Using browser console as a webscrapping tool

webscrap-text.js

var fetchText = async (url) => {
    return new Promise((resolve, reject) => {
        fetch(url)
            .then(response => {
                if(response.status == 200) return response.text();
                throw new Error(response.statusText)
            })
            .then(html => {
                let parser = new DOMParser();
                let doc = parser.parseFromString(html, 'text/html');
                let paras = doc.querySelectorAll(".article-content");
                console.log(`${url} => ${paras.length} paragraphs`);
                let text = [...paras].map(p =>p.textContent).join("\n")
                resolve({url: url, text: text})
            })
            .catch(err => reject({url: url, error: err.message}))
    })
}

var downloadTextFile = (filename, text) => {
    const element = document.createElement("a");
    const file = new Blob([text], {
      type: "text/plain",
    });
    element.href = URL.createObjectURL(file);
    element.download = filename;
    document.body.appendChild(element);
    element.click();
  };


var urls = [
		"https://archive.mv/en/articles/AdK5q",
		"https://archive.mv/en/articles/QMDK1",
		"https://archive.mv/en/articles/404-error",
		"https://archive.mv/en/articles/8OLk9"
	]


var fetchPromises = urls.map(fetchText);


Promise.allSettled(fetchPromises)
.then(results =>{
	let fetchedText = results.filter(result => result.status === "fulfilled").map(result => result.value.text).join("\n")
	let failed = results.filter(result => result.status == "rejected").map(result => `FAILED: ${result.reason.url}`)

	let allText = [fetchedText, failed].join("\n------------------\n")
	
	downloadTextFile("all_text.txt", allText)
})