My Actor 32

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": "DEVELOPMENT",
10    "startUrls": [{ "url": "https://apify.com" }],
11    "globs": [],
12    "linkSelector": "a[href]",
13    "pseudoUrls": [{ "purl": "https://apify.com[(/[\\w-]+)?]" }],
14    "pageFunction": """// The function accepts a single argument: the \"context\" object.
15// For a complete list of its properties and functions,
16// see https://apify.com/apify/web-scraper#page-function 
17async function pageFunction(context) {
18    // This statement works as a breakpoint when you're trying to debug your code. Works only with Run mode: DEVELOPMENT!
19    // debugger; 
20
21    // jQuery is handy for finding DOM elements and extracting data from them.
22    // To use it, make sure to enable the \"Inject jQuery\" option.
23    const $ = context.jQuery;
24    const pageTitle = $('title').first().text();
25
26    // Print some information to actor log
27    context.log.info(`URL: ${context.request.url}, TITLE: ${pageTitle}`);
28
29    // Manually add a new page to the queue for scraping.
30   await context.enqueueRequest({ url: 'http://www.example.com' });
31
32    // Return an object with the data extracted from the page.
33    // It will be stored to the resulting dataset.
34    return {
35        url: context.request.url,
36        pageTitle
37    };
38}""",
39    "proxyConfiguration": { "useApifyProxy": True },
40    "initialCookies": [],
41    "waitUntil": ["networkidle2"],
42    "preNavigationHooks": """// We need to return array of (possibly async) functions here.
43// The functions accept two arguments: the \"crawlingContext\" object
44// and \"gotoOptions\".
45[
46    async (crawlingContext, gotoOptions) => {
47        // ...
48    },
49]
50""",
51    "postNavigationHooks": """// We need to return array of (possibly async) functions here.
52// The functions accept a single argument: the \"crawlingContext\" object.
53[
54    async (crawlingContext) => {
55        // ...
56    },
57]""",
58    "breakpointLocation": "NONE",
59    "customData": {},
60}
61
62# Run the Actor and wait for it to finish
63run = client.actor("honzakirchner43/my-actor-32").call(run_input=run_input)
64
65# Fetch and print Actor results from the run's dataset (if there are any)
66print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
67for item in client.dataset(run["defaultDatasetId"]).iterate_items():
68    print(item)
69
70# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start