Web Scraper Task

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://crawlee.dev" }],
11    "linkSelector": "a[href]",
12    "globs": [{ "glob": "https://crawlee.dev/*/*" }],
13    "pseudoUrls": [],
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    const h1 = $('h1').first().text();
26    const first_h2 = $('h2').first().text();
27    const random_text_from_the_page = $('p').first().text();
28
29
30    // Print some information to actor log
31    context.log.info(`URL: ${context.request.url}, TITLE: ${pageTitle}`);
32
33    // Manually add a new page to the queue for scraping.
34   await context.enqueueRequest({ url: 'http://www.example.com' });
35
36    // Return an object with the data extracted from the page.
37    // It will be stored to the resulting dataset.
38    return {
39        url: context.request.url,
40        pageTitle,
41        h1,
42        first_h2,
43        random_text_from_the_page
44    };
45}""",
46    "proxyConfiguration": { "useApifyProxy": True },
47    "initialCookies": [],
48    "waitUntil": ["networkidle2"],
49    "preNavigationHooks": """// We need to return array of (possibly async) functions here.
50// The functions accept two arguments: the \"crawlingContext\" object
51// and \"gotoOptions\".
52[
53    async (crawlingContext, gotoOptions) => {
54        // ...
55    },
56]
57""",
58    "postNavigationHooks": """// We need to return array of (possibly async) functions here.
59// The functions accept a single argument: the \"crawlingContext\" object.
60[
61    async (crawlingContext) => {
62        // ...
63    },
64]""",
65    "breakpointLocation": "NONE",
66    "customData": {},
67}
68
69# Run the Actor and wait for it to finish
70run = client.actor("undrtkr984/web-scraper-task").call(run_input=run_input)
71
72# Fetch and print Actor results from the run's dataset (if there are any)
73print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
74for item in client.dataset(run["defaultDatasetId"]).iterate_items():
75    print(item)
76
77# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start