Playwright 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://crawlee.dev" }],
10    "globs": [{ "glob": "https://crawlee.dev/*/*" }],
11    "pseudoUrls": [],
12    "excludes": [{ "glob": "/**/*.{png,jpg,jpeg,pdf}" }],
13    "linkSelector": "a",
14    "pageFunction": """async function pageFunction(context) {
15    const { page, request, log } = context;
16    const title = await page.title();
17    log.info(`URL: ${request.url} TITLE: ${title}`);
18    return {
19        url: request.url,
20        title
21    };
22}""",
23    "proxyConfiguration": { "useApifyProxy": True },
24    "initialCookies": [],
25    "launcher": "chromium",
26    "waitUntil": "networkidle",
27    "preNavigationHooks": """// We need to return array of (possibly async) functions here.
28// The functions accept two arguments: the \"crawlingContext\" object
29// and \"gotoOptions\".
30[
31    async (crawlingContext, gotoOptions) => {
32        const { page } = crawlingContext;
33        // ...
34    },
35]""",
36    "postNavigationHooks": """// We need to return array of (possibly async) functions here.
37// The functions accept a single argument: the \"crawlingContext\" object.
38[
39    async (crawlingContext) => {
40        const { page } = crawlingContext;
41        // ...
42    },
43]""",
44    "customData": {},
45}
46
47# Run the Actor and wait for it to finish
48run = client.actor("apify/playwright-scraper").call(run_input=run_input)
49
50# Fetch and print Actor results from the run's dataset (if there are any)
51print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
52for item in client.dataset(run["defaultDatasetId"]).iterate_items():
53    print(item)
54
55# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start