models. The tool allows for module-wise contributions to performance in terms of accuracy. It includes training and evaluation data, failure cases, and cleansed labels.

AnyCrawl is a Node.js/TypeScript crawler that transforms websites into LLM-ready data. It extracts structured SERP results from search engines like Google, Bing, and Baidu. The tool features native multi-threading for efficient bulk processing, making it suitable for large-scale data extraction projects.

Trafilatura is a Python and command-line tool designed for gathering text and metadata from the web. It facilitates crawling, scraping, and extraction of data. The tool supports output in various formats, including CSV, JSON, HTML, MD, TXT, and XML. It is useful for researchers and developers needing to process web content.