Skip to main content
Loading...

More JavaScript Posts

//Allegedly never tested on the twitter website
function scrapeScreen(){
    let articles = Array.from(document.getElementsByTagName("article"));
    let results = [];
    for(let tweet of articles){
        const isAnAd = Array.from(tweet.querySelectorAll("span")).map((e)=>e.textContent).includes("Ad");
        if(isAnAd){
            //console.log(tweet, "is an ad. Skipping...");
            continue;
        }
        const userName = tweet.querySelector("[data-testid='User-Name'] > div:nth-child(2) > div > div")?.textContent;
        const tweetContent = tweet.querySelector("[data-testid='tweetText']")?.textContent;
        const timeStamp = tweet.querySelector("time")?.getAttribute("datetime");
        const tweetLink = tweet.querySelector("time")?.parentElement?.getAttribute("href");
        if((!userName) || (!tweetContent)) continue;
        results.push({
            username: userName,
            tweetText: tweetContent,
            timeStamp: timeStamp,
            tweetLink: tweetLink
        });
    }
    return results;
}
let scraped = scrapeScreen();
setInterval(()=>{
    scraped = scraped.concat(
        scrapeScreen().filter((tweet)=>{
            for(let scrapedTweet of scraped){
                if(scrapedTweet.username == tweet.username && scrapedTweet.tweetText == tweet.tweetText) return false;
            }
            return true;
        })
    );
}, 500); //Scrape everything on the screen twice a second

window.scrollIntervalId = setInterval(function(){
    window.scrollBy(0, 1000);
}, 500); //Scroll for me


//http://bgrins.github.io/devtools-snippets/#console-save
(function(console){

console.save = function(data, filename){

 if(!data) {
 console.error('Console.save: No data')
 return;
 }

 if(!filename) filename = 'console.json'

 if(typeof data === "object"){
 data = JSON.stringify(data, undefined, '\t')
 }

 var blob = new Blob([data], {type: 'text/json'}),
 e = document.createEvent('MouseEvents'),
 a = document.createElement('a')

 a.download = filename
 a.href = window.URL.createObjectURL(blob)
 a.dataset.downloadurl = ['text/json', a.download, a.href].join(':')
 e.initMouseEvent('click', true, false, window, 0, 0, 0, 0, 0, false, false, false, false, 0, null)
 a.dispatchEvent(e)
 }
})(console)

setTimeout(()=>{
    clearTimeout(window.scrollIntervalId);
    delete window.scrollIntervalId;

    console.save(scraped, "TwitterScrape" + Date.now() + ".json");
}, 60 * 1000 * 20); //Twenty minutes