.actor

# 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:16

# 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/Dockerfile

Crawlee and Cheerio project in javascript.

project-cheerio-crawler-javascript

Project Cheerio Crawler Javascript

.actor/actor.json

Start URLs

CheerioCrawler Template

.actor/input_schema.json

/**
 * This template is a production ready boilerplate for developing with `CheerioCrawler`.
 * 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 { CheerioCrawler } from 'crawlee';
import { router } from './routes.js';

// Initialize the Apify SDK
await Actor.init();

const startUrls = ['https://api.apify.com/v2/acts/flamboyant_marimba~my-actor/runs?token=apify_api_r0Xcytmdv3sTxxWfOJMaF9p6c6YVGY0OLBgv'];

const proxyConfiguration = await Actor.createProxyConfiguration();

const crawler = new CheerioCrawler({
    proxyConfiguration,
    requestHandler: router,
});

await crawler.run(startUrls);

// Exit successfully
await Actor.exit();


src/main.js

import { Dataset, createCheerioRouter } from 'crawlee';

export const router = createCheerioRouter();

router.addDefaultHandler(async ({ enqueueLinks, log }) => {
    log.info(`enqueueing new URLs`);
    await enqueueLinks({
        globs: ['https://apify.com/*'],
        label: 'detail',
    });
});

router.addHandler('detail', async ({ request, $, log }) => {
    const title = $('title').text();
    log.info(`${title}`, { url: request.loadedUrl });

    await Dataset.pushData({
        url: request.loadedUrl,
        title,
    });
});


src/routes.js

# configurations
.idea

# crawlee and apify storage folders
apify_storage
crawlee_storage
storage

# installed files
node_modules

# git folder
.git


.dockerignore

root = true

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


.editorconfig

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


.eslintrc

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

.DS_Store
.idea
dist
node_modules
apify_storage
storage


My Actor

Crawlee & Cheerio template

Getting Started

Install Apify CLI

Using Homebrew

Using NPM

Create a new Actor using this template

Run the Actor locally

Deploy on Apify

Log in to Apify

Deploy your Actor

Documentation reference

Where next?