Pricing
$17.99/month + usage
Pricing
$17.99/month + usage
Rating
5.0
(1)
Developer
Aijaz Alee
Actor stats
0
Bookmarked
8
Total users
2
Monthly active users
a month ago
Last modified
Categories
Share
{ "actorSpecification": 1, "name": "ig-profile-scraper", "title": "iG Profile Scraper", "description": "Analyze Instagram followers or following to find valuable profiles. Filter large accounts by engagement, contact info, and business category to discover influencers, leads, or ideal customers. Perfect for lead generation, market research, and influencer marketing.", "version": "1.0.0", "meta": { "templateId": "js-crawlee" }, "input": "./input_schema.json", "dockerfile": "./Dockerfile", "readme": "./README.md", "categories": ["SOCIAL_MEDIA"], "storages": { "dataset": { "actorSpecification": 1, "title": "Instagram Profiles", "views": { "overview": { "title": "Overview", "transformation": { "fields": [ "username", "fullName", "bio", "email", "phone", "website", "followers", "following", "posts", "businessCategory", "engagementRate", "accountType", "isVerified", "url", "scrapedAt" ] }, "display": { "component": "table", "properties": { "username": { "label": "Username", "format": "text" }, "fullName": { "label": "Full Name", "format": "text" }, "bio": { "label": "Bio", "format": "text" }, "email": { "label": "Email", "format": "text" }, "phone": { "label": "Phone", "format": "text" }, "website": { "label": "Website", "format": "link" }, "followers": { "label": "Followers", "format": "number" }, "following": { "label": "Following", "format": "number" }, "posts": { "label": "Posts", "format": "number" }, "businessCategory": { "label": "Business Category", "format": "text" }, "engagementRate": { "label": "Engagement Rate", "format": "text" }, "accountType": { "label": "Account Type", "format": "text" }, "isVerified": { "label": "Verified", "format": "boolean" }, "url": { "label": "Profile URL", "format": "link" }, "scrapedAt": { "label": "Scraped At", "format": "date" } } } } } } }}{ "title": "iG Profile Scraper Input", "type": "object", "schemaVersion": 1, "properties": { "mode": { "title": "1. Choose Operation Mode", "type": "string", "description": "Select how you want to scrape Instagram profiles", "enum": ["MODE1", "MODE2", "MODE3", "MODE4"], "enumTitles": [ "🎯 Mode 1: Analyze a Single Account's Followers/Following", "🎯 Mode 2: Batch Analyze Followers/Following", "🎯 Mode 3: Analyze a Specific List of Accounts", "🎯 Mode 4: Network Expansion" ], "default": "MODE1", "editor": "select" }, "targetUsername": { "title": "Target Account", "type": "string", "description": "Instagram handle to scrape (without @). Example: instagram", "editor": "textfield", "example": "instagram", "sectionCaption": "🎯 Mode 1: Analyze a Single Account's Followers/Following", "sectionDescription": "Scrapes followers or following from a single target account." }, "scrapeFollowers": { "title": "Scrape Followers", "type": "boolean", "description": "Extract followers of the target account", "default": true }, "scrapeFollowing": { "title": "Scrape Following", "type": "boolean", "description": "Extract following list of the target account", "default": false }, "maxProfilesMode1": { "title": "Max profiles to process (cost control)", "type": "integer", "description": "Maximum number of profiles to scrape", "minimum": 1, "maximum": 100000, "default": 100 }, "targetUsernames": { "title": "List of Target Profiles", "type": "array", "description": "Instagram handles for batch processing (one per line, without @)", "editor": "stringList", "example": ["openai", "claudeai", "instagram"], "sectionCaption": "🎯 Mode 2: Batch Analyze Followers/Following", "sectionDescription": "Scrapes followers/following from a list of multiple target accounts." }, "scrapeFollowersMode2": { "title": "Scrape Followers", "type": "boolean", "description": "Extract followers from each account", "default": true }, "scrapeFollowingMode2": { "title": "Scrape Following", "type": "boolean", "description": "Extract following from each account", "default": false }, "maxProfilesPerAccount": { "title": "Max profiles to process per account (cost control)", "type": "integer", "description": "Maximum profiles to extract per account", "minimum": 1, "maximum": 