feat(utilities): add new helpers for "run on apify" button

packages/utilities/src/index.ts

@@ -6,3 +6,4 @@ export * from './parse_jsonl_stream';
 export * from './streams_utilities';
 export * from './webhook_payload_template';
 export * from './crypto';
+export * from './url_params_utils';

packages/utilities/src/url_params_utils.ts

@@ -0,0 +1,30 @@
+/**
+ * Encodes object (e.g. input for actor) to a string hash.
+ */
+export function encodeInput<T extends object>(input: T) {
+    const data = JSON.stringify(input);
+    const buffer = Buffer.from(data, 'utf8');
+
+    return buffer.toString('base64url');
+}
+
+/**
+ * Decodes a string hash produced via `encodeInput` back into the original object.
+ */
+export function decodeInput(urlHash: string) {
+    const buffer = Buffer.from(urlHash, 'base64url');
+    const decoded = buffer.toString('utf8');
+
+    return JSON.parse(decoded);
+}
+
+/**
+ * Extract import statements from the code.
+ */
+export function separateImports(code: string): { code: string; imports: string } {
+    const lines = code.split('\n');
+    return {
+        code: lines.filter((line) => !line.trim().startsWith('import')).join('\n'),
+        imports: lines.filter((line) => line.trim().startsWith('import')).join('\n'),
+    };
+}

test/url-params-utils.test.ts

@@ -0,0 +1,48 @@
+import { encodeInput, decodeInput, separateImports } from '@apify/utilities';
+
+const input = {
+    code: `import { PlaywrightCrawler, Dataset } from 'crawlee';
+
+// PlaywrightCrawler crawls the web using a headless
+// browser controlled by the Playwright library.
+const crawler = new PlaywrightCrawler({
+// Use the requestHandler to process each of the crawled pages.
+async requestHandler({ request, page, enqueueLinks, log }) {
+    const title = await page.title();
+    log.info(\`Title of \${request.loadedUrl} is '\${title}'\`);
+
+    // Save results as JSON to ./storage/datasets/default
+    await Dataset.pushData({ title, url: request.loadedUrl });
+
+    // Extract links from the current page
+    // and add them to the crawling queue.
+    await enqueueLinks();
+},
+// Uncomment this option to see the browser window.
+// headless: false,
+});
+
+// Add first URL to the queue and start the crawl.
+await crawler.run(['https://crawlee.dev']);`,
+};
+
+test('encode/decode', async () => {
+    const hash = encodeInput(input);
+    const decoded = decodeInput(hash);
+
+    expect(input).toEqual(decoded);
+});
+
+test('import extraction', async () => {
+    const { code, imports } = separateImports(input.code);
+    const codeLines = code.split('\n');
+    const importLines = imports.split('\n');
+
+    for (const line of codeLines) {
+        expect(line).not.toMatch(/^import/);
+    }
+
+    for (const line of importLines) {
+        expect(line).toMatch(/^import/);
+    }
+});