Skip to main content

Blog category

Tutorial

Hands-on tutorials for scraping workflows, RAG ingestion, MCP setups, and production integrations with fastCRW.

Tutorial·9 min read

Build a Chat-With-Website Bot (fastCRW + LangChain)

Build a chat-with-website bot with fastCRW and LangChain: crawl a site to clean markdown, chunk, embed, and answer questions over it. Full Python tutorial.

Jun 27, 2026
Tutorial·14 min read

SERP Scraping in 2026: Search the Web With CRW's Search API (Python)

Stop scraping Google's HTML. Use CRW's /v1/search to get ranked results plus full page content in one call. Build a SERP monitor and keyword rank tracker — runnable Python, self-host free under AGPL-3.0.

Jun 27, 2026
Tutorial·15 min read

Structured Web Extraction With JSON Schema and CRW (2026): No CSS Selectors

Extract typed JSON from any page with CRW's /v1/extract and a JSON schema — no CSS selectors, no per-site code. Validate with Pydantic, batch-extract, and handle failures. Runnable Python.

Jun 26, 2026
Tutorial·9 min read

Web Scraping in Elixir: Concurrency on BEAM

Web scraping in Elixir with Req, Floki, and Task.async_stream. BEAM concurrency for fan-out scraping and where a managed scrape API fits the pipeline.

Jun 24, 2026
Tutorial·7 min read

Bash & CLI Web Scraping: One-Off Shell Pipelines

One-off bash and CLI web scraping with curl, pup, and jq. Build interactive shell pipelines, see where they break, and know when to hand off to a scrape API.

Jun 23, 2026
Tutorial·12 min read

Headless Browser Scraping: A Practical Guide

Headless browser scraping in Python with Playwright and Selenium: waiting, infinite scroll, the true cost of a browser fleet, and when to offload to an API.

Jun 21, 2026
Tutorial·10 min read

Build a Competitor Monitoring Tool (Dashboard)

Build a competitor monitoring tool: crawl rival pages on a schedule, diff changes, and surface them in a dashboard. Full Python tutorial with cost math.

Jun 20, 2026
Tutorial·9 min read

Mastra + fastCRW: TypeScript Agents, One Binary

Build Mastra TypeScript agents with live web data via fastCRW. Typed Zod tools, Firecrawl-compatible REST, and a single ~8 MB self-hostable binary.

Jun 20, 2026
Tutorial·15 min read

Build a Jobs Aggregator in Python with CRW (2026): Crawl, Extract, Filter

Aggregate job postings across multiple career pages: crawl with CRW, extract structured roles via JSON schema, normalize, dedupe, and filter by keyword and location. Full Python — AGPL-3.0 self-host.

Jun 19, 2026
Tutorial·15 min read

Build a News Aggregator in Python with CRW (2026): Crawl, Dedupe, Summarize

Build a news aggregator that crawls source homepages with CRW, extracts headlines via JSON schema, dedupes near-duplicates, and writes a daily digest. Full Python — self-host free under AGPL-3.0.

Jun 19, 2026
Tutorial·8 min read

Verify a Firecrawl Drop-In Replacement: Smoke Test

Verify a Firecrawl drop-in replacement with a compatibility smoke test: assert field names, error envelopes, and the divergence matrix before you cut over.

Jun 13, 2026
Tutorial·8 min read

Port a TypeScript Scraper to Python: Skip the Rewrite

Port TypeScript browser automation to Python, or skip the rewrite with a Firecrawl-compatible API. Map Playwright/Puppeteer scripts or call one /v1/scrape.

Jun 12, 2026
Tutorial·15 min read

Migrating from Scrapy to fastCRW: A Practical Guide (2026)

A step-by-step guide to migrating a Scrapy codebase to fastCRW — what maps cleanly, what to keep Scrapy for, incremental migration patterns, and code before/after for spiders, pipelines, and crawls.

Jun 12, 2026
Tutorial·9 min read

Weaviate + fastCRW: Semantic Search From Web

Power Weaviate semantic search with fresh web data: crawl with fastCRW, vectorize clean markdown, and run hybrid search. End-to-end pipeline and credit costs.

Jun 11, 2026
Tutorial·8 min read

Cursor + fastCRW: Live Web Context via MCP

Wire fastCRW into Cursor with the crw-mcp server so your AI coding agent scrapes, crawls, and searches the live web. Setup, config, and credit costs explained.

Jun 9, 2026
Tutorial·9 min read

Sitemap to Crawl: Optimized Discovery at Scale

Go from sitemap to a full crawl on large sites: seed with /v1/map, then cap maxDepth and maxPages. Discovery patterns, caps, concurrency, and credit costs.

Jun 9, 2026
Tutorial·9 min read

Smolagents + fastCRW: Web Grounding, Zero Bloat

Add web search and scraping to Hugging Face smolagents with fastCRW: a single ~8 MB binary keeps the stack lean, plus the highest truth-recall of three tools.

