A smart web crawler built in Rust that uses Claude AI to select the most relevant URLs from website sitemaps based on crawling objectives.
git clone https://github.com/pixlie/SmartCrawler.gitSmartCrawler is a web crawler built in Rust that uses WebDriver to extract and parse HTML content from multiple web pages simultaneously. It features intelligent duplicate detection to automatically filter redundant content patterns across domains, and template pattern recognition to identify variable content like dynamic counts or timestamps. The tool provides structured HTML tree views with detailed filtering information, making it useful for researchers, developers, and data extraction workflows. SmartCrawler supports both Firefox and Chrome WebDrivers and runs on Windows, macOS, and Linux with minimal system requirements.
Install SmartCrawler from releases or build from source, then set up WebDriver (GeckoDriver for Firefox or ChromeDriver for Chrome). Run the crawler with `smart-crawler --link "https://example.com"` for basic crawling, or add `--verbose` and `--template` flags for detailed analysis and pattern detection. Multiple URLs can be crawled by specifying multiple `--link` parameters.
Extract and deduplicate content from multi-page websites for research
Identify template patterns in dynamically generated web content
Crawl multiple domain URLs in a single session for comparative analysis
Parse structured HTML data with automatic filtering of duplicate patterns
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/pixlie/SmartCrawlerCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
I'm using SmartCrawler to analyze [WEBSITE] in the [INDUSTRY] sector. My objective is to find URLs related to [TOPIC]. Please evaluate these sitemap URLs and select the 10 most relevant ones based on my objective. Return the results in a numbered list with brief explanations for each selection.
# Relevant URLs for [WEBSITE] Analysis Based on your objective to find content about [TOPIC] in the [INDUSTRY] sector, here are the top 10 most relevant URLs from the sitemap: 1. **/industry-trends/[TOPIC]** - This URL directly matches your topic and is likely to contain comprehensive industry analysis. 2. **/case-studies/[TOPIC]-success** - A case study page that demonstrates real-world applications of [TOPIC]. 3. **/whitepapers/[TOPIC]-research** - A research whitepaper that provides in-depth insights into [TOPIC]. 4. **/blog/category/[TOPIC]** - A blog category page that aggregates all posts related to [TOPIC]. 5. **/products/[TOPIC]-solutions** - A product page that lists solutions specifically designed for [TOPIC]. 6. **/events/[TOPIC]-conference** - An event page for an upcoming conference focused on [TOPIC]. 7. **/webinars/[TOPIC]-webinar** - A webinar page that offers an educational session on [TOPIC]. 8. **/resources/[TOPIC]-guide** - A comprehensive guide that covers various aspects of [TOPIC]. 9. **/news/[TOPIC]-updates** - A news section that provides the latest updates and developments related to [TOPIC]. 10. **/about/team/[TOPIC]-experts** - A team page that highlights experts specializing in [TOPIC].
AI assistant built for thoughtful, nuanced conversation
Get more done every day with Microsoft Teams – powered by AI
Automate security compliance and monitor real-time security posture seamlessly.
Automate your spreadsheet tasks with AI power
Agentic AI Workflow platform
Connected workspace for docs, wikis, and projects
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan