My Actor avatar
My Actor

Deprecated

Pricing

Pay per usage

Go to Store
My Actor

My Actor

Deprecated

Developed by

sixtus leo

sixtus leo

Maintained by Community

Testing

0.0 (0)

Pricing

Pay per usage

1

Total users

2

Monthly users

1

Last modified

2 years ago

.actor/Dockerfile

# 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/actor.json

{
"actorSpecification": 1,
"name": "project-cheerio-crawler-javascript",
"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://apify.com"
}
]
}
}
}

src/main.js

1/**
2 * This template is a production ready boilerplate for developing with `CheerioCrawler`.
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 { CheerioCrawler } from 'crawlee';
11import { router } from './routes.js';
12
13// Initialize the Apify SDK
14await Actor.init();
15
16const startUrls = ['https://api.apify.com/v2/acts/flamboyant_marimba~my-actor/runs?token=apify_api_r0Xcytmdv3sTxxWfOJMaF9p6c6YVGY0OLBgv'];
17
18const proxyConfiguration = await Actor.createProxyConfiguration();
19
20const crawler = new CheerioCrawler({
21 proxyConfiguration,
22 requestHandler: router,
23});
24
25await crawler.run(startUrls);
26
27// Exit successfully
28await Actor.exit();

src/routes.js

1import { Dataset, createCheerioRouter } from 'crawlee';
2
3export const router = createCheerioRouter();
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, $, log }) => {
14 const title = $('title').text();
15 log.info(`${title}`, { url: request.loadedUrl });
16
17 await Dataset.pushData({
18 url: request.loadedUrl,
19 title,
20 });
21});

.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": ">=16.0.0"
},
"dependencies": {
"apify": "^3.0.0",
"crawlee": "^3.0.0"
},
"devDependencies": {
"@apify/eslint-config": "^0.3.1",
"eslint": "^8.36.0"
},
"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"
}