Vanilla JS Scraper

1from apify_client import ApifyClient
2
3# Initialize the ApifyClient with your Apify API token
4client = ApifyClient("<YOUR_API_TOKEN>")
5
6# Prepare the Actor input
7run_input = {
8    "requests": [{ "url": "https://apify.com" }],
9    "pseudoUrls": [{ "purl": "https://apify.com[(/[\\w-]+)?]" }],
10    "linkSelector": "a[href]",
11    "pageFunction": """async function pageFunction(context) {
12    const { window, document, crawler, enqueueRequest, request, response, userData, json, body, kvStore, customData } = context;
13
14    const title = document.querySelector('title').textContent
15
16    const responseHeaders = response.headers
17
18    return {
19        title,
20        responseHeaders
21    };
22}""",
23    "preNavigationHooks": """// We need to return array of (possibly async) functions here.
24// The functions accept two arguments: the \"crawlingContext\" object
25// and \"requestAsBrowserOptions\" which are passed to the `requestAsBrowser()`
26// function the crawler calls to navigate..
27[
28    async (crawlingContext, requestAsBrowserOptions) => {
29        // ...
30    }
31]""",
32    "postNavigationHooks": """// We need to return array of (possibly async) functions here.
33// The functions accept a single argument: the \"crawlingContext\" object.
34[
35    async (crawlingContext) => {
36        // ...
37    },
38]""",
39    "proxy": { "useApifyProxy": True },
40    "additionalMimeTypes": [],
41    "customData": {},
42}
43
44# Run the Actor and wait for it to finish
45run = client.actor("mstephen190/vanilla-js-scraper").call(run_input=run_input)
46
47# Fetch and print Actor results from the run's dataset (if there are any)
48print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
49for item in client.dataset(run["defaultDatasetId"]).iterate_items():
50    print(item)
51
52# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start