feat: Add Crawlee + Stagehand actor templates (JS + TS)

templates/js-crawlee-stagehand-chrome/.actor/actor.json

@@ -0,0 +1,20 @@
+{
+    "actorSpecification": 1,
+    "name": "project-stagehand-crawler-javascript",
+    "title": "Project Stagehand Crawler JavaScript",
+    "description": "Crawlee and Stagehand project in JavaScript.",
+    "version": "0.0",
+    "meta": {
+        "templateId": "js-crawlee-stagehand-chrome",
+        "generatedBy": "<FILL-IN-MODEL>"
+    },
+    "input": "./input_schema.json",
+    "output": "./output_schema.json",
+    "storages": {
+        "dataset": "./dataset_schema.json"
+    },
+    "dockerfile": "../Dockerfile",
+    "environmentVariables": {
+        "OPENAI_API_KEY": "@OPENAI_API_KEY"
+    }
+}

templates/js-crawlee-stagehand-chrome/.actor/dataset_schema.json

@@ -0,0 +1,33 @@
+{
+    "actorSpecification": 1,
+    "fields": {},
+    "views": {
+        "overview": {
+            "title": "Overview",
+            "transformation": {
+                "fields": ["title", "heading", "description", "url"]
+            },
+            "display": {
+                "component": "table",
+                "properties": {
+                    "title": {
+                        "label": "Page Title",
+                        "format": "text"
+                    },
+                    "heading": {
+                        "label": "Heading",
+                        "format": "text"
+                    },
+                    "description": {
+                        "label": "Description",
+                        "format": "text"
+                    },
+                    "url": {
+                        "label": "URL",
+                        "format": "link"
+                    }
+                }
+            }
+        }
+    }
+}

templates/js-crawlee-stagehand-chrome/.actor/input_schema.json

@@ -0,0 +1,18 @@
+{
+    "title": "StagehandCrawler Template",
+    "type": "object",
+    "schemaVersion": 1,
+    "properties": {
+        "startUrls": {
+            "title": "Start URLs",
+            "type": "array",
+            "description": "URLs to start with.",
+            "editor": "requestListSources",
+            "prefill": [
+                {
+                    "url": "https://apify.com"
+                }
+            ]
+        }
+    }
+}

templates/js-crawlee-stagehand-chrome/.actor/output_schema.json

@@ -0,0 +1,11 @@
+{
+    "actorOutputSchemaVersion": 1,
+    "title": "Output schema",
+    "properties": {
+        "overview": {
+            "type": "string",
+            "title": "Overview",
+            "template": "{{links.apiDefaultDatasetUrl}}/items?view=overview"
+        }
+    }
+}

templates/js-crawlee-stagehand-chrome/.dockerignore

@@ -0,0 +1,15 @@
+# configurations
+.idea
+.vscode
+.zed
+
+# crawlee and apify storage folders
+apify_storage
+crawlee_storage
+storage
+
+# installed files
+node_modules
+
+# git folder
+.git

templates/js-crawlee-stagehand-chrome/.editorconfig

@@ -0,0 +1,10 @@
+root = true
+
+[*]
+indent_style = space
+indent_size = 4
+charset = utf-8
+trim_trailing_whitespace = true
+insert_final_newline = true
+end_of_line = lf
+quote_type = single

templates/js-crawlee-stagehand-chrome/.gitignore

@@ -0,0 +1,10 @@
+# This file tells Git which files shouldn't be added to source control
+
+.DS_Store
+.idea
+.vscode
+.zed
+dist
+node_modules
+apify_storage
+storage

templates/js-crawlee-stagehand-chrome/.prettierrc

@@ -0,0 +1,5 @@
+{
+    "printWidth": 120,
+    "tabWidth": 4,
+    "singleQuote": true
+}

templates/js-crawlee-stagehand-chrome/Dockerfile

@@ -0,0 +1,34 @@
+# Specify the base Docker image. You can read more about
+# the available images at https://crawlee.dev/docs/guides/docker-images
+# You can also use any other image from Docker Hub.
+FROM apify/actor-node-playwright-chrome:22-1.58.1
+
+# Check preinstalled packages
+RUN npm ls @crawlee/core apify puppeteer playwright
+
+# Copy just package.json and package-lock.json
+# to speed up the build using Docker layer cache.
+COPY --chown=myuser:myuser package*.json Dockerfile ./
+
+# Check Playwright version is the same as the one from base image.
+RUN node check-playwright-version.mjs
+
+# Install NPM packages, skip optional and development dependencies to
+# keep the image small. Avoid logging too much and print the dependency
+# tree for debugging
+RUN npm --quiet set progress=false \
+    && npm install --omit=dev --omit=optional \
+    && echo "Installed NPM packages:" \
+    && (npm list --omit=dev --all || true) \
+    && echo "Node.js version:" \
+    && node --version \
+    && echo "NPM version:" \
+    && npm --version \
+    && rm -r ~/.npm
+
+# Next, copy the remaining files and directories with the source code.
+# Since we do this after NPM install, quick build will be really fast
+# for most source file changes.
+COPY --chown=myuser:myuser . ./
+
+CMD ["node", "src/main.js"]

