framalibre-scraping/chatons.js
2022-07-11 12:24:41 +02:00

128 lines
3.6 KiB
JavaScript

// récupérer des infos sur tous les chatons de chatons.org
// https://www.chatons.org/chatons/all
const url = 'https://www.chatons.org/chatons/all';
const axios = require('axios');
const cheerio = require('cheerio');
const pretty = require('pretty');
const fs = require('fs');
const pageLinkList = [];
const pagesChatons = [];
const chatonsCatalog = {
linkList: [],
pages : [],
};
// récupérer les liens de chaque chaton, exemple
// https://www.chatons.org/chatons/bastet-parinux
//
//
// infos dans la div:
// .chatons-public-column
// .chatons-public-subtitle nom
// Async function which scrapes the data
async function scrapeDataPages() {
try {
// Fetch HTML of the page we want to scrape
const { data } = await axios.get(url);
// Load HTML we fetched in the previous line
const $ = cheerio.load(data);
const listItems = $('.view-content a ');
listItems.each((index, element) => {
// console.log('element', element)
if (element.attribs && element.attribs['hreflang']) {
let url = 'https://www.chatons.org' + element.attribs['href'];
// console.log('url', url);
// console.log('element.getAttribute(\'href\')', url);
pageLinkList.push(url);
}
});
chatonsCatalog.linkList = pageLinkList;
console.log('pageLinkList.length', pageLinkList.length);
let indexPage = 0;
pageLinkList.forEach((urlPage) => {
if (indexPage < 2) {
let shouldWeSave = indexPage === pageLinkList.length - 1
scrapeDataCatalogcontent(urlPage, shouldWeSave);
}
// console.log('indexPage', indexPage, pageLinkList.length)
indexPage++;
});
} catch (e) {
console.error('e', e);
}
}
function persistCatalog() {
chatonsCatalog.pages = pagesChatons;
// console.log('pagesChatons', pagesChatons)
fs.writeFile('output/chatons_links.json', JSON.stringify(chatonsCatalog, null, 2), (err) => {
if (err) {
console.error(err);
return;
}
console.log('Successfully written data to file chatons_links.json');
});
}
async function scrapeDataCatalogcontent(url_page, shouldWeSave) {
try {
// Fetch HTML of the page we want to scrape
const { data } = await axios.get(url_page);
console.log('fetching url_page', url_page);
// Load HTML we fetched in the previous line
const $ = cheerio.load(data);
// logiciels du chatons
let softwares =[]
$('.view-kitten-software ul li a').each((idx, el) => {
// console.log('idx', idx)
// console.log('el', el)
softwares.push({
name: el.valueOf(),
link: el.attribs['href']
})
})
// console.log('org', $('.field--name-field-structure-organization')?.text());
pagesChatons.push({
name: $('h2.chatons-public-subtitle').eq(0).text().trim(),
url : $('.field--name-field-website-url .field__item')?.text().trim(),
rss : $('.field--name-field-rss-feed .field__item')?.text().trim(),
organization : $('.field--name-field-structure-organization .field__item')?.text(),
structure : $('.field--name-field-structure-type .field__item')?.text(),
geo_area : $('.field--name-field-geo-area .field__item')?.text(),
creation : $('.field--name-field-structure-creation .field__item')?.text(),
since : $('.field--name-field-member-since .field__item')?.text(),
zip_code : $('.field--name-field-zip-code .field__item')?.text(),
city : $('.field--name-field-city .field__item')?.text(),
softwares,
});
if(shouldWeSave){
setTimeout(persistCatalog,2000)
}
} catch (e) {
console.error('e', e);
}
}
// rundown all the pages
scrapeDataPages();