Skip to content

Instantly share code, notes, and snippets.

@udaylunawat

udaylunawat/instagram_posts_saver.MD

Last active April 1, 2025 22:19
Show Gist options
  • Save udaylunawat/54e67ed556c1286fcc7f54d3294d9ce7 to your computer and use it in GitHub Desktop.
Save udaylunawat/54e67ed556c1286fcc7f54d3294d9ce7 to your computer and use it in GitHub Desktop.
Download ZIP
Save instagram posts as csv using chrome developer tools
Raw
instagram_posts_saver.MD 
(async function executeInstagramPostCollection(maxPosts = 10) {
    console.log(`Starting Instagram post collection (limit: ${maxPosts} posts)...`);

    // Verify we're on Instagram
    if (!window.location.hostname.includes('instagram.com')) {
        console.error("This script should be run on Instagram.com");
        return;
    }
    
    // First wait for the page to fully load
    console.log("Waiting for page to fully load...");
    await new Promise(r => setTimeout(r, 3000));

    // Scroll down and collect unique URLs with poster names until we have enough
    const urlsWithPosters = new Map();
    await scrollAndCollectUrls(urlsWithPosters, maxPosts);

    // Verify we collected data
    if (urlsWithPosters.size === 0) {
        console.error("Failed to collect any posts. Here's some debug info:");
        console.log(`Total <a> tags on page: ${document.querySelectorAll('a').length}`);
        console.log(`Instagram post links found: ${document.querySelectorAll('a[href*="/p/"]').length}`);
        console.log(`Instagram reel links found: ${document.querySelectorAll('a[href*="/reel/"]').length}`);
        console.log("Try running the script again or checking the page structure.");
        return;
    }

    // Log what we collected for debugging
    console.log("Collected posts:");
    urlsWithPosters.forEach((posterName, url) => {
        console.log(`- ${url} by ${posterName}`);
    });

    // Save the collected URLs as a CSV file
    saveUrlsAsCsv(urlsWithPosters);

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

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

    let scrolling = true;
    let lastPostCount = 0;
    let noNewPostsCounter = 0;
    const maxNoNewPosts = 5; // Stop if no new posts are found after 5 scrolls

    while (scrolling) {
        // Try to collect posts
        const beforeCount = urlsWithPosters.size;
        collectUrls(urlsWithPosters, maxPosts);
        const afterCount = urlsWithPosters.size;
        
        // Log progress
        if (afterCount > beforeCount) {
            console.log(`Collected ${afterCount}/${maxPosts} posts...`);
            lastPostCount = afterCount;
            noNewPostsCounter = 0;
        } else {
            noNewPostsCounter++;
            console.log(`No new posts found (attempt ${noNewPostsCounter}/${maxNoNewPosts})`);
        }

        // Stop if we've collected enough posts
        if (urlsWithPosters.size >= maxPosts) {
            console.log(`Reached target of ${maxPosts} posts. Stopping collection.`);
            break;
        }

        // Stop if we haven't found new posts after several attempts
        if (noNewPostsCounter >= maxNoNewPosts) {
            console.log(`No new posts found after ${maxNoNewPosts} scroll attempts. Stopping collection.`);
            break;
        }

        // Scroll down
        window.scrollBy(0, window.innerHeight);
        await new Promise(r => setTimeout(r, 1500));

        // Check if new content has been loaded
        if (document.body.scrollHeight <= window.innerHeight + window.scrollY) {
            console.log("Reached the end of the page.");
            scrolling = false;
        }
    }

    console.log(`Scrolling complete. Total Instagram posts collected: ${urlsWithPosters.size}`);
}

// Function to collect Instagram post URLs and poster names
function collectUrls(urlsWithPosters, maxPosts) {
    if (urlsWithPosters.size >= maxPosts) return;
    
    // Find all post and reel links
    const postLinks = Array.from(document.querySelectorAll('a[href*="/p/"], a[href*="/reel/"]'));
    
    for (const link of postLinks) {
        if (urlsWithPosters.size >= maxPosts) break;
        
        const postUrl = link.href;
        // Skip if we already have this URL
        if (!postUrl || urlsWithPosters.has(postUrl)) continue;
        
        // Extract username from the href attribute
        let username = extractUsernameFromHref(link.href);
        
        // If we couldn't get the username from the href, try to find it in the parent elements
        if (!username) {
            const parent = findParentContainer(link);
            if (parent) {
                username = findUsernameInContainer(parent);
            }
        }
        
