GC7 01 SimpleRequest

# configurations
.idea
.vscode

# 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

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

.DS_Store
.idea
dist
node_modules
apify_storage
storage

# Added by Apify CLI
.venv

{
    "name": "Simple crawlee",
    "version": "0.0.1",
    "type": "module",
    "description": "This is an example to learn Apify actor.",
    "dependencies": {
        "crawlee": "^3.10.0"
    },
    "scripts": {
        "start": "node src/main.mjs",
        "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1"
    },
    "author": "GC7",
    "license": "ISC"
}

{
	"actorSpecification": 1,
	"name": "GC7-01-SimpleRequest",
	"title": "Project Crawler JavaScript",
	"description": "Crawlee project in JavaScript.",
	"version": "0.1",
	"meta": {
		"templateId": "js-crawlee-puppeteer-chrome"
	},
	"input": "./input_schema.json",
	"dockerfile": "./Dockerfile"
}

# 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-puppeteer-chrome:18
FROM apify/actor-node-playwright: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

# 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

{
    "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"
                }
            ]
        }
    }
}

1## Hello, coder!
2
3Thank you for using this actor GC7 01 (SimpleRequest)
4
5I will let you know the output of the next one…
6
7Good use, in the meantime.
8
9See you soon,
10
11---
12
13## Bonjour, codeur!
14
15Merci d'utiliser cet actor GC7 01 (SimpleRequest)
16
17À la sortie du suivant, je vous ferai signe...
18
19Bon usage, en attendant.
20
21@++,
22
23---
24
25GC7

{
    "cSpell.words": ["apify", "crawlee"]
}

1import { RequestQueue, CheerioCrawler, log } from 'crawlee';
2
3// Uncomment the line above to see INFO logs
4// Décommentez la ligne ci-dessous pour voir les journaux INFO
5log.setLevel(log.LEVELS.WARNING);
6
7// 0 for textual result
8// 0 pour un résultat textuel
9const tableResult = 1;
10
11
12// Create queue and add your URLs to it
13// Créez une file d'attente et ajoutez vos URLs à celle-ci
14const requestQueue = await RequestQueue.open();
15const urls = ['https://crawlee.dev', 'https://google.com', 'https://c57.fr'];
16
17for (const url of urls) {
18    await requestQueue.addRequest({ url });
19}
20
21// Create the crawler and add the queue with our URL and a request handler to process the page.
22// Créez le crawler et ajoutez la file d'attente avec notre URL et un gestionnaire de requêtes pour traiter la page.
23let websites = [];
24const crawler = new CheerioCrawler({
25    requestQueue,
26    // The `$` argument is the Cheerio object which contains parsed HTML of the website.
27    // L'argument `$` est l'objet Cheerio qui contient le HTML analysé du site Web.
28    async requestHandler({ $, request }) {
29        // Extract <title> text with Cheerio. See Cheerio documentation for API docs.
30        // Extrait le texte <title> avec Cheerio. Voir la documentation de Cheerio pour les docs de l'API.
31        const title = $('title').text();
32        if (!tableResult) {
33            log.info('Result:');
34            console.log(`The title of "${request.url}" is: ${title}.`);
35        }
36        websites.push({ url: request.url, title });
37    },
38});
39// Start the crawler and wait for it to finish
40// Démarre le crawler et attendez qu'il termine
41await crawler.run(['https://apify.com']);
42
43// Show result as table, sorting by URL, without 'https://'
44// Affiche le résultat sous forme de tableau, trié par URL, sans le 'https://'
45websites = websites.map(website => ({ ...website, url: website.url.slice(8) })).sort((a, b) => a.url.localeCompare(b.url));
46if (tableResult) console.table(websites);