feat: add Camoufox-based Crawlee JS/TS templates (#336)

Following the apify/apify-sdk-js#364 and
apify/crawlee#2842 , this PR adds
Camoufox-enabled templates to Apify Actor templates. The implementation
is heavily based on the existing Playwright + Chrome templates.

The only issue (I'm aware of) currently is the immense size of those
images (as they contain Chrome and we add Camoufox binaries). Installing
Camoufox directly to a `node-debian` image results in missing system
dependencies. While it might be possible to install those manually in
the Dockerfile, it might make the Dockerfile too complex for a regular
user.


![image](https://github.com/user-attachments/assets/fb0050fd-fadc-4bbc-80f3-0681dcfa2b92)

Author: barjin

templates/js-crawlee-playwright-camoufox/.actor/Dockerfile

@@ -0,0 +1,33 @@
+# 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:20
+
+# Check preinstalled packages
+RUN npm ls crawlee apify playwright
+
+# Copy just package.json and package-lock.json
+# to speed up the build using Docker layer cache.
+COPY --chown=myuser package*.json ./
+
+# 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 \
+    && 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 . ./
+
+# Run the image. If you know you won't need headful browsers,
+# you can remove the XVFB start script for a micro perf gain.
+CMD ./start_xvfb_and_run_cmd.sh && npm start --silent

templates/js-crawlee-playwright-camoufox/.actor/actor.json

@@ -0,0 +1,12 @@
+{
+    "actorSpecification": 1,
+    "name": "project-playwright-camoufox-crawler-javascript",
+    "title": "Camoufox Playwright Crawler JavaScript",
+    "description": "Crawlee and Playwright project with Camoufox in JavaScript.",
+    "version": "0.0",
+    "meta": {
+        "templateId": "js-crawlee-playwright-camoufox"
+    },
+    "input": "./input_schema.json",
+    "dockerfile": "./Dockerfile"
+}

templates/js-crawlee-playwright-camoufox/.actor/input_schema.json

@@ -0,0 +1,18 @@
+{
+    "title": "PlaywrightCrawler 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-playwright-camoufox/.dockerignore

@@ -0,0 +1,13 @@
+# configurations
+.idea
+
+# crawlee and apify storage folders
+apify_storage
+crawlee_storage
+storage
+
+# installed files
+node_modules
+
+# git folder
+.git

templates/js-crawlee-playwright-camoufox/.editorconfig

@@ -0,0 +1,9 @@
+root = true
+
+[*]
+indent_style = space
+indent_size = 4
+charset = utf-8
+trim_trailing_whitespace = true
+insert_final_newline = true
+end_of_line = lf

templates/js-crawlee-playwright-camoufox/.eslintrc

@@ -0,0 +1,4 @@
+{
+    "extends": "@apify",
+    "root": true
+}

templates/js-crawlee-playwright-camoufox/.gitignore

@@ -0,0 +1,8 @@
+# This file tells Git which files shouldn't be added to source control
+
+.DS_Store
+.idea
+dist
+node_modules
+apify_storage
+storage

templates/js-crawlee-playwright-camoufox/README.md

@@ -0,0 +1,23 @@
+## PlaywrightCrawler + Camoufox template
+
+This template is a production-ready boilerplate for developing an [Actor](https://apify.com/actors) with `PlaywrightCrawler`. It has [Camoufox](https://github.com/daijro/camoufox) - a stealthy fork of Firefox - preinstalled. Note that Camoufox might consume more resources than the default Playwright-bundled Chromium or Firefox.
+
+Use this template to bootstrap your projects using the most up-to-date code.
+
+> We decided to split Apify SDK into two libraries, Crawlee and Apify SDK v3. Crawlee will retain all the crawling and scraping-related tools and will always strive to be the best [web scraping](https://apify.com/web-scraping) library for its community. At the same time, Apify SDK will continue to exist, but keep only the Apify-specific features related to building actors on the Apify platform. Read the upgrading guide to learn about the changes.
+>
+
+## Resources
+
+If you're looking for examples or want to learn more visit:
+
+- [Crawlee + Apify Platform guide](https://crawlee.dev/docs/guides/apify-platform)
+- [Documentation](https://crawlee.dev/api/playwright-crawler/class/PlaywrightCrawler) and [examples](https://crawlee.dev/docs/examples/playwright-crawler)
+- [Node.js tutorials](https://docs.apify.com/academy/node-js) in Academy
+- [Scraping single-page applications with Playwright](https://blog.apify.com/scraping-single-page-applications-with-playwright/)
+- [How to scale Puppeteer and Playwright](https://blog.apify.com/how-to-scale-puppeteer-and-playwright/)
+- [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-playwright-camoufox/package.json

@@ -0,0 +1,28 @@
+{
+    "name": "crawlee-playwright-javascript-camoufox",
+    "version": "0.0.1",
+    "type": "module",
+    "description": "This is an example of an Apify actor.",
+    "engines": {
+        "node": ">=20.0.0"
+    },
+    "dependencies": {
+        "apify": "^3.2.6",
+        "camoufox-js": "^0.1.3",
+        "crawlee": "^3.11.5",
+        "playwright": "*"
+    },
+    "devDependencies": {
+        "@apify/eslint-config": "^0.4.0",
+        "eslint": "^8.50.0"
+    },
+    "scripts": {
+        "start": "node src/main.js",
+        "lint": "eslint ./src --ext .js,.jsx",
+        "lint:fix": "eslint ./src --ext .js,.jsx --fix",
+        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1",
+        "postinstall": "npx camoufox-js fetch"
+    },
+    "author": "It's not you it's me",
+    "license": "ISC"
+}

templates/js-crawlee-playwright-camoufox/src/main.js

@@ -0,0 +1,41 @@
+/**
+ * This template is a production ready boilerplate for developing with `PlaywrightCrawler`.
+ * 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://docs.apify.com/sdk/js
+import { Actor } from 'apify';
+// For more information, see https://crawlee.dev
+import { PlaywrightCrawler } from 'crawlee';
+// 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';
+import { firefox } from 'playwright';
+import { launchOptions as camoufoxLaunchOptions } from 'camoufox-js';
+
+// Initialize the Apify SDK
+await Actor.init();
+
+const {
+    startUrls = ['https://crawlee.dev'],
+} = await Actor.getInput() ?? {};
+
+const proxyConfiguration = await Actor.createProxyConfiguration();
+
+const crawler = new PlaywrightCrawler({
+    proxyConfiguration,
+    requestHandler: router,
+    launchContext: {
+        launcher: firefox,
+        launchOptions: await camoufoxLaunchOptions({
+            headless: true,
+            // fonts: ['Times New Roman'], // <- custom Camoufox options
+        }),
+    }
+});
+
+await crawler.run(startUrls);
+
+// Exit successfully
+await Actor.exit();