Library / Web Scraping & Research
Web Scraping & Research
Compile interview dossiers from Jina AI scraping, RSS feeds and Gemini
Triggered by a form submission, it resolves a company's domain and logo, scrapes its website, Google News RSS and Hacker News in parallel, then uses Gemini to build a visual research dossier.
What it does
## 1. Auto Domain Discovery and Parallel Scraping Resolves the official domain and logo, then scrapes the official site, Google News RSS (with URLs), and Hacker News threads simultaneously.
The steps
- Interview Research Form
- Auto-Discover Company URL
- Resolve URL and Visual Assets
- Scrape Website (Jina Reader)
- Fetch 6M News (Google RSS)
- Projects and Tech Pulse (HN API)
- Merge Research Streams
- Build Context with Source URLs
- Synthesize Dossier (LLM Chain)
- Google Gemini Chat Model
- Build Visual PDF Dossier
- Display and Auto-Print PDF in Browser
- Create Downloadable Dossier File
Similar automations
AI Agents & AssistantsRun AI Video Interviews and Score Candidates with BeyondPresence13 stepsMonitoring, Ops & IncidentsMonitor RSS Topics with OpenAI and Slack Alerts18 stepsAI Agents & AssistantsMarket Research Agent with Tavily Search and RSS6 stepsWeb Scraping & ResearchScrape Web Pages with Jina and OpenAI to Sheets6 steps