Jun 7, 2026
Tutorial·14 min read

CRW Go Quickstart (2026): Scrape, Crawl, and Search With the HTTP API

A from-zero Go quickstart for CRW using the standard net/http client: scrape to markdown, crawl a site with job polling, map URLs, web search, and a worker-pool batch. Self-host free under AGPL-3.0.

Jun 5, 2026
Tutorial·14 min read

Web Scraping in Go (2026): Goroutines, Backpressure, and When to Stop Building It Yourself

A practical guide to web scraping in Go — colly/goquery, goroutine concurrency and backpressure, the anti-bot wall every Go scraper hits, and how to call a Rust scraping engine from Go without losing the static-binary ethos.

Jun 4, 2026
Tutorial·14 min read

Web Scraping in Java (2026): JSoup, the JVM Footprint Tax, and the Sidecar Pattern

Web scraping in Java for backend teams — JSoup and HtmlUnit, Selenium's heavyweight reality, the JVM memory tax for scrape workers, and why a single-binary scraping sidecar beats fattening your service.

Jun 1, 2026
Tutorial·11 min read

Pointing the Firecrawl SDK at Any Backend: The api_url Swap, Done Right (2026)

A hands-on guide to redirecting the official Firecrawl Python and Node SDKs at a Firecrawl-compatible backend via api_url — including LangChain/LlamaIndex, config patterns, and a parity test harness.

May 30, 2026
Tutorial·13 min read

CRW Python Quickstart (2026): Scrape, Crawl, Map, Search in 15 Minutes

A from-zero Python quickstart for CRW: install, scrape a page to markdown, crawl a site, map URLs, search the web, and extract JSON. Async batch included. Self-host free under AGPL-3.0.

May 27, 2026
Tutorial·16 min read

Scrape-to-RAG with LlamaIndex and CRW (2026): A Production Ingestion Pipeline

Build a production scrape-to-RAG pipeline: crawl a docs site with CRW, chunk clean markdown, embed with OpenAI, and query with LlamaIndex. Full runnable Python — self-host for $0 under AGPL-3.0.

May 22, 2026
Tutorial·15 min read

E-Commerce Stock & Restock Monitoring in Python with CRW (2026)

Build a restock monitor: poll product pages with CRW, extract stock status via JSON schema, detect in-stock transitions, and fire instant alerts. Full runnable Python — self-host free under AGPL-3.0.

May 21, 2026
Tutorial·10 min read

Build a Perplexity-Style Search Answer Engine in 50 Lines (with Citations)

fastCRW v0.7.0 ships answer: true on /v1/search — one call gives you a synthesized answer plus validated citations, powered by the managed LLM on paid plans. Full Python and TypeScript tutorial.

May 14, 2026
Tutorial·12 min read

fastCRW AI Web Summaries: A Managed-LLM Scrape-Summary Tutorial

Build a production AI web summarizer with fastCRW's managed LLM. Add a summary format to /v1/scrape — no LLM key to manage, usage metered in CRW credits on paid plans. Full Python and TypeScript code.

May 13, 2026
Tutorial·12 min read

Build a RAG Pipeline with LangChain and CRW in 5 Minutes

Use langchain-crw to crawl a docs site, chunk the content, embed into a vector store, and answer questions — all with LangChain's native interface.

Apr 30, 2026
Tutorial·16 min read

$5 VPS Web Scraping: Run CRW Where Firecrawl Can't

Deploy a full Firecrawl-compatible scraping API on a $5/month VPS with 512 MB RAM. CRW's tiny single-binary memory footprint makes it possible — here's the complete guide.

Apr 29, 2026
Tutorial·19 min read

How to Build a Job Board Scraper with CRW and OpenAI

Build a job board scraper with CRW and OpenAI — extract listings, match against your resume, and automate your job search.

Apr 29, 2026
Tutorial·14 min read

Exa Search API Guide for AI Agents: Search Types, MCP, Pricing, and Alternatives

A practical guide to the Exa Search API: search types, contents, MCP, pricing, and when fastCRW is a better production choice for AI agents.

Apr 27, 2026
Tutorial·18 min read

How to Build a Web Scraping Agent with LangGraph and CRW

Build a web scraping agent with LangGraph and CRW — graph-based orchestration, state management, and conditional routing.

Apr 27, 2026
Tutorial·14 min read

How to Connect CRW to n8n for Automated Scraping Workflows

Connect n8n to CRW's API for automated web scraping — build scheduled scrapers, data pipelines, and alerts without code.

Apr 26, 2026
Tutorial·20 min read

JavaScript Web Scraping in 2026 — 4 Approaches Tested (Cheerio, Puppeteer, Playwright, fastCRW)

JavaScript web scraping compared: Cheerio (fastest parsing), Puppeteer, Playwright, fastCRW API. Code examples in Node.js + TypeScript with cost, RAM, and reliability tradeoffs. Pick the right tool for your scraper.

Apr 21, 2026
Tutorial·14 min read

How to Build a RAG Chatbot with Langflow and CRW

Build a visual RAG chatbot pipeline in Langflow using CRW as the web scraping data source — no coding required.

