Skip to main content AI Studio  add-on for Spider.
Guides · Task manual

From first crawl to production.

Each guide walks one job end to end, in code that runs as-is. Follow a track in order, or jump straight to the task in front of you.

20 guides 5 tracks Updated Mar 2026
Start here Web Crawling & Scraping with SpiderSet up Spider, run your first crawl, and scale your scraping to production with request modes, proxies, streaming, and clean markdown for LLM pipelines.5 min read
Track 01

Fundamentals

The API surface end to end — crawl, scrape, search, and what it costs.

3 guides · ~12 min
  1. 01Spider API: Crawl, Scrape & Search the WebSpider API turns any URL into markdown, HTML, or JSON in one request. See endpoints, code examples, and how to start crawling or scraping the web today.
  2. 02Web Search API (SERP) - Search and ScrapeQuery the web and scrape results in one call with Spider's web search API. Covers parameters, geo-targeting, time filters, pagination, and code examples.
  3. 03Spider Pricing and Plans: What You Pay and WhyA clear breakdown of Spider's pay-as-you-go pricing, per-endpoint costs, volume discounts, and how billing actually works for web scraping and browser automation.
Track 02

AI & agents

Feed crawls into LLMs, agent frameworks, and RAG pipelines.

6 guides · ~49 min
  1. 01Build an AI Agent from ScratchBuild a research agent that searches the web with Spider, evaluates results, and forms answers with OpenAI.
  2. 02LangChain + Groq + Spider Integration GuideCrawl multiple URLs with Spider's LangChain loader, then summarize the results with Groq and Llama 3.
  3. 03Scrape & Crawl Agent with Microsoft's AutogenSet up an Autogen agent that scrapes and crawls websites using the Spider API.
  4. 04Stock Research Assistant Using crewAI and SpiderBuild a crewAI research pipeline that uses Spider to scrape financial data and write stock analysis reports.
  5. 05Speedy Resilient Web Scraper for RAG AI: Part 1Choosing your scraper, cleaning HTML for RAG, deduplicating content, and testing on a single site before scaling up.
  6. 06Speedy Resilient Web Scraper for RAG AI: Part 2Scaling web scraping for RAG pipelines. Error-first design, retry strategies, and handling failures at volume.
Track 03

Harder targets

Login walls, proxy routing, and headless Chrome at scale.

3 guides · ~7 min
  1. 01Crawling Authenticated PagesTwo methods for crawling pages behind login walls: cookies and execution scripts.
  2. 02Proxy Mode - HTTP, HTTPS & SOCKS5 EndpointsRoute scraping traffic through the Spider proxy over HTTP, HTTPS, or SOCKS5. Rotating datacenter and residential proxies, same credits as the standard API.
  3. 03Scaling Headless Chrome for High-Performance ApplicationsPractical strategies for scaling headless Chrome, from container orchestration to Rust-based CDP handlers and ALB configuration.
Track 04

Applied workflows

Complete tasks built on the API — leads, outreach, search, archives.

5 guides · ~16 min
  1. 01Extract LeadsExtract contact information from any website using Spider's AI-powered pipeline. Emails, phone numbers, and more.
  2. 02Automated Cold Email Outreach Using SpiderExtract company info from inbound emails, scrape their website with Spider, and generate personalized replies with RAG.
  3. 03Discord Real-Time Data RetrievalSet up Spider Bot on your Discord server to fetch and analyze web data using slash commands.
  4. 04Set Up Automated Free Website Static SearchAdd full-text static search to any website using Spider and Pagefind.
  5. 05Website ArchivingArchive web pages with Spider. Capture full page resources, automate regular crawls, and store content for long-term access.
Track 05

Open source & self-hosting

Run the Rust crawler yourself, and the OSS projects behind Spider.

2 guides · ~10 min
  1. 01Self-Hosting Spider: Using the Open Source Rust CrateBuild your own web crawler with the open source spider Rust crate. Quick start, Docker setup, configuration, and when to upgrade to the cloud API.
  2. 02The Spider Open Source EcosystemA guide to all open source Spider projects: the core crawler, browser client, HTML transformer, TLS fingerprinting, and more. Quick-start examples for each.
Get started

Start crawling in 30 seconds.

One API key. No servers to manage.

Free balance on signup · No card required

Get started freeRead the docs