Extended GPT Scraper

1from apify_client import ApifyClient
2
3# Initialize the ApifyClient with your Apify API token
4client = ApifyClient("<YOUR_API_TOKEN>")
5
6# Prepare the Actor input
7run_input = {
8    "startUrls": [{ "url": "https://news.ycombinator.com/" }],
9    "instructions": """Gets the post with the most points from the page and returns it as JSON in this format: 
10postTitle
11postUrl
12pointsCount""",
13    "model": "gpt-3.5-turbo",
14    "includeUrlGlobs": [],
15    "excludeUrlGlobs": [],
16    "linkSelector": "a[href]",
17    "initialCookies": [],
18    "proxyConfiguration": { "useApifyProxy": True },
19    "targetSelector": "",
20    "removeElementsCssSelector": "script, style, noscript, path, svg, xlink",
21    "skipGptGlobs": [],
22    "schema": {
23        "type": "object",
24        "properties": {
25            "title": {
26                "type": "string",
27                "description": "Page title",
28            },
29            "description": {
30                "type": "string",
31                "description": "Page description",
32            },
33        },
34        "required": [
35            "title",
36            "description",
37        ],
38    },
39    "schemaDescription": "",
40}
41
42# Run the Actor and wait for it to finish
43run = client.actor("drobnikj/extended-gpt-scraper").call(run_input=run_input)
44
45# Fetch and print Actor results from the run's dataset (if there are any)
46print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
47for item in client.dataset(run["defaultDatasetId"]).iterate_items():
48    print(item)
49
50# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start