Apr 20, 2026
Tutorial·12 min read

How to Automate Web Scraping with Make.com and CRW

Step-by-step guide to building automated web scraping workflows in Make.com using CRW's Firecrawl-compatible API — no code required.

Apr 20, 2026
Tutorial·13 min read

How to Use CRW with Lovable for AI App Prototyping

Build a web app prototype with Lovable's AI app builder that uses CRW/fastCRW for live web scraping — from prompt to working app in minutes.

Apr 19, 2026
Tutorial·10 min read

Add Web Scraping to OpenClaw Agents with CRW

Install the CRW plugin for OpenClaw and give your WhatsApp, Telegram, and Discord AI agents the ability to scrape, crawl, and map any website.

Apr 19, 2026
Tutorial·14 min read

Build a RAG-Powered Research Agent with CrewAI and CRW

Combine crewai-crw web scraping tools with a vector store to build a CrewAI agent that crawls sites, builds a knowledge base, and answers questions with RAG.

Apr 18, 2026
Tutorial·16 min read

How to Build a Lead Enrichment Pipeline with CRW

Build a lead enrichment pipeline that scrapes company websites, extracts structured data like industry, size, and tech stack, and enriches your CRM using CRW.

Apr 18, 2026
Tutorial·20 min read

How to Scrape Cloudflare-Protected Sites with CRW's Stealth Mode

CRW v0.0.11 adds automatic stealth JavaScript injection and Cloudflare challenge retry. Here's how it works under the hood, and how to configure it for maximum success rate.

Apr 17, 2026
Tutorial·16 min read

How to Use CRW with OpenAI Agents SDK for Web-Aware AI

Integrate CRW as a tool in OpenAI's Agents SDK. Build web-aware agents with function calling, handoffs, and real-time web scraping capabilities.

Apr 17, 2026
Tutorial·18 min read

How to Add Web Scraping to Claude Code in 30 Seconds

Give Claude Code web scraping superpowers with CRW's built-in MCP server. One command, zero config — scrape any website directly from your terminal AI assistant.

Apr 13, 2026
Tutorial·14 min read

How to Use CRW with CrewAI for Multi-Agent Web Scraping

Build a CrewAI crew with specialized agents for web scraping and data analysis. Use crewai-crw — the CRW tool package — for fast, clean content extraction.

Apr 12, 2026
Tutorial·20 min read

Browser Automation for AI Agents: Playwright, Stagehand, Browser Use, and APIs (2026)

Playwright, Puppeteer, Stagehand, Browser Use, Browserbase, or a scraping API? A practical guide to browser automation for AI agents in 2026.

Apr 11, 2026
Tutorial·15 min read

Building AI Agents with Google ADK and CRW

Use Google ADK with CRW for web scraping — learn function declarations, tool registration, and Gemini-powered scraping agents.

Apr 6, 2026
Tutorial·17 min read

How to Monitor Competitor Websites with CRW

Set up automated competitor website monitoring with CRW — detect changes, compare snapshots, and generate AI summaries of what your competitors are up to.

Apr 4, 2026
Tutorial·18 min read

Build an AI Price Tracker in Python (2026) — 50 Lines, Zero API Cost [Self-Hosted]

Build an AI price tracker in 50 lines of Python: scrape with fastCRW, extract structured prices via LLM, store in SQLite, alert on drops. AGPL-3.0 self-host, zero per-request cost — full code included.

Apr 3, 2026
Tutorial·18 min read

Web Scraping for Beginners: From Zero to Production (2026)

Beginner-friendly introduction to web scraping — what it is, how it works, legal considerations, tools overview, and hands-on examples with CRW's API.

Apr 3, 2026
Tutorial·20 min read

How to Build a Deep Research Agent with CRW

Build a deep research agent that searches, scrapes, and synthesizes findings into structured reports using CRW's scraping API.

Apr 2, 2026
Tutorial·22 min read

Python Web Scraping: The Complete Guide with CRW (2026)

Python web scraping guide — requests, Beautiful Soup, Scrapy, and the modern API approach with CRW. Code examples included.

Mar 29, 2026
Tutorial·6 min read

How to Self-Host a Firecrawl-Like API with a Single Binary

Run a Firecrawl-compatible scraping API on your own server in under 60 seconds using CRW's single Docker image.

Mar 9, 2026
Tutorial·16 min read

How to Convert Websites to Clean Markdown for LLMs

Turn any web page into clean, noise-free markdown ready for LLMs using CRW's scrape endpoint. No selectors, no regex.

Mar 8, 2026
Tutorial·20 min read

How to Expose Web Scraping to AI Agents with MCP

Connect CRW's built-in MCP server to Claude, Cursor, or any MCP-compatible AI agent for live web scraping in agentic workflows.

Mar 7, 2026
Tutorial·22 min read

How to Build a RAG Pipeline from Websites Using CRW

Step-by-step guide to scraping websites, converting to clean markdown, and feeding into a RAG pipeline using CRW's API.

Mar 6, 2026

Browse more

Jump back to the full archive

This category contains 54 of 156 total posts in the fastCRW blog archive.

View all blog posts