        // Fallback if all methods fail
        if (!username) {
            username = "unknown_user";
        }
        
        // Add to our collection
        urlsWithPosters.set(postUrl, username);
        console.log(`Added post: ${postUrl} by ${username}`);
    }
}

// Function to extract username from the Instagram post/reel URL
function extractUsernameFromHref(href) {
    try {
        // Instagram URLs are typically structured as:
        // https://www.instagram.com/USERNAME/p/POST_ID/
        // https://www.instagram.com/USERNAME/reel/REEL_ID/
        const url = new URL(href);
        const pathParts = url.pathname.split('/').filter(Boolean);
        
        // Check if this is a post or reel URL with the expected structure
        if (pathParts.length >= 3 && (pathParts[1] === 'p' || pathParts[1] === 'reel')) {
            return pathParts[0]; // The first path segment is the username
        }
        
        return null;
    } catch (e) {
        console.error("Error extracting username from URL:", e);
        return null;
    }
}

// Helper function to find username in a container
function findUsernameInContainer(container) {
    if (!container) return null;
    
    // Look for links that might be user profiles
    const profileLinks = container.querySelectorAll('a:not([href*="/p/"]):not([href*="/reel/"])');
    for (const link of profileLinks) {
        if (!link.href || !link.href.includes('instagram.com/')) continue;
        
        try {
            const url = new URL(link.href);
            const pathParts = url.pathname.split('/').filter(Boolean);
            
            // Skip links to Instagram features
            if (pathParts.length > 0 && 
                !['explore', 'reels', 'stories', 'direct', 'accounts'].includes(pathParts[0])) {
                return pathParts[0]; // Return the username
            }
        } catch (e) {
            console.error("Error parsing profile URL:", e);
        }
    }
    
    return null;
}

// Helper function to find a reasonable parent container
function findParentContainer(element) {
    if (!element) return null;
    
    // Try to find a parent that's likely to contain the username
    let current = element;
    for (let i = 0; i < 5; i++) { // Look up to 5 levels up
        if (!current.parentElement) break;
        current = current.parentElement;
        
        // If we found an article or a div that seems like a post container, return it
        if (current.tagName === 'ARTICLE' || 
            (current.tagName === 'DIV' && (
                current.hasAttribute('role') || 
                current.childElementCount > 3 || 
                current.classList.length > 0)
            )) {
            return current;
        }
    }
    return null;
}

// Function to save collected URLs and poster names as a CSV file
function saveUrlsAsCsv(urlsWithPosters) {
    if (urlsWithPosters.size === 0) {
        console.error("No posts were collected. Unable to create CSV.");
        return;
    }
    
    // Create CSV content with proper escaping for CSV format
    let csvRows = ["URL,Poster"];
    
    urlsWithPosters.forEach((posterName, url) => {
        // Escape quotes in the poster name and wrap in quotes if it contains commas
        let escapedPosterName = posterName.replace(/"/g, '""');
        if (escapedPosterName.includes(',')) {
            escapedPosterName = `"${escapedPosterName}"`;
        }
        
        csvRows.push(`${url},${escapedPosterName}`);
    });
    
    let csvContent = csvRows.join('\n');
    
    // Create a Blob with the CSV data
    const blob = new Blob([csvContent], { type: 'text/csv;charset=utf-8;' });
    const url = URL.createObjectURL(blob);
    
    // 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 link = document.createElement("a");
    link.setAttribute("href", url);
    link.setAttribute("download", fileName);
    document.body.appendChild(link); // Required for Firefox
    link.click();
    
    // Clean up
    setTimeout(() => {
        document.body.removeChild(link);
        window.URL.revokeObjectURL(url);
    }, 100);

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

Instagram Post Collector - Usage Instructions

This script allows you to collect Instagram post URLs and creator usernames from any Instagram page.

