feat: Instagram scraper with GraphQL API integration - Automated followings list extraction via API interception - Profile scraping using GraphQL endpoint interception - DOM fallback for edge cases - Performance timing for all operations - Anti-bot measures and human-like behavior simulation

utils.js

@@ -0,0 +1,146 @@
+function randomSleep(minMs = 2000, maxMs = 5000) {
+  const delay = Math.floor(Math.random() * (maxMs - minMs + 1)) + minMs;
+  return new Promise((res) => setTimeout(res, delay));
+}
+
+async function humanLikeMouseMovement(page, steps = 10) {
+  // Simulate human-like mouse movements across the page
+  const viewport = await page.viewport();
+  const width = viewport.width;
+  const height = viewport.height;
+
+  for (let i = 0; i < steps; i++) {
+    const x = Math.floor(Math.random() * width);
+    const y = Math.floor(Math.random() * height);
+
+    await page.mouse.move(x, y, { steps: Math.floor(Math.random() * 10) + 5 });
+    await randomSleep(100, 500);
+  }
+}
+
+async function randomScroll(page, scrollCount = 3) {
+  // Perform random scrolling to simulate human behavior
+  for (let i = 0; i < scrollCount; i++) {
+    const scrollAmount = Math.floor(Math.random() * 300) + 100;
+    await page.evaluate((amount) => {
+      window.scrollBy(0, amount);
+    }, scrollAmount);
+    await randomSleep(800, 1500);
+  }
+}
+
+async function simulateHumanBehavior(page, options = {}) {
+  // Combined function to simulate various human-like behaviors
+  const { mouseMovements = 5, scrolls = 2, randomClicks = false } = options;
+
+  // Random mouse movements
+  if (mouseMovements > 0) {
+    await humanLikeMouseMovement(page, mouseMovements);
+  }
+
+  // Random scrolling
+  if (scrolls > 0) {
+    await randomScroll(page, scrolls);
+  }
+
+  // Optional: Random clicks on non-interactive elements
+  if (randomClicks) {
+    try {
+      await page.evaluate(() => {
+        const elements = document.querySelectorAll("div, span, p");
+        if (elements.length > 0) {
+          const randomElement =
+            elements[Math.floor(Math.random() * elements.length)];
+          const rect = randomElement.getBoundingClientRect();
+          // Just move to it, don't actually click to avoid triggering actions
+        }
+      });
+    } catch (err) {
+      // Ignore errors from random element selection
+    }
+  }
+
+  await randomSleep(500, 1000);
+}
+
+async function withRetry(fn, options = {}) {
+  const {
+    maxRetries = 3,
+    initialDelay = 2000,
+    maxDelay = 30000,
+    shouldRetry = (error) => true,
+  } = options;
+
+  for (let attempt = 0; attempt < maxRetries; attempt++) {
+    try {
+      return await fn();
+    } catch (error) {
+      const isLastAttempt = attempt === maxRetries - 1;
+
+      // Check if we should retry this error
+      if (!shouldRetry(error) || isLastAttempt) {
+        throw error;
+      }
+
+      // Calculate exponential backoff delay: 2s, 4s, 8s, 16s, 30s (capped)
+      const exponentialDelay = Math.min(
+        initialDelay * Math.pow(2, attempt),
+        maxDelay
+      );
+
+      // Add jitter (randomize ±20%) to avoid thundering herd
+      const jitter = exponentialDelay * (0.8 + Math.random() * 0.4);
+      const delay = Math.floor(jitter);
+
+      console.log(
+        `Retry attempt ${attempt + 1}/${maxRetries} after ${delay}ms delay...`
+      );
+      console.log(`Error: ${error.message || error}`);
+
+      await randomSleep(delay, delay);
+    }
+  }
+}
+
+async function handleRateLimitedRequest(page, requestFn, context = "") {
+  return withRetry(requestFn, {
+    maxRetries: 5,
+    initialDelay: 2000,
+    maxDelay: 60000,
+    shouldRetry: (error) => {
+      // Retry on rate limit (429) or temporary errors
+      if (error.status === 429 || error.statusCode === 429) {
+        console.log(`Rate limited (429) ${context}. Backing off...`);
+        return true;
+      }
+
+      // Retry on 5xx server errors
+      if (error.status >= 500 || error.statusCode >= 500) {
+        console.log(
+          `Server error (${
+            error.status || error.statusCode
+          }) ${context}. Retrying...`
+        );
+        return true;
+      }
+
+      // Retry on network errors
+      if (error.code === "ECONNRESET" || error.code === "ETIMEDOUT") {
+        console.log(`Network error (${error.code}) ${context}. Retrying...`);
+        return true;
+      }
+
+      // Don't retry on client errors (4xx except 429)
+      return false;
+    },
+  });
+}
+
+module.exports = {
+  randomSleep,
+  humanLikeMouseMovement,
+  randomScroll,
+  simulateHumanBehavior,
+  withRetry,
+  handleRateLimitedRequest,
+};