Web Scraper Experimental Debug

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    "pseudoUrls": [{ "purl": "https://apify.com[(/[\\w-]+)?]" }],
11    "linkSelector": "a",
12    "pageFunction": """async function pageFunction(context) {
13    // See README for context properties. If the syntax is unfamiliar see the link
14    // https://javascript.info/destructuring-assignment#object-destructuring
15    const { request, log, jQuery } = context;
16
17    // To be able to use jQuery as $, one needs save it into a variable
18    // and select the inject jQuery option. We've selected it for you.
19    const $ = jQuery;
20    const title = $('title').text();
21
22    // This is yet another new feature of Javascript called template strings.
23    // https://javascript.info/string#quotes
24    log.info(`URL: ${request.url} TITLE: ${title}`);
25
26    // To save data just return an object with the requested properties.
27    return {
28        url: request.url,
29        title
30    };
31}""",
32    "proxyConfiguration": { "useApifyProxy": False },
33    "initialCookies": [],
34    "waitUntil": ["networkidle2"],
35    "customData": {},
36}
37
38# Run the Actor and wait for it to finish
39run = client.actor("mtrunkat/web-scraper-experimental-dbgr").call(run_input=run_input)
40
41# Fetch and print Actor results from the run's dataset (if there are any)
42print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
43for item in client.dataset(run["defaultDatasetId"]).iterate_items():
44    print(item)
45
46# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start