# Specify the base Docker image. You can read more about
# the available images at https://docs.apify.com/sdk/js/docs/guides/docker-images
# You can also use any other image from Docker Hub.
FROM apify/actor-node:20

# Copy just package.json and package-lock.json
# to speed up the build using Docker layer cache.
COPY 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

# 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 . ./


# Run the image.
CMD npm start --silent

.actor/actor.json

{
    "actorSpecification": 1,
    "name": "my-actor-2",
    "title": "Project Cheerio Crawler Javascript",
    "description": "Crawlee and Cheerio project in javascript.",
    "version": "0.0",
    "meta": {
        "templateId": "js-crawlee-cheerio"
    },
    "input": "./input_schema.json",
    "dockerfile": "./Dockerfile"
}

.actor/input_schema.json

{
    "title": "CheerioCrawler 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
        }
    }
}

src/main.js

1// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/)
2import { Actor } from 'apify';
3// Crawlee - web scraping and browser automation library (Read more at https://crawlee.dev)
4import { CheerioCrawler, Dataset } from 'crawlee';
5// this is ESM project, and as such, it requires you to specify extensions in your relative imports
6// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
7// import { router } from './routes.js';
8
9// The init() call configures the Actor for its environment. It's recommended to start every Actor with an init()
10await Actor.init();
11
12// Structure of input is defined in input_schema.json
13const {
14    startUrls = ['https://crawlee.dev'],
15    maxRequestsPerCrawl = 100,
16} = await Actor.getInput() ?? {};
17
18const proxyConfiguration = await Actor.createProxyConfiguration();
19
20const crawler = new CheerioCrawler({
21    proxyConfiguration,
22    maxRequestsPerCrawl,
23    async requestHandler({ enqueueLinks, request, $, log }) {
24        log.info('enqueueing new URLs');
25        await enqueueLinks();
26
27        // Extract title from the page.
28        const title = $('title').text();
29        log.info(`${title}`, { url: request.loadedUrl });
30
31        // Save url and title to Dataset - a table-like storage.
32        await Dataset.pushData({ url: request.loadedUrl, title });
33    },
34});
35
36await crawler.run(startUrls);
37
38// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit()
39await Actor.exit();

.dockerignore

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git

.editorconfig

root = true

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

.eslintrc

{
    "extends": "@apify",
    "root": true
}

.gitignore

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

.DS_Store
.idea
dist
node_modules
apify_storage
storage

package.json

{
    "name": "crawlee-cheerio-javascript",
    "version": "0.0.1",
    "type": "module",
    "description": "This is a boilerplate of an Apify actor.",
    "engines": {
        "node": ">=18.0.0"
    },
    "dependencies": {
        "apify": "^3.1.10",
        "crawlee": "^3.5.4"
    },
    "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"
    },
    "author": "It's not you it's me",
    "license": "ISC"
}