Arab chat 1

# 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 AS builder

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY --chown=myuser package*.json ./

# Install all dependencies. Don't audit to speed up the installation.
RUN npm install --include=dev --audit=false

# Next, copy the source files using the user set
# in the base image.
COPY --chown=myuser . ./

# Install all dependencies and build the project.
# Don't audit to speed up the installation.
RUN npm run build

# Create final image
FROM apify/actor-node-playwright-chrome:20

# 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 --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

# Copy built JS files from builder image
COPY --from=builder --chown=myuser /home/myuser/dist ./dist

# 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 run start:prod --silent

{
    "actorSpecification": 1,
    "name": "my-actor",
    "title": "Project Playwright Crawler Typescript",
    "description": "Crawlee and Playwright project in typescript.",
    "version": "0.0",
    "meta": {
        "templateId": "ts-crawlee-playwright-chrome"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

{
    "title": "PlaywrightCrawler Template",
    "type": "object",
    "schemaVersion": 1,
    "properties": {
        "startUrls": {
            "title": "Start URLs",
            "type": "array",
            "description": "URLs to start with.",
            "editor": "requestListSources",
            "prefill": [
                {
                    "url": "https://crawlee.dev"
                }
            ]
        },
        "maxRequestsPerCrawl": {
            "title": "Max Requests per Crawl",
            "type": "integer",
            "description": "Maximum number of requests that can be made by this crawler.",
            "default": 100
        }
    }
}

1/**
2 * This template is a production ready boilerplate for developing with `PlaywrightCrawler`.
3 * Use this to bootstrap your projects using the most up-to-date code.
4 * If you're looking for examples or want to learn more, see README.
5 */
6
7// For more information, see https://docs.apify.com/sdk/js
8import { Actor } from 'apify';
9// For more information, see https://crawlee.dev
10import { PlaywrightCrawler } from 'crawlee';
11// this is ESM project, and as such, it requires you to specify extensions in your relative imports
12// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
13// note that we need to use `.js` even when inside TS files
14import { router } from './routes.js';
15
16interface Input {
17    startUrls: string[];
18    maxRequestsPerCrawl: number;
19}
20
21// Initialize the Apify SDK
22await Actor.init();
23
24// Structure of input is defined in input_schema.json
25const {
26    startUrls = ['https://crawlee.dev'],
27    maxRequestsPerCrawl = 100,
28} = await Actor.getInput<Input>() ?? {} as Input;
29
30const proxyConfiguration = await Actor.createProxyConfiguration();
31
32const crawler = new PlaywrightCrawler({
33    proxyConfiguration,
34    maxRequestsPerCrawl,
35    requestHandler: router,
36});
37
38await crawler.run(startUrls);
39
40// Exit successfully
41await Actor.exit();

1import { Dataset, createPlaywrightRouter } from 'crawlee';
2
3export const router = createPlaywrightRouter();
4
5router.addDefaultHandler(async ({ enqueueLinks, log }) => {
6    log.info(`enqueueing new URLs`);
7    await enqueueLinks({
8        globs: ['https://apify.com/*'],
9        label: 'detail',
10    });
11});
12
13router.addHandler('detail', async ({ request, page, log }) => {
14    const title = await page.title();
15    log.info(`${title}`, { url: request.loadedUrl });
16
17    await Dataset.pushData({
18        url: request.loadedUrl,
19        title,
20    });
21});

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

root = true

[*]
indent_style = space
indent_size = 4
charset = utf-8
trim_trailing_whitespace = true
insert_final_newline = true
end_of_line = lf

{
    "root": true,
    "env": {
        "browser": true,
        "es2020": true,
        "node": true
    },
    "extends": [
        "@apify/eslint-config-ts"
    ],
    "parserOptions": {
        "project": "./tsconfig.json",
        "ecmaVersion": 2020
    },
    "ignorePatterns": [
        "node_modules",
        "dist",
        "**/*.d.ts"
    ]
}

# This file tells Git which files shouldn't be added to source control

.DS_Store
.idea
dist
node_modules
apify_storage
storage

{
    "name": "crawlee-playwright-typescript",
    "version": "0.0.1",
    "type": "module",
    "description": "This is an example of an Apify actor.",
    "engines": {
        "node": ">=18.0.0"
    },
    "dependencies": {
        "apify": "^3.1.10",
        "crawlee": "^3.5.4",
        "playwright": "*"
    },
    "devDependencies": {
        "@apify/eslint-config-ts": "^0.3.0",
        "@apify/tsconfig": "^0.1.0",
        "@typescript-eslint/eslint-plugin": "^6.7.2",
        "@typescript-eslint/parser": "^6.7.2",
        "eslint": "^8.50.0",
        "tsx": "^4.6.2",
        "typescript": "^5.3.3"
    },
    "scripts": {
        "start": "npm run start:dev",
        "start:prod": "node dist/main.js",
        "start:dev": "tsx src/main.ts",
        "build": "tsc",
        "lint": "eslint ./src --ext .ts",
        "lint:fix": "eslint ./src --ext .ts --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"
}

{
    "extends": "@apify/tsconfig",
    "compilerOptions": {
        "module": "NodeNext",
        "moduleResolution": "NodeNext",
        "target": "ES2022",
        "outDir": "dist",
        "noUnusedLocals": false,
        "skipLibCheck": true,
        "lib": ["DOM"]
    },
    "include": [
        "./src/**/*"
    ]
}