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>
143 lines
4.6 KiB
Python
143 lines
4.6 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Debug script - wait for search results to load before extracting.
|
|
"""
|
|
import time
|
|
from seleniumbase import Driver
|
|
from selenium.webdriver.common.by import By
|
|
from selenium.webdriver.support.ui import WebDriverWait
|
|
from selenium.webdriver.support import expected_conditions as EC
|
|
|
|
driver = Driver(uc=True, headless=True)
|
|
|
|
url = "https://www.google.com/maps/search/?api=1&query=soho+vilna+club&hl=en"
|
|
print(f"Navigating to: {url}")
|
|
driver.get(url)
|
|
time.sleep(2)
|
|
|
|
# Handle GDPR
|
|
if 'consent.google.com' in driver.current_url:
|
|
print("Handling GDPR...")
|
|
form_btns = driver.find_elements(By.CSS_SELECTOR, 'form button')
|
|
for btn in form_btns:
|
|
if 'accept all' in (btn.text or '').lower():
|
|
btn.click()
|
|
time.sleep(2)
|
|
break
|
|
|
|
print(f"Current URL: {driver.current_url}")
|
|
print("Waiting for search results to load...\n")
|
|
|
|
# Wait for search results to appear (but don't wait so long that Google auto-navigates)
|
|
try:
|
|
# Wait for the first result card to appear
|
|
wait = WebDriverWait(driver, 10)
|
|
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, 'div[role="article"], a[href*="/place/"]')))
|
|
print("✓ Search results loaded!")
|
|
except Exception as e:
|
|
print(f"✗ Timeout waiting for results: {e}")
|
|
|
|
# Give it just a tiny bit more time for content to render
|
|
time.sleep(0.5)
|
|
|
|
print(f"Current URL: {driver.current_url}")
|
|
print(f"Still on search results: {'/search/' in driver.current_url}\n")
|
|
|
|
# Extract
|
|
result = driver.execute_script("""
|
|
const info = {
|
|
businessName: null,
|
|
rating: null,
|
|
reviewCount: null,
|
|
debug: []
|
|
};
|
|
|
|
// Find first result card
|
|
const resultCard = document.querySelector('div[role="article"], a[href*="/place/"]');
|
|
if (!resultCard) {
|
|
info.debug.push('No result card found');
|
|
return info;
|
|
}
|
|
|
|
info.debug.push('Found result card');
|
|
|
|
// Get full text of card
|
|
const cardText = resultCard.textContent || '';
|
|
info.debug.push(`Card text length: ${cardText.length}`);
|
|
info.debug.push(`Card text (first 300 chars): ${cardText.substring(0, 300)}`);
|
|
|
|
// Extract business name (usually first h3 or div with specific class)
|
|
const nameElem = resultCard.querySelector('h3, div.fontHeadlineSmall, div[class*="fontHeadline"]');
|
|
if (nameElem) {
|
|
info.businessName = nameElem.textContent.trim();
|
|
info.debug.push(`Found name: ${info.businessName}`);
|
|
}
|
|
|
|
// Extract rating
|
|
const ratingElem = resultCard.querySelector('[role="img"][aria-label*="star"]');
|
|
if (ratingElem) {
|
|
const ariaLabel = ratingElem.getAttribute('aria-label');
|
|
const match = ariaLabel.match(/([0-9.]+)/);
|
|
if (match) {
|
|
info.rating = parseFloat(match[1]);
|
|
info.debug.push(`Found rating: ${info.rating}`);
|
|
}
|
|
}
|
|
|
|
// Extract review count - look for "N reviews" pattern
|
|
const numberPattern = /(\\d[\\d,\\.]*)\\s*(?:review|reseña|avis)/i;
|
|
const match = cardText.match(numberPattern);
|
|
|
|
if (match) {
|
|
const num = parseInt(match[1].replace(/[,\\.\\s]/g, ''));
|
|
if (num > 0 && num < 1000000) {
|
|
info.reviewCount = num;
|
|
info.debug.push(`✓ Found review count: ${num}`);
|
|
}
|
|
} else {
|
|
info.debug.push('No review count pattern found in card text');
|
|
|
|
// Try checking individual child elements
|
|
const allChildren = resultCard.querySelectorAll('*');
|
|
info.debug.push(`Card has ${allChildren.length} child elements`);
|
|
|
|
for (let child of allChildren) {
|
|
const childText = child.textContent || '';
|
|
if (childText.length < 100 && /review/i.test(childText)) {
|
|
info.debug.push(`Element with "review": ${childText}`);
|
|
|
|
const match = childText.match(numberPattern);
|
|
if (match) {
|
|
const num = parseInt(match[1].replace(/[,\\.\\s]/g, ''));
|
|
if (num > 0 && num < 1000000 && !info.reviewCount) {
|
|
info.reviewCount = num;
|
|
info.debug.push(`✓ Found via child element: ${num}`);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
return info;
|
|
""")
|
|
|
|
print("="*80)
|
|
print("EXTRACTION RESULTS:")
|
|
print("="*80)
|
|
print(f"Business Name: {result['businessName']}")
|
|
print(f"Rating: {result['rating']}")
|
|
print(f"Review Count: {result['reviewCount']}\n")
|
|
|
|
print("="*80)
|
|
print("DEBUG INFO:")
|
|
print("="*80)
|
|
for debug_line in result['debug']:
|
|
print(f" {debug_line}")
|
|
|
|
# Take a screenshot of the search results
|
|
screenshot_path = '/tmp/search_results.png'
|
|
driver.save_screenshot(screenshot_path)
|
|
print(f"\n✓ Screenshot saved to: {screenshot_path}")
|
|
|
|
driver.quit()
|