Tag
This paper presents an automated method to extract quantitative techno-economic data from 76,000 energy system studies, compiling 3.2 million structured data points. The resulting FAIR database enables analysis of literature trends and provides input for energy models.
Introduces DECODEM, benchmark datasets for evaluating automated extraction of corporate governance variables from legal documents using large language models, showing high accuracy for many provisions.
Context.dev is a YC-backed API that allows developers and AI agents to scrape, crawl, and extract structured data from any website, with features like markdown, HTML, sitemaps, screenshots, and brand intelligence, aiming to simplify web data integration.
This article categorizes 14 web scraping tools into five groups: AI new paradigms, engineering-grade frameworks, browser automation, China-specific platforms, and modern lightweight tools, accompanied by real-world cases and selection recommendations.
Context.dev provides a single API for scraping, enriching, and extracting data from the internet.
Tweet de @ecommartinez que lista 10 repositorios de GitHub para hacer web scraping y extraer datos limpios de cualquier sitio web.
Datalab's balanced mode extraction achieves 95.9% accuracy in internal benchmarks, surpassing Reducto Deep Extract (95.1%) at less than half the price, with full verification including citations and reasoning.
Liquid AI releases LFM2.5-230M, a lightweight foundation model that runs on devices from cloud GPUs to CPUs and Raspberry Pi, with strong performance on tool use and data extraction tasks.
MinerU is a free, open-source tool that extracts text, tables, and equations from PDFs and scanned documents, supporting 109 languages and batch processing, saving hours of manual work.
This article introduces 10 open-source GitHub repositories for web scraping, including Firecrawl, Crawl4AI, etc., which can extract clean data from websites and support AI-ready formats.
Vik Paruchuri showcases lift, an open-source extraction model capable of pulling structured data from messy contracts.
A curated thread listing 10 GitHub repositories for web scraping, including Firecrawl, Crawl4AI, Browser Use, and others, covering everything from simple scraping to stealth tools and LLM-ready data extraction.
Vik Paruchuri is open-sourcing a 9B model that extracts structured data from documents with near-frontier performance (90.2% on their benchmark, vs Gemini 3.5 Flash at 91.3%).
A benchmark comparing AI models ranging from 2B to 35B parameters on a challenging task of extracting structured data from HTML, evaluating their performance and accuracy.
Agentic Document Extraction is a tool that uses AI agents to make documents computable by extracting structured data from unstructured documents.
VikParuchuri announces the launch of turbo mode data extraction, claiming 5x faster and cheaper performance with 7% more accuracy than Azure Content Understanding, achieving competitive latency for real-time workflows.
A viral open-source web crawling tool called Crawl4AI offers free, LLM-friendly scraping with features like JavaScript rendering, async crawling, and clean structured output, contrasting with paid services like Firecrawl.
browser_use is a tool that converts any website into clean JSON via a single curl call, handling JavaScript rendering and bypassing bot protections like Cloudflare.
Browser Use launched Fetch Use, a Python SDK for scraping websites with a stealth browser that handles proxies, cookies, and sessions automatically.
This article introduces 5 open-source tools (Agent-reach, Scrapling, Browser-use, Claude in Chrome, Web-access) that enable AI agents like Claude Code to perform web scraping, browser operations, etc., covering scenarios from lightweight to heavy-duty, along with configuration tips.