10000, "default": 100 }, "usernamesToAnalyze": { "title": "List of Profiles to Analyze", "type": "array", "description": "Specific Instagram handles to enrich with data (one per line, without @)", "editor": "stringList", "example": ["openai", "claudeai", "instagram"], "sectionCaption": "🎯 Mode 3: Analyze a Specific List of Accounts", "sectionDescription": "Enriches a provided list of profiles with data (does not scrape their followers)." }, "maxProfilesMode3": { "title": "Max profiles to process (cost control)", "type": "integer", "description": "Maximum number of profiles to analyze", "minimum": 1, "maximum": 100000, "default": 100 }, "seedUsernames": { "title": "Start Profiles", "type": "array", "description": "Seed profiles to start network expansion (one per line, without @)", "editor": "stringList", "example": ["influencer1", "influencer2"], "sectionCaption": "🎯 Mode 4: Network Expansion", "sectionDescription": "Discovers similar profiles using Instagram's own «Suggested for You» algorithm." }, "expansionDepth": { "title": "Search Depth", "type": "integer", "description": "How many levels deep to expand (1 recommended for cost efficiency)", "minimum": 1, "maximum": 3, "default": 1 }, "maxProfilesMode4": { "title": "Max profiles to process (cost control)", "type": "integer", "description": "Maximum number of profiles to discover", "minimum": 1, "maximum": 100000, "default": 200 }, "extractEmail": { "title": "Extract Email", "type": "boolean", "description": "Try to extract email addresses from bio and business contact info", "default": true, "sectionCaption": "⚙️ Data Extraction Options", "sectionDescription": "Select what data to collect and which enrichments to perform. These options apply to all modes." }, "extractPhone": { "title": "Extract Phone Number", "type": "boolean", "description": "Try to extract phone numbers from bio and business contact info", "default": true }, "extractWebsite": { "title": "Extract Website URL", "type": "boolean", "description": "Extract website/external links from profile", "default": true }, "extractBusinessCategory": { "title": "Extract Business Category", "type": "boolean", "description": "Extract business category/niche (if available)", "default": true }, "extractAddress": { "title": "Extract Physical Address", "type": "boolean", "description": "Extract business address from location info", "default": false }, "calculateEngagementRate": { "title": "Calculate Engagement Rate (ER)", "type": "boolean", "description": "Calculate engagement rate based on recent posts (may increase processing time)", "default": true }, "extractPostCaptions": { "title": "Extract Latest Post Captions", "type": "boolean", "description": "Get text content from recent posts", "default": false }, "deepContactSearch": { "title": "Deep Search for Contacts in Posts", "type": "boolean", "description": "Search for additional contact info in post captions and comments (slower)", "default": false }, "keywords": { "title": "Filter by Keywords", "type": "array", "description": "Only include profiles containing these keywords (leave empty to disable)", "editor": "stringList", "example": ["marketing", "entrepreneur", "coach"], "sectionCaption": "🔬 Advanced Filtering (Optional)", "sectionDescription": "Use these filters to get a highly targeted list and save on processing costs." }, "keywordSearchIn": { "title": "Search Keywords In", "type": "string", "description": "Where to search for keywords", "enum": ["bio", "fullName", "both"], "enumTitles": ["Biography or Full Name", "Biography only", "Full Name only"], "default": "bio", "editor": "select" }, "locationKeywords": { "title": "Filter by Location Keywords", "type": "array", "description": "Filter by location mentioned in bio (e.g., New York, London, Dubai)", "editor": "stringList", "example": ["New York", "London", "Dubai"] }, "language": { "title": "Filter by Profile Language", "type": "string", "description": "Filter profiles by detected language in bio", "enum": ["any", "en", "es", "fr", "de", "it", "pt", "ar", "hi", "ja", "ko"], "enumTitles": ["any", "English", "Spanish", "French", "German", "Italian", "Portuguese", "Arabic", "Hindi", "Japanese", "Korean"], "default": "any", "editor": "select" }, "minFollowers": { "title": "Follower