Save instagram posts as csv using chrome developer tools

instagram_posts_saver.MD

(async function executeInstagramPostCollection() {
    console.log("Starting Instagram post collection...");

    // Step 1: Scroll to the bottom of the page to load all content
    await scrollToBottomAndLoadContent();

    // Step 2: Scroll back to the top
    await scrollToTop();

    // Step 3: Scroll down and collect unique URLs
    const urls = new Set();
    await scrollAndCollectUrls(urls);

    // Step 4: Verify content loading and scroll if more content is being loaded
    await verifyAndContinueScrolling(urls);

    // Step 5: Save the collected URLs as a CSV file
    saveUrlsAsCsv(urls);

    console.log("Instagram post collection complete.");
})();

// Function to scroll to the bottom and ensure all content is loaded
async function scrollToBottomAndLoadContent() {
    console.log("Loading all content by scrolling to the bottom...");
    
    let lastHeight = document.body.scrollHeight;
    let retries = 0;
    const maxRetries = 10;

    while (retries < maxRetries) {
        window.scrollBy(0, window.innerHeight);
        await new Promise(r => setTimeout(r, 1000)); // Adjust this timeout as needed

        let newHeight = document.body.scrollHeight;

        if (newHeight === lastHeight) {
            retries++;
        } else {
            retries = 0; // Reset retries if new content was loaded
        }

        lastHeight = newHeight;
    }

    console.log("All content loaded.");
}

// Function to scroll to the top of the page
async function scrollToTop() {
    console.log("Scrolling to the top...");
    window.scrollTo(0, 0);
    await new Promise(r => setTimeout(r, 2000)); // Wait for the page to settle
}

// Function to scroll down and collect Instagram post URLs
async function scrollAndCollectUrls(urls) {
    console.log("Starting to scroll down, count posts, and collect URLs...");

    let scrolling = true;

    while (scrolling) {
        collectUrls(urls);

        // Scroll down
        window.scrollBy(0, window.innerHeight);
        await new Promise(r => setTimeout(r, 15)); // Short pause to allow page to render new content

        // Check if new content has been loaded
        if (document.body.scrollHeight <= window.innerHeight + window.scrollY) {
            scrolling = false;
        }
    }

    console.log(`Scrolling complete. Total unique Instagram posts found: ${urls.size}`);
}

// Function to collect Instagram post URLs
function collectUrls(urls) {
    document.querySelectorAll('a').forEach(link => {
        const href = link.href;
        if (href.startsWith("https://www.instagram.com/p/")) {
            urls.add(href);
        }
    });
}

// Function to verify content loading and continue scrolling if more content is being loaded
async function verifyAndContinueScrolling(urls) {
    console.log("Verifying content loading status...");

    let lastHeight = document.body.scrollHeight;

    for (let i = 0; i < 3; i++) {
        let previousSize = urls.size;

        // Perform a check for more content and collect URLs
        collectUrls(urls);

        // Scroll down to load more content if needed
        window.scrollBy(0, window.innerHeight);
        await new Promise(r => setTimeout(r, 1500)); // Wait 1000ms between verification checks

        let newHeight = document.body.scrollHeight;

        if (previousSize !== urls.size || newHeight > lastHeight) {
            console.log(`Verification ${i + 1}: New content loaded. Continuing to scroll...`);
            lastHeight = newHeight;
            i = 0; // Reset verification if new content is detected
        } else {
            console.log(`Verification ${i + 1}: No new content loaded.`);
        }
    }

    console.log(`Final verification complete. Total unique Instagram posts found: ${urls.size}`);
}

// Function to save collected URLs as a CSV file
function saveUrlsAsCsv(urls) {
    let urlArray = [...urls];
    let csvContent = "data:text/csv;charset=utf-8," + urlArray.map(e => e).join("\n");

    // Get the title of the page to use as the filename
    let pageTitle = document.title.replace(/[^a-z0-9]/gi, '_').toLowerCase(); // Sanitize title for filename
    let fileName = `${pageTitle}_instagram_post_urls.csv`;

    // Create a link element and trigger the download
    let encodedUri = encodeURI(csvContent);
    let link = document.createElement("a");
    link.setAttribute("href", encodedUri);
    link.setAttribute("download", fileName);
    document.body.appendChild(link); // Required for Firefox
    link.click();
    document.body.removeChild(link); // Clean up

    console.log(`CSV file "${fileName}" has been saved.`);
}

Key Changes:

1. Dynamic Filename from Page Title:
   • The script now retrieves the title of the page using document.title and uses it as the base for the CSV filename.
   • The title is sanitized by replacing any characters that are not alphanumeric with underscores (_) to ensure the filename is valid across different operating systems.
2. Filename Construction:
   • The filename is constructed by appending _instagram_post_urls.csv to the sanitized title of the page. For example, if the page title is "John's Instagram", the CSV file will be named johns_instagram_instagram_post_urls.csv.

Usage Instructions:

1. Open Developer Tools:
   • Open the Instagram page with posts.
   • Open Chrome Developer Tools (F12 or right-click and select "Inspect").
   • Go to the "Console" tab.
2. Run the Script:
   • Copy and paste the updated script into the console.
   • Press Enter to execute the script.
3. Download the CSV:
   • The script will automatically handle everything, from scrolling and collecting URLs to saving them in a CSV file with the page title as its name.

This approach provides a meaningful filename based on the page’s content, making it easier to identify and manage the downloaded CSV files.