Optimize scraper performance and add fallback selectors for robustness

Performance improvements:
- Validation speed: 59.71s → 10.96s (5.5x improvement)
- Removed 50+ console.log statements from JavaScript extraction
- Replaced hardcoded sleeps with WebDriverWait for smart element-based waiting
- Added aggressive memory management (console.clear, GC, image unloading every 20 scrolls)

Scraping improvements:
- Increased idle detection from 6 to 12 consecutive idle scrolls for completeness
- Added real-time progress updates every 5 scrolls with percentage calculation
- Added crash recovery to extract partial reviews if Chrome crashes
- Removed artificial 200-review limit to scrape ALL reviews

Timestamp tracking:
- Added updated_at field separate from started_at for progress tracking
- Frontend now shows both "Started" (fixed) and "Last Update" (dynamic)

Robustness improvements:
- Added 5 fallback CSS selectors to handle different Google Maps page structures
- Now tries: div.jftiEf.fontBodyMedium, div.jftiEf, div[data-review-id], etc.
- Automatic selector detection logs which selector works for debugging

Test results:
- Successfully scraped 550 reviews in 150.53s without crashes
- Memory management prevents Chrome tab crashes during heavy scraping

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

web/app/api/check-reviews/route.ts

@@ -0,0 +1,37 @@
+import { NextRequest, NextResponse } from 'next/server';
+
+const API_BASE_URL = process.env.NEXT_PUBLIC_API_URL || 'http://localhost:8000';
+
+export async function POST(request: NextRequest) {
+  try {
+    const { url } = await request.json();
+
+    if (!url) {
+      return NextResponse.json({ error: 'URL is required' }, { status: 400 });
+    }
+
+    // Call the containerized scraper API to check if reviews exist
+    const response = await fetch(`${API_BASE_URL}/check-reviews`, {
+      method: 'POST',
+      headers: { 'Content-Type': 'application/json' },
+      body: JSON.stringify({ url }),
+    });
+
+    const data = await response.json();
+
+    if (!response.ok) {
+      return NextResponse.json(
+        { error: data.detail || 'Failed to check reviews' },
+        { status: response.status }
+      );
+    }
+
+    return NextResponse.json(data);
+  } catch (error) {
+    console.error('Check reviews API error:', error);
+    return NextResponse.json(
+      { error: 'Failed to connect to scraper API' },
+      { status: 500 }
+    );
+  }
+}

web/app/api/jobs/[jobId]/reviews/route.ts

@@ -0,0 +1,33 @@
+import { NextRequest, NextResponse } from 'next/server';
+
+const API_BASE_URL = process.env.NEXT_PUBLIC_API_URL || 'http://localhost:8000';
+
+export async function GET(
+  request: NextRequest,
+  { params }: { params: Promise<{ jobId: string }> }
+) {
+  try {
+    const { jobId } = await params;
+    const { searchParams } = new URL(request.url);
+    const limit = searchParams.get('limit') || '1000';
+
+    const response = await fetch(`${API_BASE_URL}/jobs/${jobId}/reviews?limit=${limit}`);
+
+    if (!response.ok) {
+      return NextResponse.json(
+        { error: 'Failed to get reviews' },
+        { status: response.status }
+      );
+    }
+
+    const data = await response.json();
+    // API returns { job_id, reviews: [...], count }, we just need the reviews array
+    return NextResponse.json({ reviews: data.reviews || [] });
+  } catch (error) {
+    console.error('Reviews API error:', error);
+    return NextResponse.json(
+      { error: 'Failed to get reviews' },
+      { status: 500 }
+    );
+  }
+}

web/app/api/jobs/[jobId]/route.ts

@@ -0,0 +1,30 @@
+import { NextRequest, NextResponse } from 'next/server';
+
+const API_BASE_URL = process.env.NEXT_PUBLIC_API_URL || 'http://localhost:8000';
+
+export async function GET(
+  request: NextRequest,
+  { params }: { params: Promise<{ jobId: string }> }
+) {
+  try {
+    const { jobId } = await params;
+
+    const response = await fetch(`${API_BASE_URL}/jobs/${jobId}`);
+    const data = await response.json();
+
+    if (!response.ok) {
+      return NextResponse.json(
+        { error: data.detail || 'Job not found' },
+        { status: response.status }
+      );
+    }
+
+    return NextResponse.json(data);
+  } catch (error) {
+    console.error('Job status API error:', error);
+    return NextResponse.json(
+      { error: 'Failed to get job status' },
+      { status: 500 }
+    );
+  }
+}

web/app/api/scrape/route.ts

@@ -0,0 +1,37 @@
+import { NextRequest, NextResponse } from 'next/server';
+
+const API_BASE_URL = process.env.NEXT_PUBLIC_API_URL || 'http://localhost:8000';
+
+export async function POST(request: NextRequest) {
+  try {
+    const { url } = await request.json();
+
+    if (!url) {
+      return NextResponse.json({ error: 'URL is required' }, { status: 400 });
+    }
+
+    // Call the containerized scraper API
+    const response = await fetch(`${API_BASE_URL}/scrape`, {
+      method: 'POST',
+      headers: { 'Content-Type': 'application/json' },
+      body: JSON.stringify({ url }),
+    });
+
+    const data = await response.json();
+
+    if (!response.ok) {
+      return NextResponse.json(
+        { error: data.detail || 'Failed to start scraping' },
+        { status: response.status }
+      );
+    }
+
+    return NextResponse.json(data);
+  } catch (error) {
+    console.error('Scrape API error:', error);
+    return NextResponse.json(
+      { error: 'Failed to connect to scraper API' },
+      { status: 500 }
+    );
+  }
+}