ScraperCodeGenerator

1from apify_client import ApifyClient
2
3# Initialize the ApifyClient with your Apify API token
4# Replace '<YOUR_API_TOKEN>' with your token.
5client = ApifyClient("<YOUR_API_TOKEN>")
6
7# Prepare the Actor input
8run_input = {
9    "targetUrl": "https://books.toscrape.com/",
10    "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.",
11    "actors": [
12        {
13            "name": "cheerio-scraper",
14            "enabled": True,
15            "input": {
16                "maxRequestRetries": 3,
17                "requestTimeoutSecs": 30,
18                "maxPagesPerCrawl": 1,
19                "pageFunction": """async function pageFunction(context) {
20    const { request, log, $ } = context;
21    try {
22        const title = $('title').text() || '';
23        const html = $('html').html() || '';
24        return {
25            url: request.url,
26            title: title,
27            html: html
28        };
29    } catch (error) {
30        log.error('Error in pageFunction:', error);
31        return {
32            url: request.url,
33            title: '',
34            html: ''
35        };
36    }
37}""",
38                "proxyConfiguration": { "useApifyProxy": True },
39            },
40        },
41        {
42            "name": "web-scraper",
43            "enabled": False,
44            "input": {
45                "maxRequestRetries": 3,
46                "requestTimeoutSecs": 30,
47                "maxPagesPerCrawl": 1,
48                "pageFunction": """async function pageFunction(context) {
49    const { request, log, page } = context;
50    try {
51        const title = await page.title();
52        const html = await page.content();
53        return {
54            url: request.url,
55            title: title,
56            html: html
57        };
58    } catch (error) {
59        log.error('Error in pageFunction:', error);
60        return {
61            url: request.url,
62            title: '',
63            html: ''
64        };
65    }
66}""",
67                "proxyConfiguration": { "useApifyProxy": True },
68            },
69        },
70        {
71            "name": "website-content-crawler",
72            "enabled": True,
73            "input": {
74                "maxCrawlPages": 1,
75                "crawler": "playwright",
76                "proxyConfiguration": { "useApifyProxy": True },
77            },
78        },
79        {
80            "name": "playwright-scraper",
81            "enabled": False,
82            "input": {
83                "maxRequestRetries": 2,
84                "requestTimeoutSecs": 45,
85                "maxPagesPerCrawl": 1,
86                "pageFunction": """async function pageFunction(context) {
87    const { request, log, page } = context;
88    try {
89        const title = await page.title();
90        const html = await page.content();
91        return {
92            url: request.url,
93            title: title,
94            html: html
95        };
96    } catch (error) {
97        log.error('Error in pageFunction:', error);
98        return {
99            url: request.url,
100            title: '',
101            html: ''
102        };
103    }
104}""",
105                "proxyConfiguration": { "useApifyProxy": True },
106            },
107        },
108    ],
109}
110
111# Run the Actor and wait for it to finish
112run = client.actor("ohlava/scrapercodegenerator").call(run_input=run_input)
113
114# Fetch and print Actor results from the run's dataset (if there are any)
115print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
116for item in client.dataset(run["defaultDatasetId"]).iterate_items():
117    print(item)
118
119# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start