Crawler Puppeteer

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": [
10        { "url": "http://example.com" },
11        { "url": "http://iana.org" },
12    ],
13    "pseudoUrls": [{ "purl": "https://www.iana.org/[((?!\\.pdf$).)*]" }],
14    "linkSelector": "a",
15    "pageFunction": """async ({ request, page, keyValueStore, log }) => {
16    const title = await page.title();
17    log.info(`Title of page with url ${request.url} is: ${title}`);
18    await keyValueStore.setValue(Math.random().toString(36), { title });
19    return { title }
20}""",
21    "proxyConfiguration": { "useApifyProxy": False },
22}
23
24# Run the Actor and wait for it to finish
25run = client.actor("jancurn/crawler-puppeteer").call(run_input=run_input)
26
27# Fetch and print Actor results from the run's dataset (if there are any)
28print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
29for item in client.dataset(run["defaultDatasetId"]).iterate_items():
30    print(item)
31
32# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start