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    "runMode": "PRODUCTION",
10    "startUrls": [{ "url": "https://www.example.com" }],
11    "pageFunction": """// The function accepts a single argument: the \"context\" object.
12// For a complete list of its properties and functions,
13// see https://apify.com/apify/web-scraper#page-function 
14async function pageFunction(context) {
15    // This statement works as a breakpoint when you're trying to debug your code. Works only with Run mode: DEVELOPMENT!
16    // debugger; 
17
18    // jQuery is handy for finding DOM elements and extracting data from them.
19    // To use it, make sure to enable the \"Inject jQuery\" option.
20    const $ = context.jQuery;
21    const pageTitle = $('title').first().text();
22    const h1 = $('h1').first().text();
23    const first_h2 = $('h2').first().text();
24    const random_text_from_the_page = $('p').first().text();
25
26
27    // Print some information to actor log
28    context.log.info(`URL: ${context.request.url}, TITLE: ${pageTitle}`);
29
30    // Manually add a new page to the queue for scraping.
31   await context.enqueueRequest({ url: 'http://www.example.com' });
32
33    // Return an object with the data extracted from the page.
34    // It will be stored to the resulting dataset.
35    return {
36        url: context.request.url,
37        pageTitle,
38        h1,
39        first_h2,
40        random_text_from_the_page
41    };
42}""",
43    "proxyConfiguration": { "useApifyProxy": True },
44    "proxyRotation": "UNTIL_FAILURE",
45    "initialCookies": [],
46    "waitUntil": ["networkidle2"],
47    "preNavigationHooks": """// We need to return array of (possibly async) functions here.
48// The functions accept two arguments: the \"crawlingContext\" object
49// and \"gotoOptions\".
50[
51    async (crawlingContext, gotoOptions) => {
52        // ...
53    },
54]
55""",
56    "postNavigationHooks": """// We need to return array of (possibly async) functions here.
57// The functions accept a single argument: the \"crawlingContext\" object.
58[
59    async (crawlingContext) => {
60        // ...
61    },
62]""",
63    "breakpointLocation": "NONE",
64    "customData": {},
65}
66
67# Run the Actor and wait for it to finish
68run = client.actor("xrhibiyftd/my-actr-testing").call(run_input=run_input)
69
70# Fetch and print Actor results from the run's dataset (if there are any)
71print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
72for item in client.dataset(run["defaultDatasetId"]).iterate_items():
73    print(item)
74
75# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start