Count Range: Min", "type": "integer", "description": "Minimum number of followers (0 = no minimum)", "minimum": 0, "default": 0 }, "maxFollowers": { "title": "and Max", "type": "integer", "description": "Maximum number of followers (0 = unlimited)", "minimum": 0, "default": 0 }, "lastPostAfter": { "title": "Filter by Last Post Date", "type": "string", "description": "Only include profiles that posted after this date (YYYY-MM-DD)", "editor": "textfield", "example": "2024-01-01" }, "minPostsInPeriod": { "title": "Filter by Posting Frequency: Min Posts", "type": "integer", "description": "Minimum number of posts required in the specified period", "minimum": 0, "default": 0 }, "postingPeriodDays": { "title": "in the last (days)", "type": "integer", "description": "Time period in days to check posting frequency", "minimum": 1, "maximum": 365, "default": 30 }, "reelsFilter": { "title": "Filter by Recent Reels", "type": "string", "description": "Filter by presence of recent Reels/video content", "enum": ["disabled", "hasReels", "noReels"], "enumTitles": ["Disabled", "Has Recent Reels", "No Recent Reels"], "default": "disabled", "editor": "select" }, "minMedianViews": { "title": "Filter by Median Views", "type": "integer", "description": "Minimum median views on recent posts (0 = disabled)", "minimum": 0, "default": 0 }, "highEngagementOnly": { "title": "Filter by Views/Followers Ratio >= 30%", "type": "boolean", "description": "Only include accounts with high engagement (views >= 30% of followers)", "default": false }, "contactInfoFilter": { "title": "Filter by Contact Info Presence", "type": "string", "description": "Filter profiles by availability of contact information", "enum": ["any", "hasEmail", "hasPhone", "hasWebsite", "hasAny", "hasEmailOrPhone"], "enumTitles": ["Any", "Has Email", "Has Phone Number", "Has Website", "Has Any Contact", "Has Email or Phone"], "default": "any", "editor": "select" }, "requireWebsite": { "title": "Filter by Website Presence", "type": "boolean", "description": "Only include profiles with website links", "default": false }, "accountTypeFilter": { "title": "Filter by Account Type", "type": "string", "description": "Filter by Instagram account type", "enum": ["any", "business", "creator", "personal"], "enumTitles": ["Any", "Business accounts only", "Creator accounts only", "Personal accounts only"], "default": "any", "editor": "select" }, "influencersOnly": { "title": "Filter for Influencers Only (by Category)", "type": "boolean", "description": "Only include accounts identified as influencers", "default": false }, "businessCategories": { "title": "Filter by Specific Business Category", "type": "array", "description": "Specific business categories/niches to filter (e.g., Fashion, Fitness, Food)", "editor": "stringList", "example": ["Fashion", "Fitness", "Food", "Travel", "Beauty"] }, "verificationFilter": { "title": "Filter by Verification", "type": "string", "description": "Filter by Instagram verification status (blue checkmark)", "enum": ["any", "verified", "notVerified"], "enumTitles": ["Any", "Verified only", "Not verified only"], "default": "any", "editor": "select" }, "proxy": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings - Residential proxies strongly recommended for Instagram", "editor": "proxy", "default": { "useApifyProxy": true, "apifyProxyGroups": ["RESIDENTIAL"] }, "sectionCaption": "▶️ Run & Storage Options" }, "sessionCookie": { "title": "Instagram Session Cookie (Recommended)", "type": "string", "description": "Your Instagram sessionid cookie for better access and data quality. See documentation for how to get this.", "editor": "textfield", "isSecret": true } }, "required": ["mode"]}1import { Actor } from 'apify';2import { PlaywrightCrawler } from 'crawlee';3
4// Main execution wrapped in try-catch5const main = async () => {6 console.log('🚀 iG Profile Scraper - Starting...');7
8 const input = await Actor.getInput();9 10 if (!input) {11 throw new Error('No input provided. Please configure the actor input.');12 }13