templates/js-crawlee-stagehand-chrome/README.md

@@ -0,0 +1,23 @@
+## StagehandCrawler template
+
+<!-- This is an Apify template readme -->
+
+This template is a production-ready boilerplate for developing an [Actor](https://apify.com/actors) with `StagehandCrawler`. It combines [Crawlee](https://crawlee.dev)'s powerful crawling infrastructure with [Stagehand](https://github.com/browserbase/stagehand)'s AI-powered browser automation, enabling you to interact with web pages and extract structured data using natural language instructions.
+
+The template demonstrates two key Stagehand capabilities:
+- **`act()`** — Perform actions on a page using natural language (e.g., closing cookie dialogs)
+- **`extract()`** — Extract structured data from pages using Zod schemas and AI
+
+## Resources
+
+If you're looking for examples or want to learn more visit:
+
+- [Crawlee + Apify Platform guide](https://crawlee.dev/docs/guides/apify-platform)
+- [Stagehand documentation](https://docs.stagehand.dev)
+- [Crawlee documentation](https://crawlee.dev/docs/quick-start)
+- [Node.js tutorials](https://docs.apify.com/academy/node-js) in Academy
+- [Integration with Zapier](https://apify.com/integrations), Make, GitHub, Google Drive and other apps
+- [Video guide on getting data using Apify API](https://www.youtube.com/watch?v=ViYYDHSBAKM)
+- A short guide on how to create Actors using code templates:
+
+[web scraper template](https://www.youtube.com/watch?v=u-i-Korzf8w)

templates/js-crawlee-stagehand-chrome/eslint.config.mjs

@@ -0,0 +1,6 @@
+import prettier from 'eslint-config-prettier';
+
+import apify from '@apify/eslint-config/js.js';
+
+// eslint-disable-next-line import/no-default-export
+export default [{ ignores: ['**/dist'] }, ...apify, prettier];

templates/js-crawlee-stagehand-chrome/package.json

@@ -0,0 +1,30 @@
+{
+    "name": "crawlee-stagehand-javascript",
+    "version": "0.0.1",
+    "type": "module",
+    "description": "This is an example of an Apify Actor.",
+    "dependencies": {
+        "apify": "^3.5.2",
+        "@crawlee/stagehand": "^3.16.0",
+        "playwright": "1.58.1",
+        "openai": "^4.96.0",
+        "zod": "^3.25.0"
+    },
+    "devDependencies": {
+        "@apify/eslint-config": "^1.0.0",
+        "eslint": "^9.29.0",
+        "eslint-config-prettier": "^10.1.5",
+        "prettier": "^3.5.3"
+    },
+    "scripts": {
+        "start": "node src/main.js",
+        "format": "prettier --write .",
+        "format:check": "prettier --check .",
+        "lint": "eslint",
+        "lint:fix": "eslint --fix",
+        "test": "echo \"Error: oops, the Actor has no tests yet, sad!\" && exit 1",
+        "postinstall": "npx crawlee install-playwright-browsers"
+    },
+    "author": "It's not you it's me",
+    "license": "ISC"
+}

templates/js-crawlee-stagehand-chrome/src/main.js

@@ -0,0 +1,44 @@
+/**
+ * This template is a production ready boilerplate for developing with `StagehandCrawler`.
+ * Use this to bootstrap your projects using the most up-to-date code.
+ * If you're looking for examples or want to learn more, see README.
+ */
+
+// For more information, see https://crawlee.dev
+import { StagehandCrawler } from '@crawlee/stagehand';
+// For more information, see https://docs.apify.com/sdk/js
+import { Actor } from 'apify';
+
+// this is ESM project, and as such, it requires you to specify extensions in your relative imports
+// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
+import { router } from './routes.js';
+
+// Initialize the Apify SDK
+await Actor.init();
+
+const { startUrls = ['https://apify.com'] } = (await Actor.getInput()) ?? {};
+
+// `checkAccess` flag ensures the proxy credentials are valid, but the check can take a few hundred milliseconds.
+// Disable it for short runs if you are sure your proxy configuration is correct
+const proxyConfiguration = await Actor.createProxyConfiguration({ checkAccess: true });
+
+const crawler = new StagehandCrawler({
+    proxyConfiguration,
+    requestHandler: router,
+    stagehandOptions: {
+        model: 'openai/gpt-4o-mini',
+        apiKey: process.env.OPENAI_API_KEY,
+    },
+    launchContext: {
+        launchOptions: {
+            args: [
+                '--disable-gpu', // Mitigates the "crashing GPU process" issue in Docker containers
+            ],
+        },
+    },
+});
+
+await crawler.run(startUrls);
+
+// Exit successfully
+await Actor.exit();

