@slash-tmp/rgaa-scraper/build/esm/scrape.js

Scrapes RGAA's website and fetch topics, criteria and tests into a JSON format.

var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
    return new (P || (P = Promise))(function (resolve, reject) {
        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
        step((generator = generator.apply(thisArg, _arguments || [])).next());
    });
};
import Crawler from 'crawler';
import RgaaResultWrapper from './RgaaResultWrapper';
import { parseCriteriaArticle, parseTestLi, parseTopicA } from './parser';
const RGAA_URL = 'https://www.numerique.gouv.fr/publications/rgaa-accessibilite/methode-rgaa/criteres/';
function queueAsPromise(uri, crawler) {
    return new Promise((resolve, reject) => {
        crawler.direct({
            uri,
            callback(error, response) {
                if (error) {
                    reject(error);
                }
                resolve(response);
            },
        });
    });
}
function parseRgaaPage({ $ }) {
    const criteria = $('#criteres article')
        .toArray()
        .map(el => parseCriteriaArticle($(el)));
    const tests = $('#criteres li[id*="test"]')
        .toArray()
        .map(el => parseTestLi($(el)));
    const topics = $('ol#topics-list li a')
        .toArray()
        .map(el => parseTopicA($(el)));
    return {
        criteria,
        tests,
        topics,
    };
}
/**
 * Scrapes the RGAA website and returns a promise to an object representing
 * topics, criteria and tests.
 */
export default function scrapeRgaa() {
    return __awaiter(this, void 0, void 0, function* () {
        const crawler = new Crawler({});
        // fetch RGAA page
        const res = yield queueAsPromise(RGAA_URL, crawler);
        // parse the page for criteria and tests
        const data = parseRgaaPage(res);
        return new RgaaResultWrapper(data);
    });
}
//# sourceMappingURL=scrape.js.map