14 const {15 mode = 'MODE1',16 targetUsername,17 scrapeFollowers = true,18 scrapeFollowing = false,19 maxProfilesMode1 = 100,20 targetUsernames = [],21 scrapeFollowersMode2 = true,22 scrapeFollowingMode2 = false,23 maxProfilesPerAccount = 100,24 usernamesToAnalyze = [],25 maxProfilesMode3 = 100,26 seedUsernames = [],27 expansionDepth = 1,28 maxProfilesMode4 = 200,29 extractEmail = true,30 extractPhone = true,31 extractWebsite = true,32 extractBusinessCategory = true,33 extractAddress = false,34 calculateEngagementRate = true,35 extractPostCaptions = false,36 deepContactSearch = false,37 keywords = [],38 keywordSearchIn = 'bio',39 locationKeywords = [],40 language = 'any',41 minFollowers = 0,42 maxFollowers = 0,43 lastPostAfter,44 minPostsInPeriod = 0,45 postingPeriodDays = 30,46 reelsFilter = 'disabled',47 minMedianViews = 0,48 highEngagementOnly = false,49 contactInfoFilter = 'any',50 requireWebsite = false,51 accountTypeFilter = 'any',52 influencersOnly = false,53 businessCategories = [],54 verificationFilter = 'any',55 proxy,56 sessionCookie57 } = input;58
59 // Calculate max profiles based on mode60 let maxProfiles = 100;61 try {62 switch(mode) {63 case 'MODE1': 64 maxProfiles = maxProfilesMode1 || 100; 65 break;66 case 'MODE2': 67 maxProfiles = (maxProfilesPerAccount || 100) * Math.max(1, (targetUsernames || []).length); 68 break;69 case 'MODE3': 70 maxProfiles = maxProfilesMode3 || 100; 71 break;72 case 'MODE4': 73 maxProfiles = maxProfilesMode4 || 200; 74 break;75 }76 } catch (e) {77 console.log(`⚠️ Error calculating max profiles: ${e.message}`);78 maxProfiles = 100;79 }80
81 console.log(`📊 Mode: ${mode}`);82 console.log(`🎯 Max profiles to scrape: ${maxProfiles}`);83
84 // Validate mode-specific requirements85 if (mode === 'MODE1' && !targetUsername) {86 throw new Error('Target username is required for Mode 1. Please provide a username in the "Target Account" field.');87 }88 if (mode === 'MODE2' && (!targetUsernames || targetUsernames.length === 0)) {89 throw new Error('At least one username is required for Mode 2. Please provide usernames in the "List of Target Profiles" field.');90 }91 if (mode === 'MODE3' && (!usernamesToAnalyze || usernamesToAnalyze.length === 0)) {92 throw new Error('At least one username is required for Mode 3. Please provide usernames in the "List of Profiles to Analyze" field.');93 }94 if (mode === 'MODE4' && (!seedUsernames || seedUsernames.length === 0)) {95 throw new Error('At least one seed username is required for Mode 4. Please provide usernames in the "Start Profiles" field.');96 }97
98 // Setup proxy99 let proxyConfiguration;100 try {101 proxyConfiguration = await Actor.createProxyConfiguration(proxy);102 console.log('✅ Proxy configuration created');103 } catch (e) {104 console.error(`❌ Error creating proxy configuration: ${e.message}`);105 throw new Error('Failed to create proxy configuration. Please check your proxy settings.');106 }107
108 // Helper functions109 const extractEmailFromText = (text) => {110 if (!text || !extractEmail) return null;111 try {112 const emailRegex = /([a-zA-Z0-9._-]+@[a-zA-Z0-9._-]+\.[a-zA-Z0-9_-]+)/gi;113 const matches = text.match(emailRegex);114 return matches ? matches[0] : null;115 } catch (e) {116 return null;117 }118 };119
120 const extractPhoneFromText = (text) => {121 if (!text || !extractPhone) return null;122 try {123 const phoneRegex = /[\+]?[(]?[0-9]{1,4}[)]?[-\s\.]?[(]?[0-9]{1,4}[)]?[-\s\.]?[0-9]{1,4}[-\s\.]?[0-9]{1,9}/g;124 const matches = text.match(phoneRegex);125 return matches ? matches.filter(m => m.length >= 10)[0] : null;126 } catch (e) {127 return null;128 }129 };130
131 const containsKeywords = (text, keywordList) => {132 if (!keywordList || keywordList.length === 0) return true;133 if (!text) return false;134 try {135 const lowerText = text.toLowerCase();136 return keywordList.some(keyword => lowerText.includes(keyword.toLowerCase()));137 } catch (e) {138 return false;139 }140 };141
142 const applyFilters = (profile) => {143 try {144 // Keyword filter145 if (keywords.length > 0) {146 let textToSearch = '';147 if (keywordSearchIn === 'bio' || keywordSearchIn === 'both') {148 textToSearch += (profile.bio || '') + ' ';149 }150 if (keywordSearchIn === 'fullName' || keywordSearchIn === 'both') {151 textToSearch += (profile.fullName || '');152 }153 if (!containsKeywords(textToSearch, keywords)) return false;154 }155
