/*
the twitter api is stupid. it is stupid and bad and expensive. hence, this. 

Literally just paste this in the JS console on the bookmarks tab and the script will automatically scroll to the bottom of your bookmarks and keep a track of them as it goes. 

When finished, it downloads a JSON file containing the raw text content of every bookmark. 

for now it stores just the text inside the tweet itself, but if you're reading this why don't you go ahead and try to also store other information (author, tweetLink, pictures, everything). come on. do it. please?
*/

// ITS DONE! ✅

let tweets = []; // Initialize an empty array to hold all tweet elements

const scrollInterval = 1000; 
const scrollStep = 5000; // Pixels to scroll on each step

let previousTweetCount = 0;
let unchangedCount = 0;

const scrollToEndIntervalID = setInterval(() => {
    window.scrollBy(0, scrollStep);
    const currentTweetCount = tweets.length;
    if (currentTweetCount === previousTweetCount) {
        unchangedCount++;
        if (unchangedCount >= 2) { // Stop if the count has not changed 5 times
            console.log('Scraping complete');
            console.log('Total tweets scraped: ', tweets.length);
            console.log('Downloading tweets as JSON...');
            clearInterval(scrollToEndIntervalID); // Stop scrolling
            observer.disconnect(); // Stop observing DOM changes
            downloadTweetsAsJson(tweets); // Download the tweets list as a JSON file
        }
    } else {
        unchangedCount = 0; // Reset counter if new tweets were added
    }
    previousTweetCount = currentTweetCount; // Update previous count for the next check
}, scrollInterval);

function updateTweets() {
    document.querySelectorAll('article[data-testid="tweet"]').forEach(tweetElement => {
        const authorName = tweetElement.querySelector('[data-testid="User-Name"]')?.innerText;
        const handle = tweetElement.querySelector('[role="link"]').href.split('/').pop();
        const tweetText = tweetElement.querySelector('[data-testid="tweetText"]')?.innerText;
        const time = tweetElement.querySelector('time').getAttribute('datetime');
        const postUrl = tweetElement.querySelector('.css-175oi2r.r-18u37iz.r-1q142lx a')?.href;

        // Filter and extract interaction data in an enhanced way
        const interactionInfo = [...tweetElement.querySelectorAll('[aria-label]')]
            .map(element => element.getAttribute('aria-label'))
            .find(label => label && /replies|reposts|likes|bookmarks|views/.test(label));

        const {replies, reposts, likes, bookmarks, views} = interactionInfo ? extractInteractionDataFromString(interactionInfo) : {
            replies: 0,
            reposts: 0,
            likes: 0,
            bookmarks: 0,
            views: 0
        };

        const isTweetNew = !tweets.some(tweet => tweet.postUrl === postUrl);
        if (isTweetNew) {
            tweets.push({
                authorName,
                handle,
                tweetText,
                time,
                postUrl,
                interaction: {replies, reposts, likes, bookmarks, views}
            });
            console.log("Tweets capturados: ", tweets.length);
        }
    });
}

function extractInteractionDataFromString(infoString) {
    let replies = 0, reposts = 0, likes = 0, bookmarks = 0, views = 0;

    // Helper function to extract numbers based on a keyword
    function extractNumberForKeyword(text, keyword) {
        const regex = new RegExp(`(\\d+)\\s${keyword}`, "i");
        const match = text.match(regex);
        return match ? parseInt(match[1], 10) : 0;
    }

    if (infoString) {
        // Individually extract each interaction type using the helper function
        replies = extractNumberForKeyword(infoString, "replies");
        reposts = extractNumberForKeyword(infoString, "reposts");
        likes = extractNumberForKeyword(infoString, "likes");
        bookmarks = extractNumberForKeyword(infoString, "bookmarks");
        views = extractNumberForKeyword(infoString, "views");
    }

    return { replies, reposts, likes, bookmarks, views };
}


// Initially populate the tweets array
updateTweets();

// Create a MutationObserver to observe changes in the DOM
const observer = new MutationObserver(mutations => {
    mutations.forEach(mutation => {
        if (mutation.addedNodes.length) {
            updateTweets(); // Call updateTweets whenever new nodes are added to the DOM
        }
    });
});

// Start observing the document body for child list changes
observer.observe(document.body, { childList: true, subtree: true });

function downloadTweetsAsJson(tweetsArray) {
    const jsonData = JSON.stringify(tweetsArray); // Convert the array to JSON
    const blob = new Blob([jsonData], { type: 'application/json' });
    const url = URL.createObjectURL(blob);
    const link = document.createElement('a');
    link.href = url;
    link.download = 'tweets.json'; // Specify the file name
    document.body.appendChild(link); // Append the link to the document
    link.click(); // Programmatically click the link to trigger the download
    document.body.removeChild(link); // Clean up and remove the link
}