Features

  • Collects both posts and reels with their creator usernames
  • Customizable collection limit (default: 10 posts)
  • Automatically scrolls through the page to find posts
  • Exports data to a CSV file with proper formatting
  • Smart scrolling that stops when collection target is reached
  • User-friendly console feedback throughout the process

How To Use

  1. Navigate to Instagram

    • Open any Instagram page where you want to collect posts (profile, explore, home feed, etc.)
    • Make sure you're logged in if the content requires authentication

  2. Open Developer Tools

    • Press F12 or right-click and select "Inspect"
    • Navigate to the "Console" tab

  3. Run the Script

    • Copy and paste the entire script into the console
    • Press Enter to execute

  4. Customize Collection (Optional)

    • By default, the script collects 10 posts
    • To change this, modify the maxPosts parameter in the first line: 
      (async function executeInstagramPostCollection(maxPosts = 50) {

  5. Monitor Progress

    • The script provides real-time feedback in the console as it collects posts
    • You'll see messages like "Collected 5/10 posts..." as it progresses

  6. Get Results

    • When collection is complete, the CSV file will automatically download
    • The filename is based on the current page title (e.g., username_instagram_post_urls.csv)
    • The CSV contains two columns: URL and Poster (username)

Troubleshooting

If the script doesn't find any posts, it will provide debugging information:

  • Total number of <a> tags on the page
  • Number of Instagram post and reel links found
  • Suggestions for resolving the issue

CSV File Format

The exported CSV file contains:

  • A header row with "URL,Poster"
  • One row per post with the post/reel URL and creator username
  • Proper CSV escaping for values containing commas or quotes

Example Output

URL,Poster
https://www.instagram.com/username/p/AbCdEfGhIjK/,username
https://www.instagram.com/another_user/reel/AbCdEfGhIjK/,another_user

The script automatically handles the download process - no manual steps required!

