Web Scraper new

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    "startUrls": [{ "url": "https://apify.com" }],
10    "linkSelector": "a[href]",
11    "pseudoUrls": [{ "purl": "https://apify.com[(/[\\w-]+)?]" }],
12    "pageFunction": """// The function accepts a single argument: the \"context\" object.
13// For a complete list of its properties and functions,
14// see https://apify.com/apify/web-scraper#page-function 
15async function pageFunction(context) {
16    // jQuery is handy for finding DOM elements and extracting data from them.
17    // To use it, make sure to enable the \"Inject jQuery\" option.
18    const $ = context.jQuery;
19    const pageTitle = $('title').first().text();
20
21    // Print some information to actor log
22    context.log.info(`URL: ${context.request.url}, TITLE: ${pageTitle}`);
23
24    // Manually add a new page to the queue for scraping.
25    // To make this work, make sure the \"Use request queue\" option is enabled.
26    context.enqueueRequest({ url: 'http://www.example.com' });
27
28    // Return an object with the data extracted from the page.
29    // It will be stored to the resulting dataset.
30    return {
31        url: context.request.url,
32        pageTitle
33    };
34}""",
35    "proxyConfiguration": { "useApifyProxy": False },
36    "initialCookies": [],
37    "waitUntil": ["networkidle2"],
38    "customData": {},
39}
40
41# Run the Actor and wait for it to finish
42run = client.actor("honzakirchner43/web-scraper-new").call(run_input=run_input)
43
44# Fetch and print Actor results from the run's dataset (if there are any)
45print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
46for item in client.dataset(run["defaultDatasetId"]).iterate_items():
47    print(item)
48
49# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start