Extended GPT Scraper

  • drobnikj/extended-gpt-scraper
  • Modified
  • Users 413
  • Runs 31.5k
  • Created by Author's avatarJakub Drobník

Extract data from any website and feed it into GPT via the OpenAI API. Use ChatGPT to proofread content, analyze sentiment, summarize reviews, extract contact details, and much more.

To run the code examples, you need to have an Apify account. Replace <YOUR_API_TOKEN> in the code with your API token. For a more detailed explanation, please read about running Actors via the API in Apify Docs.

# Set API token
API_TOKEN=<YOUR_API_TOKEN>

# Prepare Actor input
cat > input.json <<'EOF'
{
  "startUrls": [
    {
      "url": "https://news.ycombinator.com/"
    }
  ],
  "globs": [],
  "linkSelector": "a[href]",
  "instructions": "Gets the post with the most points from the page and returns it as JSON in this format: \npostTitle\npostUrl\npointsCount",
  "model": "gpt-3.5-turbo",
  "targetSelector": "",
  "schema": {
    "type": "object",
    "properties": {
      "title": {
        "type": "string",
        "description": "Page title"
      },
      "description": {
        "type": "string",
        "description": "Page description"
      }
    },
    "required": [
      "title",
      "description"
    ]
  },
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}
EOF

# Run the Actor
curl "https://api.apify.com/v2/acts/drobnikj~extended-gpt-scraper/runs?token=$API_TOKEN" \
  -X POST \
  -d @input.json \
  -H 'Content-Type: application/json'