Technical deep dives on web extraction, content parsing for LLMs, anti-bot bypass, and building open-source infrastructure in Rust. Written by the team behind webclaw.
webclaw turns any website into clean, structured content for AI applications. These posts cover the engineering decisions, trade-offs, and lessons learned building a web extraction toolkit from scratch.

LangChain's built-in loaders break on bot-protected sites and return raw HTML your LLM can't use. Here's how to get clean, reliable web data into any LangChain pipeline.

Google killed plain HTTP to search results. 5 ways that still work in 2026: TLS fingerprinting, headless browsers, SERP APIs. Code examples for each.

If you're building with LLMs, you need web data. Here's how the main scraping APIs compare on the things that actually matter for AI use cases.

Fix the four signals Cloudflare checks before you reach for a headless browser: TLS, HTTP/2, challenge, session. Why proxy and user-agent rotation alone fails.

You don't always need the full page. Sometimes you need three fields from a product listing. Here's how to pull exactly the data you want from any URL.

Most RAG tutorials stop at "upload a PDF." Real apps need live web data. Here's how to build a pipeline that fetches, extracts, and indexes pages.

MCP web scraping gives Claude Code, Cursor, and AI agents live web access. Scrape, crawl, search, extract, and summarize from one server.

Convert HTML to Markdown for LLMs with boilerplate removed, links preserved, and cleaner RAG input for agents and summarization.

Most scraping tools were built for data pipelines, not AI agents. Three things quietly break your pipeline and how to fix them.
Cancel anytime. Turn any page into clean, structured content your agent can actually use.