Vanilla JS Scraper

1# Set API token
2API_TOKEN=<YOUR_API_TOKEN>
3
4# Prepare Actor input
5cat > input.json <<'EOF'
6{
7  "requests": [
8    {
9      "url": "https://apify.com"
10    }
11  ],
12  "pseudoUrls": [
13    {
14      "purl": "https://apify.com[(/[\\w-]+)?]"
15    }
16  ],
17  "linkSelector": "a[href]",
18  "pageFunction": "async function pageFunction(context) {\n    const { window, document, crawler, enqueueRequest, request, response, userData, json, body, kvStore, customData } = context;\n\n    const title = document.querySelector('title').textContent\n\n    const responseHeaders = response.headers\n\n    return {\n        title,\n        responseHeaders\n    };\n}",
19  "preNavigationHooks": "// We need to return array of (possibly async) functions here.\n// The functions accept two arguments: the \"crawlingContext\" object\n// and \"requestAsBrowserOptions\" which are passed to the `requestAsBrowser()`\n// function the crawler calls to navigate..\n[\n    async (crawlingContext, requestAsBrowserOptions) => {\n        // ...\n    }\n]",
20  "postNavigationHooks": "// We need to return array of (possibly async) functions here.\n// The functions accept a single argument: the \"crawlingContext\" object.\n[\n    async (crawlingContext) => {\n        // ...\n    },\n]",
21  "proxy": {
22    "useApifyProxy": true
23  },
24  "additionalMimeTypes": [],
25  "customData": {}
26}
27EOF
28
29# Run the Actor using an HTTP API
30# See the full API reference at https://docs.apify.com/api/v2
31curl "https://api.apify.com/v2/acts/mstephen190~vanilla-js-scraper/runs?token=$API_TOKEN" \
32  -X POST \
33  -d @input.json \
34  -H 'Content-Type: application/json'