Extended GPT Scraper avatar
Extended GPT Scraper
Try for free

No credit card required

View all Actors
Extended GPT Scraper

Extended GPT Scraper

drobnikj/extended-gpt-scraper
Try for free

No credit card required

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.

The code examples below show how to run the Actor and get its results. To run the code, you need to have an Apify account. Replace <YOUR_API_TOKEN> in the code with your API token, which you can find under Settings > Integrations in Apify Console. Learn mode

Node.js

Python

curl

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'
Developer
Maintained by Apify
Actor metrics
  • 80 monthly users
  • 95.2% runs succeeded
  • 2.7 days response time
  • Created in Jun 2023
  • Modified 14 days ago