🧠 Y Combinator Job Scraper (Apify Actor) This Apify actor scrapes job listings from WorkAtAStartup.com, the official Y Combinator job board, and uses the Perplexity AI API to extract structured job data based on keywords and location filters. --- ## 🚀 How It Works 1. Scrapes the raw job board HTML from https://www.workatastartup.com/jobs. 2. Extracts unstructured job descriptions using BeautifulSoup. 3. Builds a custom prompt with keyword and location filters. 4. Sends the prompt to Perplexity AI (Sonar-Pro model) to get structured JSON. 5. Pushes the output to the Apify dataset. --- ## 🧾 Input Schema | Field | Type | Description | |-----------|--------|------------------------------------------------------------| | keywords | Array of strings | Keywords to filter jobs (e.g., ["python", "AI", "remote"]) | | location | String | Location filter (e.g., "remote", "San Francisco") | Example input: json { "keywords": ["data", "python", "backend"], "location": "remote" } 📤 Output Format The actor returns a JSON array of job listings with the following fields: json { "title": "Senior Backend Engineer", "company": "AI Robotics Inc", "location": "Remote", "link": "https://www.workatastartup.com/jobs/12345" } Each object contains: title: Job title company: Company name location: Job location link: Direct job listing link