templates/js-crawlee-stagehand-chrome/src/routes.js

@@ -0,0 +1,35 @@
+import { createStagehandRouter, Dataset } from '@crawlee/stagehand';
+import { z } from 'zod';
+
+export const router = createStagehandRouter();
+
+router.addDefaultHandler(async ({ enqueueLinks, log }) => {
+    log.info('enqueueing new URLs');
+    await enqueueLinks({
+        globs: ['https://apify.com/*'],
+        label: 'detail',
+    });
+});
+
+router.addHandler('detail', async ({ request, page, log }) => {
+    const title = await page.title();
+    log.info(`${title}`, { url: request.loadedUrl });
+
+    // Use Stagehand act() to interact with the page
+    await page.act('Close any cookie consent dialogs or popups if present');
+
+    // Use Stagehand extract() to pull structured data with a Zod schema
+    const extracted = await page.extract({
+        instruction: 'Extract the main heading and a brief description of this page',
+        schema: z.object({
+            heading: z.string().describe('The main heading of the page'),
+            description: z.string().describe('A brief description or subtitle of the page'),
+        }),
+    });
+
+    await Dataset.pushData({
+        url: request.loadedUrl,
+        title,
+        ...extracted,
+    });
+});

templates/manifest.json

@@ -413,6 +413,22 @@
             "showcaseFiles": ["src/main.js", "src/routes.js"],
             "useCases": ["WEB_SCRAPING"]
         },
+        {
+            "id": "js-crawlee-stagehand-chrome",
+            "name": "project_stagehand_crawler_js",
+            "label": "Crawlee + Stagehand + Chrome",
+            "category": "javascript",
+            "technologies": ["nodejs", "crawlee", "stagehand", "chrome"],
+            "description": "AI-powered web scraper using Crawlee and Stagehand. Uses natural language to interact with pages and extract structured data using LLMs.",
+            "archiveUrl": "https://github.com/apify/actor-templates/blob/master/dist/templates/js-crawlee-stagehand-chrome.zip?raw=true",
+            "defaultRunOptions": {
+                "build": "latest",
+                "memoryMbytes": 4096,
+                "timeoutSecs": 3600
+            },
+            "showcaseFiles": ["src/main.js", "src/routes.js"],
+            "useCases": ["AI", "WEB_SCRAPING"]
+        },
         {
             "id": "js-crawlee-playwright-camoufox",
             "name": "project_playwright_camoufox_crawler_js",
@@ -494,6 +510,22 @@
             "showcaseFiles": ["src/main.ts", "src/routes.ts"],
             "useCases": ["WEB_SCRAPING"]
         },
+        {
+            "id": "ts-crawlee-stagehand-chrome",
+            "name": "project_stagehand_crawler_ts",
+            "label": "Crawlee + Stagehand + Chrome",
+            "category": "typescript",
+            "technologies": ["nodejs", "crawlee", "stagehand", "chrome"],
+            "description": "AI-powered web scraper using Crawlee and Stagehand. Uses natural language to interact with pages and extract structured data using LLMs.",
+            "archiveUrl": "https://github.com/apify/actor-templates/blob/master/dist/templates/ts-crawlee-stagehand-chrome.zip?raw=true",
+            "defaultRunOptions": {
+                "build": "latest",
+                "memoryMbytes": 4096,
+                "timeoutSecs": 3600
+            },
+            "showcaseFiles": ["src/main.ts", "src/routes.ts"],
+            "useCases": ["AI", "WEB_SCRAPING"]
+        },
         {
             "id": "ts-crawlee-playwright-camoufox",
             "name": "project_playwright_camoufox_crawler_ts",

templates/ts-crawlee-stagehand-chrome/.actor/actor.json

@@ -0,0 +1,20 @@
+{
+    "actorSpecification": 1,
+    "name": "project-stagehand-crawler-typescript",
+    "title": "Project Stagehand Crawler Typescript",
+    "description": "Crawlee and Stagehand project in typescript.",
+    "version": "0.0",
+    "meta": {
+        "templateId": "ts-crawlee-stagehand-chrome",
+        "generatedBy": "<FILL-IN-MODEL>"
+    },
+    "input": "./input_schema.json",
+    "output": "./output_schema.json",
+    "storages": {
+        "dataset": "./dataset_schema.json"
+    },
+    "dockerfile": "../Dockerfile",
+    "environmentVariables": {
+        "OPENAI_API_KEY": "@OPENAI_API_KEY"
+    }
+}