Scrapes an Instagram profile to extract user info based on username

instaprofile.js

// author: github.com/tas33n

const fs = require('fs');

/**
 * Scrapes an Instagram profile to extract user info based on username
 * @param {string} username - The Instagram username to scrape
 * @returns {Promise<Object>} - The structured user data or null if failed
 */
async function scrapeInstagramProfile(username) {
    try {
        const profileUrl = `https://www.instagram.com/${username}/`;

        const cookieString = 'csrftoken=1ljzQha1_HNVy_LXT7qPOd; mid=acYSKgALAAF6WjXyT72IzpuQESsQ; ig_did=3DBBE74E-6E71-4194-AB4F-6CEA1A61E67D; ig_nrcb=1; datr=KBHGaei4RCO-Rl9aKjn4xepQ';
        const csrfTokenMatch = cookieString.match(/csrftoken=([^;]+)/);
        const csrfToken = csrfTokenMatch ? csrfTokenMatch[1] : '';


        const profileResponse = await fetch(profileUrl, {
            headers: {
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36',
                'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
                'sec-ch-ua': '"Chromium";v="146", "Not-A.Brand";v="24", "Google Chrome";v="146"',
                'sec-ch-ua-mobile': '?0',
                'sec-ch-ua-platform': '"Windows"',
                'dnt': '1',
                'upgrade-insecure-requests': '1',
                'sec-fetch-site': 'none',
                'sec-fetch-mode': 'navigate',
                'sec-fetch-user': '?1',
                'sec-fetch-dest': 'document',
                'accept-language': 'en-GB,en;q=0.9',
                'priority': 'u=0, i',
                'Cookie': cookieString
            }
        });

        if (!profileResponse.ok) {
            throw new Error(`Failed to fetch profile page. HTTP Status: ${profileResponse.status}`);
        }

        const html = await profileResponse.text();

        const userIdMatch = html.match(/"user_id":"(\d+)"/);

        if (!userIdMatch || !userIdMatch[1]) {
            throw new Error("Could not find user_id in the profile page HTML. Instagram might have blocked the request or the DOM structure changed.");
        }

        const userId = userIdMatch[1];


        const graphqlUrl = 'https://www.instagram.com/graphql/query';

        const variables = {
            "enable_integrity_filters": true,
            "id": userId,
            "render_surface": "PROFILE",
            "__relay_internal__pv__PolarisCannesGuardianExperienceEnabledrelayprovider": true,
            "__relay_internal__pv__PolarisCASB976ProfileEnabledrelayprovider": false,
            "__relay_internal__pv__PolarisWebSchoolsEnabledrelayprovider": false,
            "__relay_internal__pv__PolarisRepostsConsumptionEnabledrelayprovider": false
        };

        const bodyParams = new URLSearchParams();
        bodyParams.append('variables', JSON.stringify(variables));
        bodyParams.append('doc_id', '34272012165747896');


        const graphqlResponse = await fetch(graphqlUrl, {
            method: 'POST',
            headers: {
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36',
                'Accept': '*/*',
                'Content-Type': 'application/x-www-form-urlencoded',
                'x-ig-app-id': '936619743392459',
                'x-fb-friendly-name': 'PolarisProfilePageContentQuery',
                'x-csrftoken': csrfToken,
                'Cookie': cookieString,
                'sec-ch-ua': '"Chromium";v="146", "Not-A.Brand";v="24", "Google Chrome";v="146"',
                'sec-ch-ua-mobile': '?0',
                'sec-ch-ua-platform': '"Windows"',
                'origin': 'https://www.instagram.com',
                'referer': profileUrl,
                'accept-language': 'en-GB,en;q=0.9',
                'priority': 'u=1, i'
            },
            body: bodyParams.toString()
        });

        if (!graphqlResponse.ok) {
            throw new Error(`Failed to fetch GraphQL data. HTTP Status: ${graphqlResponse.status}`);
        }

        const json = await graphqlResponse.json();

        if (json.status !== 'ok' || !json.data || !json.data.user) {
            throw new Error(`Invalid GraphQL response structure or user not found. Status: ${json.status || 'unknown'}`);
        }

        const user = json.data.user;

        const structuredData = {
            username: user.username,
            userid: user.pk,
            thumbnail: user.profile_pic_url,
            hd_profile_pic: user.hd_profile_pic_url_info ? user.hd_profile_pic_url_info.url : null,
            biography: user.biography,
            full_name: user.full_name,
            is_verified: user.is_verified,
            follower_count: user.follower_count,

            following_count: user.following_count,
            media_count: user.media_count,
            is_private: user.is_private,
            is_business: user.is_business,
            external_url: user.external_url || null,
            category: user.category || null
        };



        return structuredData;

    } catch (error) {
        throw error;
    }
}

if (require.main === module) {
    const testUsername = '__mithilarahman__';
    scrapeInstagramProfile(testUsername)
        .then(data => console.log(JSON.stringify(data, null, 2)))
        .catch(err => console.error(err.message));
}

module.exports = { scrapeInstagramProfile };