156 // Location filter157 if (locationKeywords.length > 0) {158 if (!containsKeywords(profile.bio || '', locationKeywords)) return false;159 }160
161 // Follower count filter162 if (minFollowers > 0 && profile.followers < minFollowers) return false;163 if (maxFollowers > 0 && profile.followers > maxFollowers) return false;164
165 // Contact info filter166 if (contactInfoFilter !== 'any') {167 const hasEmail = !!profile.email;168 const hasPhone = !!profile.phone;169 const hasWebsite = !!profile.website;170 171 if (contactInfoFilter === 'hasEmail' && !hasEmail) return false;172 if (contactInfoFilter === 'hasPhone' && !hasPhone) return false;173 if (contactInfoFilter === 'hasWebsite' && !hasWebsite) return false;174 if (contactInfoFilter === 'hasAny' && !hasEmail && !hasPhone && !hasWebsite) return false;175 if (contactInfoFilter === 'hasEmailOrPhone' && !hasEmail && !hasPhone) return false;176 }177
178 if (requireWebsite && !profile.website) return false;179 if (accountTypeFilter !== 'any' && profile.accountType !== accountTypeFilter) return false;180 if (verificationFilter === 'verified' && !profile.isVerified) return false;181 if (verificationFilter === 'notVerified' && profile.isVerified) return false;182
183 return true;184 } catch (e) {185 console.error(`Error applying filters: ${e.message}`);186 return true; // Don't filter out on error187 }188 };189
190 // Generate start URLs191 const generateStartUrls = () => {192 const urls = [];193 194 try {195 switch (mode) {196 case 'MODE1':197 console.log(`🎯 Mode 1: Analyzing @${targetUsername}`);198 urls.push({199 url: `https://www.instagram.com/${targetUsername}/`,200 userData: { label: 'PROFILE', username: targetUsername, mode: 'MODE1' }201 });202 break;203 204 case 'MODE2':205 console.log(`🎯 Mode 2: Batch analyzing ${targetUsernames.length} accounts`);206 targetUsernames.forEach(username => {207 urls.push({208 url: `https://www.instagram.com/${username}/`,209 userData: { label: 'PROFILE', username, mode: 'MODE2' }210 });211 });212 break;213 214 case 'MODE3':215 console.log(`🎯 Mode 3: Analyzing ${usernamesToAnalyze.length} specific profiles`);216 usernamesToAnalyze.slice(0, maxProfiles).forEach(username => {217 urls.push({218 url: `https://www.instagram.com/${username}/`,219 userData: { label: 'PROFILE_DIRECT', username }220 });221 });222 break;223 224 case 'MODE4':225 console.log(`🎯 Mode 4: Network expansion from ${seedUsernames.length} seed profiles`);226 seedUsernames.forEach(username => {227 urls.push({228 url: `https://www.instagram.com/${username}/`,229 userData: { label: 'NETWORK_SEED', username, depth: 0 }230 });231 });232 break;233 }234 } catch (e) {235 console.error(`Error generating start URLs: ${e.message}`);236 throw e;237 }238 239 return urls;240 };241
242 const scrapedUsernames = new Set();243 let profileCount = 0;244
245 // Create Playwright crawler246 console.log('🔧 Creating Playwright crawler...');247 248 const crawler = new PlaywrightCrawler({249 proxyConfiguration,250 maxRequestsPerCrawl: maxProfiles * 10,251 headless: true,252 253 launchContext: {254 launchOptions: {255 headless: true,256 args: [257 '--no-sandbox',258 '--disable-setuid-sandbox',259 '--disable-dev-shm-usage',260 '--disable-accelerated-2d-canvas',261 '--disable-gpu'262 ]263 }264 },265
266 preNavigationHooks: [async ({ page, request }) => {267 try {268 // Set user agent269 await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36');270 271 // Set session cookie if provided272 if (sessionCookie) {273 await page.context().addCookies([274 {275 name: 'sessionid',276 value: sessionCookie,277 domain: '.instagram.com',278 path: '/',279 httpOnly: true,280 secure: true,281 sameSite: 'None'282 }283 ]);284 }285 } catch (e) {286 console.error(`Error in preNavigationHook: ${e.message}`);287 }288 }],289
290 requestHandler: async ({ page, request, crawler }) => {291 try {292 const { label, username, mode: reqMode, depth } = request.userData;293
294 await page.waitForTimeout(2000 + Math.random() * 2000);295
