ScraperCodeGenerator

1import { ApifyClient } from 'apify-client';
2
3// Initialize the ApifyClient with your Apify API token
4// Replace the '<YOUR_API_TOKEN>' with your token
5const client = new ApifyClient({
6    token: '<YOUR_API_TOKEN>',
7});
8
9// Prepare Actor input
10const input = {
11    "targetUrl": "https://books.toscrape.com/",
12    "userGoal": "Get me a list of all the books on the first page. For each book, I want its title, price, star rating, and whether it is in stock.",
13    "actors": [
14        {
15            "name": "cheerio-scraper",
16            "enabled": true,
17            "input": {
18                "maxRequestRetries": 3,
19                "requestTimeoutSecs": 30,
20                "maxPagesPerCrawl": 1,
21                "pageFunction": "async function pageFunction(context) {\n    const { request, log, $ } = context;\n    try {\n        const title = $('title').text() || '';\n        const html = $('html').html() || '';\n        return {\n            url: request.url,\n            title: title,\n            html: html\n        };\n    } catch (error) {\n        log.error('Error in pageFunction:', error);\n        return {\n            url: request.url,\n            title: '',\n            html: ''\n        };\n    }\n}",
22                "proxyConfiguration": {
23                    "useApifyProxy": true
24                }
25            }
26        },
27        {
28            "name": "web-scraper",
29            "enabled": false,
30            "input": {
31                "maxRequestRetries": 3,
32                "requestTimeoutSecs": 30,
33                "maxPagesPerCrawl": 1,
34                "pageFunction": "async function pageFunction(context) {\n    const { request, log, page } = context;\n    try {\n        const title = await page.title();\n        const html = await page.content();\n        return {\n            url: request.url,\n            title: title,\n            html: html\n        };\n    } catch (error) {\n        log.error('Error in pageFunction:', error);\n        return {\n            url: request.url,\n            title: '',\n            html: ''\n        };\n    }\n}",
35                "proxyConfiguration": {
36                    "useApifyProxy": true
37                }
38            }
39        },
40        {
41            "name": "website-content-crawler",
42            "enabled": true,
43            "input": {
44                "maxCrawlPages": 1,
45                "crawler": "playwright",
46                "proxyConfiguration": {
47                    "useApifyProxy": true
48                }
49            }
50        },
51        {
52            "name": "playwright-scraper",
53            "enabled": false,
54            "input": {
55                "maxRequestRetries": 2,
56                "requestTimeoutSecs": 45,
57                "maxPagesPerCrawl": 1,
58                "pageFunction": "async function pageFunction(context) {\n    const { request, log, page } = context;\n    try {\n        const title = await page.title();\n        const html = await page.content();\n        return {\n            url: request.url,\n            title: title,\n            html: html\n        };\n    } catch (error) {\n        log.error('Error in pageFunction:', error);\n        return {\n            url: request.url,\n            title: '',\n            html: ''\n        };\n    }\n}",
59                "proxyConfiguration": {
60                    "useApifyProxy": true
61                }
62            }
63        }
64    ]
65};
66
67// Run the Actor and wait for it to finish
68const run = await client.actor("ohlava/scrapercodegenerator").call(input);
69
70// Fetch and print Actor results from the run's dataset (if any)
71console.log('Results from dataset');
72console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
73const { items } = await client.dataset(run.defaultDatasetId).listItems();
74items.forEach((item) => {
75    console.dir(item);
76});
77
78// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs