Extended GPT Scraper

1# Set API token
2API_TOKEN=<YOUR_API_TOKEN>
3
4# Prepare Actor input
5cat > input.json <<'EOF'
6{
7  "startUrls": [
8    {
9      "url": "https://news.ycombinator.com/"
10    }
11  ],
12  "instructions": "Gets the post with the most points from the page and returns it as JSON in this format: \npostTitle\npostUrl\npointsCount",
13  "model": "gpt-3.5-turbo",
14  "includeUrlGlobs": [],
15  "excludeUrlGlobs": [],
16  "linkSelector": "a[href]",
17  "initialCookies": [],
18  "proxyConfiguration": {
19    "useApifyProxy": true
20  },
21  "targetSelector": "",
22  "removeElementsCssSelector": "script, style, noscript, path, svg, xlink",
23  "skipGptGlobs": [],
24  "schema": {
25    "type": "object",
26    "properties": {
27      "title": {
28        "type": "string",
29        "description": "Page title"
30      },
31      "description": {
32        "type": "string",
33        "description": "Page description"
34      }
35    },
36    "required": [
37      "title",
38      "description"
39    ]
40  },
41  "schemaDescription": ""
42}
43EOF
44
45# Run the Actor using an HTTP API
46# See the full API reference at https://docs.apify.com/api/v2
47curl "https://api.apify.com/v2/acts/drobnikj~extended-gpt-scraper/runs?token=$API_TOKEN" \
48  -X POST \
49  -d @input.json \
50  -H 'Content-Type: application/json'