296 // Handle profile page for Mode 1 and Mode 2297 if (label === 'PROFILE') {298 console.log(`📋 Analyzing profile: @${username}`);299 300 try {301 await page.waitForSelector('header section', { timeout: 15000 });302 } catch (e) {303 console.log(` ⚠️ Could not load profile page: ${e.message}`);304 return;305 }306 307 // Extract profile data308 const profileData = await page.evaluate(() => {309 try {310 const data = {};311 312 data.username = window.location.pathname.split('/')[1];313 314 const nameEl = document.querySelector('header section h2, header h1, header section span');315 data.fullName = nameEl ? nameEl.innerText.trim() : '';316 317 const bioEl = document.querySelector('header section div.-vDIg span, header section ._aa_c span, header section span');318 data.bio = bioEl ? bioEl.innerText.trim() : '';319 320 const statsEls = document.querySelectorAll('header section ul li, header section a span');321 statsEls.forEach(el => {322 const text = el.innerText.toLowerCase();323 const countMatch = text.match(/[\d,kmb.]+/i);324 if (!countMatch) return;325 326 let countStr = countMatch[0].replace(/,/g, '');327 let multiplier = 1;328 if (countStr.toLowerCase().includes('k')) {329 multiplier = 1000;330 countStr = countStr.replace(/k/i, '');331 } else if (countStr.toLowerCase().includes('m')) {332 multiplier = 1000000;333 countStr = countStr.replace(/m/i, '');334 } else if (countStr.toLowerCase().includes('b')) {335 multiplier = 1000000000;336 countStr = countStr.replace(/b/i, '');337 }338 const count = Math.floor(parseFloat(countStr) * multiplier);339 340 if (text.includes('post')) data.posts = count;341 if (text.includes('follower')) data.followers = count;342 if (text.includes('following')) data.following = count;343 });344 345 const websiteEl = document.querySelector('header section a[href*="http"]');346 data.website = websiteEl ? websiteEl.href : null;347 348 data.isVerified = !!document.querySelector('header svg[aria-label*="Verified"], header svg[aria-label*="verified"]');349 350 return data;351 } catch (e) {352 console.error('Error extracting profile data:', e.message);353 return { username: window.location.pathname.split('/')[1] };354 }355 });356
357 profileData.url = `https://www.instagram.com/${username}/`;358 profileData.scrapedAt = new Date().toISOString();359 profileData.email = extractEmailFromText(profileData.bio);360 profileData.phone = extractPhoneFromText(profileData.bio);361 profileData.accountType = 'personal';362 363 console.log(` Profile: @${profileData.username} - ${profileData.followers || 0} followers`);364
365 // For Mode 1 and Mode 2, get followers/following366 if (reqMode === 'MODE1' || reqMode === 'MODE2') {367 const shouldScrapeFollowers = reqMode === 'MODE1' ? scrapeFollowers : scrapeFollowersMode2;368 const shouldScrapeFollowing = reqMode === 'MODE1' ? scrapeFollowing : scrapeFollowingMode2;369 const maxPerAccount = reqMode === 'MODE1' ? maxProfilesMode1 : maxProfilesPerAccount;370 371 if (shouldScrapeFollowers) {372 console.log(` 📥 Getting followers...`);373 374 try {375 await page.click('a[href*="/followers/"]', { timeout: 5000 });376 await page.waitForTimeout(3000);377 378 const followerUsernames = await page.evaluate(async (maxCount) => {379 const usernames = new Set();380 const dialog = document.querySelector('div[role="dialog"]');381 if (!dialog) return [];382 383 let lastCount = 0;384 let stableCount = 0;385 386 while (usernames.size < maxCount && stableCount < 5) {387 const links = dialog.querySelectorAll('a[href^="/"]');388 links.forEach(link => {389 const href = link.getAttribute('href');390 const match = href.match(/^\/([^\/]+)\/?$/);391 if (match && match[1]) {392 usernames.add(match[1]);393 }394 });395 396 dialog.scrollTop = dialog.scrollHeight;397 await new Promise(r => setTimeout(r, 1500));398 399 if (usernames.size === lastCount) {400 stableCount++;401 } else {402 stableCount = 0;403 }404 lastCount = usernames.size;405 }406 407 return Array.from(usernames);408 }, maxPerAccount);409 410 console.log(` ✅ Found ${followerUsernames.length} followers`);411 412 for (const followerUsername of followerUsernames) {413 if (profileCount >= maxProfiles) break;414 if (scrapedUsernames.has(followerUsername)) continue;415 416 scrapedUsernames.add(followerUsername);417 await crawler.addRequests([{418 url: `https://www.instagram.com/${followerUsername}/`,419 userData: { label: 'PROFILE_DIRECT', username: followerUsername }420 }]);421 }422 423 await page.keyboard.press('Escape');424 await page.waitForTimeout(1000);425 } catch (e) {426 console.log(` ⚠️ Could not scrape followers: ${e.message}`);427 }428 }429 430 if (shouldScrapeFollowing) {431 console.log(` 📤 Getting following...