Puppeteer Scraper

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    const { page, request, log } = context;
14    const title = await page.title();
15    log.info(`URL: ${request.url} TITLE: ${title}`);
16    return {
17        url: request.url,
18        title
19    };
20}""",
21    "proxyConfiguration": { "useApifyProxy": False },
22    "customData": {},
23    "initialCookies": [],
24    "preGotoFunction": """async function preGotoFunction({ request, page, Apify }) {
25    /* add your pre-navigation logic here, if needed */
26}""",
27}
28
29# Run the Actor and wait for it to finish
30run = client.actor("apify/puppeteer-scraper").call(run_input=run_input)
31
32# Fetch and print Actor results from the run's dataset (if there are any)
33print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
34for item in client.dataset(run["defaultDatasetId"]).iterate_items():
35    print(item)
36
37# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start