$echo '{
< "startUrls": [
< {
< "url": "https://crawlee.dev/js"
< }
< ],
< "globs": [
< {
< "glob": "https://crawlee.dev/js/*/*"
< }
< ],
< "pseudoUrls": [],
< "excludes": [
< {
< "glob": "/**/*.{png,jpg,jpeg,pdf}"
< }
< ],
< "linkSelector": "a",
< "respectRobotsTxtFile": true,
< "pageFunction": "async function pageFunction(context) {\\n const { page, request, log } = context;\\n const title = await page.title();\\n log.info(`URL: ${request.url} TITLE: ${title}`);\\n return {\\n url: request.url,\\n title\\n };\\n}",
< "proxyConfiguration": {
< "useApifyProxy": true
< },
< "initialCookies": [],
< "launcher": "chromium",
< "waitUntil": "networkidle",
< "preNavigationHooks": "// We need to return array of (possibly async) functions here.\\n// The functions accept two arguments: the \\"crawlingContext\\" object\\n// and \\"gotoOptions\\".\\n[\\n async (crawlingContext, gotoOptions) => {\\n const { page } = crawlingContext;\\n // ...\\n },\\n]",
< "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 const { page } = crawlingContext;\\n // ...\\n },\\n]",
< "customData": {}
<}' |
<apify call apify/playwright-scraper --silent --output-dataset