`);432 433 try {434 await page.click('a[href*="/following/"]', { timeout: 5000 });435 await page.waitForTimeout(3000);436 437 const followingUsernames = await page.evaluate(async (maxCount) => {438 const usernames = new Set();439 const dialog = document.querySelector('div[role="dialog"]');440 if (!dialog) return [];441 442 let lastCount = 0;443 let stableCount = 0;444 445 while (usernames.size < maxCount && stableCount < 5) {446 const links = dialog.querySelectorAll('a[href^="/"]');447 links.forEach(link => {448 const href = link.getAttribute('href');449 const match = href.match(/^\/([^\/]+)\/?$/);450 if (match && match[1]) {451 usernames.add(match[1]);452 }453 });454 455 dialog.scrollTop = dialog.scrollHeight;456 await new Promise(r => setTimeout(r, 1500));457 458 if (usernames.size === lastCount) {459 stableCount++;460 } else {461 stableCount = 0;462 }463 lastCount = usernames.size;464 }465 466 return Array.from(usernames);467 }, maxPerAccount);468 469 console.log(` ✅ Found ${followingUsernames.length} following`);470 471 for (const followingUsername of followingUsernames) {472 if (profileCount >= maxProfiles) break;473 if (scrapedUsernames.has(followingUsername)) continue;474 475 scrapedUsernames.add(followingUsername);476 await crawler.addRequests([{477 url: `https://www.instagram.com/${followingUsername}/`,478 userData: { label: 'PROFILE_DIRECT', username: followingUsername }479 }]);480 }481 } catch (e) {482 console.log(` ⚠️ Could not scrape following: ${e.message}`);483 }484 }485 }486 }487
488 // Handle direct profile scraping489 if (label === 'PROFILE_DIRECT') {490 if (profileCount >= maxProfiles) {491 console.log(`⏸️ Reached maximum profile limit (${maxProfiles})`);492 return;493 }494
495 console.log(`👤 Scraping: @${username} (${profileCount + 1}/${maxProfiles})`);496 497 try {498 await page.waitForSelector('header section', { timeout: 15000 });499 } catch (e) {500 console.log(` ⚠️ Could not load profile: ${e.message}`);501 return;502 }503 504 const profileData = await page.evaluate(() => {505 try {506 const data = {};507 data.username = window.location.pathname.split('/')[1];508 509 const nameEl = document.querySelector('header section h2, header h1, header section span');510 data.fullName = nameEl ? nameEl.innerText.trim() : '';511 512 const bioEl = document.querySelector('header section div.-vDIg span, header section ._aa_c span, header section span');513 data.bio = bioEl ? bioEl.innerText.trim() : '';514 515 const statsEls = document.querySelectorAll('header section ul li, header section a span');516 statsEls.forEach(el => {517 const text = el.innerText.toLowerCase();518 const countMatch = text.match(/[\d,kmb.]+/i);519 if (!countMatch) return;520 521 let countStr = countMatch[0].replace(/,/g, '');522 let multiplier = 1;523 if (countStr.toLowerCase().includes('k')) {524 multiplier = 1000;525 countStr = countStr.replace(/k/i, '');526 } else if (countStr.toLowerCase().includes('m')) {527 multiplier = 1000000;528 countStr = countStr.replace(/m/i, '');529 } else if (countStr.toLowerCase().includes('b')) {530 multiplier = 1000000000;531 countStr = countStr.replace(/b/i, '');532 }533 const count = Math.floor(parseFloat(countStr) * multiplier);534 535 if (text.includes('post')) data.posts = count;536 if (text.includes('follower')) data.followers = count;537 if (text.includes('following')) data.following = count;538 });539 540 const websiteEl = document.querySelector('header section a[href*="http"]');541 data.website = websiteEl ? websiteEl.href : null;542 543 data.isVerified = !!document.querySelector('header svg[aria-label*="Verified"], header svg[aria-label*="verified"]');544 545 return data;546 } catch (e) {547 return { username: window.location.pathname.split('/')[1] };548 }549 });550
551 profileData.url = `https://www.instagram.com/${username}/`;552 profileData.scrapedAt = new Date().toISOString();553 profileData.email = extractEmailFromText(profileData.bio);554 profileData.phone = extractPhoneFromText(profileData.bio);555 profileData.accountType = 'personal';556 557 if (calculateEngagementRate && profileData.followers > 0) {558 const estimatedRate = Math.max(0.5, Math.min(15, 100 / Math.log10(profileData.followers + 10)));559 profileData.engagementRate = estimatedRate.toFixed(2) + '%';560 }561