Raw
save_posts_to_csv.jsx
(async function executeInstagramPostCollection(maxPosts = 10) {
console.log(`Starting Instagram post collection (limit: ${maxPosts} posts)...`);
// Verify we're on Instagram
if (!window.location.hostname.includes('instagram.com')) {
console.error("This script should be run on Instagram.com");
return;
}
// First wait for the page to fully load
console.log("Waiting for page to fully load...");
await new Promise(r => setTimeout(r, 3000));
// Scroll down and collect unique URLs with poster names until we have enough
const urlsWithPosters = new Map();
await scrollAndCollectUrls(urlsWithPosters, maxPosts);
// Verify we collected data
if (urlsWithPosters.size === 0) {
console.error("Failed to collect any posts. Here's some debug info:");
console.log(`Total <a> tags on page: ${document.querySelectorAll('a').length}`);
console.log(`Instagram post links found: ${document.querySelectorAll('a[href*="/p/"]').length}`);
console.log(`Instagram reel links found: ${document.querySelectorAll('a[href*="/reel/"]').length}`);
console.log("Try running the script again or checking the page structure.");
return;
}
// Log what we collected for debugging
console.log("Collected posts:");
urlsWithPosters.forEach((posterName, url) => {
console.log(`- ${url} by ${posterName}`);
});
// Save the collected URLs as a CSV file
saveUrlsAsCsv(urlsWithPosters);
console.log("Instagram post collection complete.");
})();
// Function to scroll down and collect Instagram post URLs
async function scrollAndCollectUrls(urlsWithPosters, maxPosts) {
console.log("Starting to scroll down and collect posts...");
let scrolling = true;
let lastPostCount = 0;
let noNewPostsCounter = 0;
const maxNoNewPosts = 5; // Stop if no new posts are found after 5 scrolls
while (scrolling) {
// Try to collect posts
const beforeCount = urlsWithPosters.size;
collectUrls(urlsWithPosters, maxPosts);
const afterCount = urlsWithPosters.size;
// Log progress
if (afterCount > beforeCount) {
console.log(`Collected ${afterCount}/${maxPosts} posts...`);
lastPostCount = afterCount;
noNewPostsCounter = 0;
} else {
noNewPostsCounter++;
console.log(`No new posts found (attempt ${noNewPostsCounter}/${maxNoNewPosts})`);
}
// Stop if we've collected enough posts
if (urlsWithPosters.size >= maxPosts) {
console.log(`Reached target of ${maxPosts} posts. Stopping collection.`);
break;
}
// Stop if we haven't found new posts after several attempts
if (noNewPostsCounter >= maxNoNewPosts) {
console.log(`No new posts found after ${maxNoNewPosts} scroll attempts. Stopping collection.`);
break;
}
// Scroll down
window.scrollBy(0, window.innerHeight);
await new Promise(r => setTimeout(r, 1500));
// Check if new content has been loaded
if (document.body.scrollHeight <= window.innerHeight + window.scrollY) {
console.log("Reached the end of the page.");
scrolling = false;
}
}
console.log(`Scrolling complete. Total Instagram posts collected: ${urlsWithPosters.size}`);
}
// Function to collect Instagram post URLs and poster names
function collectUrls(urlsWithPosters, maxPosts) {
if (urlsWithPosters.size >= maxPosts) return;
// Find all post and reel links
const postLinks = Array.from(document.querySelectorAll('a[href*="/p/"], a[href*="/reel/"]'));
for (const link of postLinks) {
if (urlsWithPosters.size >= maxPosts) break;
const postUrl = link.href;
// Skip if we already have this URL
if (!postUrl || urlsWithPosters.has(postUrl)) continue;
// Extract username from the href attribute
let username = extractUsernameFromHref(link.href);
// If we couldn't get the username from the href, try to find it in the parent elements
if (!username) {
const parent = findParentContainer(link);
if (parent) {
username = findUsernameInContainer(parent);
}
}
// Fallback if all methods fail
if (!username) {
username = "unknown_user";
}
// Add to our collection
urlsWithPosters.set(postUrl, username);
console.log(`Added post: ${postUrl} by ${username}`);
}
}
// Function to extract username from the Instagram post/reel URL
function extractUsernameFromHref(href) {
try {
// Instagram URLs are typically structured as:
// https://www.instagram.com/USERNAME/p/POST_ID/
// https://www.instagram.com/USERNAME/reel/REEL_ID/
const url = new URL(href);
const pathParts = url.pathname.split('/').filter(Boolean);
// Check if this is a post or reel URL with the expected structure
if (pathParts.length >= 3 && (pathParts[1] === 'p' || pathParts[1] === 'reel')) {
return pathParts[0]; // The first path segment is the username
}
return null;
} catch (e) {
console.error("Error extracting username from URL:", e);
return null;
}
}
// Helper function to find username in a container
function findUsernameInContainer(container) {
if (!container) return null;
// Look for links that might be user profiles
const profileLinks = container.querySelectorAll('a:not([href*="/p/"]):not([href*="/reel/"])');
for (const link of profileLinks) {
if (!link.href || !link.href.includes('instagram.com/')) continue;
try {
const url = new URL(link.href);
const pathParts = url.pathname.split('/').filter(Boolean);
// Skip links to Instagram features
if (pathParts.length > 0 &&
!['explore', 'reels', 'stories', 'direct', 'accounts'].includes(pathParts[0])) {
return pathParts[0]; // Return the username
}
} catch (e) {
console.error("Error parsing profile URL:", e);
}
}
return null;
}
// Helper function to find a reasonable parent container
function findParentContainer(element) {
if (!element) return null;
// Try to find a parent that's likely to contain the username
let current = element;
for (let i = 0; i < 5; i++) { // Look up to 5 levels up
if (!current.parentElement) break;
current = current.parentElement;
// If we found an article or a div that seems like a post container, return it
if (current.tagName === 'ARTICLE' ||
(current.tagName === 'DIV' && (
current.hasAttribute('role') ||
current.childElementCount > 3 ||
current.classList.length > 0)
)) {
return current;
}
}
return null;
}
// Function to save collected URLs and poster names as a CSV file
function saveUrlsAsCsv(urlsWithPosters) {
if (urlsWithPosters.size === 0) {
console.error("No posts were collected. Unable to create CSV.");
return;
}
// Create CSV content with proper escaping for CSV format
let csvRows = ["URL,Poster"];
urlsWithPosters.forEach((posterName, url) => {
// Escape quotes in the poster name and wrap in quotes if it contains commas
let escapedPosterName = posterName.replace(/"/g, '""');
if (escapedPosterName.includes(',')) {
escapedPosterName = `"${escapedPosterName}"`;
}
csvRows.push(`${url},${escapedPosterName}`);
});
let csvContent = csvRows.join('\n');
// Create a Blob with the CSV data
const blob = new Blob([csvContent], { type: 'text/csv;charset=utf-8;' });
const url = URL.createObjectURL(blob);
// 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 = `${pageTitle}_instagram_post_urls.csv`;
// Create a link element and trigger the download
let link = document.createElement("a");
link.setAttribute("href", url);
link.setAttribute("download", fileName);
document.body.appendChild(link); // Required for Firefox
link.click();
// Clean up
setTimeout(() => {
document.body.removeChild(link);
window.URL.revokeObjectURL(url);
}, 100);
console.log(`CSV file "${fileName}" has been saved with ${urlsWithPosters.size} posts.`);
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment