data-scraper-agent

Automated web scraping and Notion storage can be scheduled using GitHub Actions. This Skill uses Python with Playwright and BeautifulSoup to collect public data, then stores the scraped items directly into a Notion database on a recurring schedule.

Yes, you can enrich collected web scraping data using AI. This Skill uses Gemini Flash to automatically score, summarize, classify, or match each scraped item, adding an AI-driven analysis layer to your raw data collection pipeline.

Yes, Python is required to collect data from public websites using this approach. The scraping logic relies on Python libraries like requests, beautifulsoup4, and playwright to fetch and parse public sources before scheduling the runs with GitHub Actions.

The best way to monitor new GitHub repositories by topic is using an automated data collection agent. This Skill can track repositories tagged with keywords like 'llm' or 'agents', scrape the details, and enrich the listings with AI for structured database storage.

Yes, automated data collection works with dynamic web pages. This Skill includes Playwright as a dependency, allowing it to render and scrape JavaScript-driven public websites alongside static content parsed by BeautifulSoup and lxml.

Using a free LLM like Gemini Flash for data enrichment limits processing to its rate limits and context window size. While sufficient for summarizing and classifying standard scraped items, extremely large web scraping payloads may require batch processing to avoid exceeding API constraints.