562 if (applyFilters(profileData)) {563 await Actor.pushData(profileData);564 profileCount++;565 console.log(` ✅ Saved (${profileCount}/${maxProfiles})`);566 } else {567 console.log(` ⛔ Filtered out`);568 }569 }570
571 // Handle network expansion572 if (label === 'NETWORK_SEED') {573 console.log(`🌐 Network expansion from: @${username} (depth: ${depth}/${expansionDepth})`);574 575 try {576 await page.waitForTimeout(3000);577 await page.evaluate(() => window.scrollTo(0, document.body.scrollHeight));578 await page.waitForTimeout(2000);579 580 const suggestedUsernames = await page.evaluate(() => {581 const usernames = [];582 const links = document.querySelectorAll('a[href^="/"]');583 links.forEach(link => {584 const href = link.getAttribute('href');585 const match = href.match(/^\/([^\/]+)\/?$/);586 if (match && match[1]) {587 usernames.push(match[1]);588 }589 });590 return [...new Set(usernames)];591 });592
593 console.log(` Found ${suggestedUsernames.length} suggested profiles`);594
595 const toProcess = suggestedUsernames.slice(0, 20);596 for (const suggestedUsername of toProcess) {597 if (profileCount >= maxProfiles) break;598 if (scrapedUsernames.has(suggestedUsername)) continue;599 600 scrapedUsernames.add(suggestedUsername);601 602 await crawler.addRequests([{603 url: `https://www.instagram.com/${suggestedUsername}/`,604 userData: { label: 'PROFILE_DIRECT', username: suggestedUsername }605 }]);606
607 if (depth < expansionDepth - 1) {608 await crawler.addRequests([{609 url: `https://www.instagram.com/${suggestedUsername}/`,610 userData: { label: 'NETWORK_SEED', username: suggestedUsername, depth: depth + 1 }611 }]);612 }613 }614 } catch (e) {615 console.log(` ⚠️ Network expansion error: ${e.message}`);616 }617 }618 } catch (error) {619 console.error(`❌ Error in request handler: ${error.message}`);620 console.error(error.stack);621 }622 },623
624 failedRequestHandler: async ({ request, error }) => {625 console.log(`❌ Request failed: ${request.url}`);626 console.log(` Error: ${error.message}`);627 },628
629 maxRequestRetries: 2,630 requestHandlerTimeoutSecs: 120,631 });632
633 // Start crawling634 try {635 const startUrls = generateStartUrls();636 console.log(`\n🎯 Starting with ${startUrls.length} initial URLs`);637 console.log(`⚙️ Data extraction: Email=${extractEmail}, Phone=${extractPhone}, Website=${extractWebsite}`);638 if (keywords.length > 0) {639 console.log(`🔍 Filtering by keywords: ${keywords.join(', ')}`);640 }641 console.log(`\n▶️ Starting crawl...\n`);642 643 await crawler.run(startUrls);644 645 console.log(`\n✅ Scraping completed!`);646 console.log(`📊 Total profiles scraped: ${profileCount}`);647 console.log(`💾 Results saved to dataset`);648 } catch (error) {649 console.error(`\n❌ Crawl error: ${error.message}`);650 console.error(error.stack);651 throw error;652 }653};654
655// Initialize Actor and run main function656try {657 await Actor.init();658 await main();659 await Actor.exit();660} catch (error) {661 console.error(`\n💥 Critical error: ${error.message}`);662 console.error(error.stack);663 await Actor.exit({ statusMessage: error.message, exitCode: 1 });664}# Use the Apify base image with Playwright and ChromeFROM apify/actor-node-playwright-chrome:20
# Copy package.json and package-lock.jsonCOPY package*.json ./
# Install dependenciesRUN npm --quiet set progress=false \ && npm install --only=prod --no-optional \ && echo "Installed NPM packages:" \ && (npm list --only=prod --no-optional --all || true) \ && echo "Node.js version:" \ && node --version \ && echo "NPM version:" \ && npm --version \ && echo "Playwright version:" \ && npm list playwright
# Copy source codeCOPY . ./
# Run the actorCMD npm start{ "name": "instagram-lead-scraper", "version": "1.0.0", "type": "module", "description": "Scrape Instagram leads from hashtags", "main": "src/main.js", "scripts": { "start": "node src/main.js", "test": "echo \"No tests specified\"" }, "dependencies": { "apify": "^3.1.0", "crawlee": "^3.5.0", "playwright": "^1.48.0"
}, "author": "lucid_garden", "license": "ISC"}