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>
145 lines
4.4 KiB
Python
145 lines
4.4 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Debug script for the actual business user tried: Soho Vilna Club
|
|
"""
|
|
import time
|
|
from seleniumbase import Driver
|
|
from selenium.webdriver.common.by import By
|
|
|
|
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(3)
|
|
|
|
# Handle GDPR
|
|
if 'consent.google.com' in driver.current_url:
|
|
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(3)
|
|
break
|
|
|
|
time.sleep(5)
|
|
print(f"Current URL: {driver.current_url}\n")
|
|
|
|
# Check if still on search results or navigated to business page
|
|
is_search_results = '/search/' in driver.current_url
|
|
print(f"On search results page: {is_search_results}\n")
|
|
|
|
# Extract info
|
|
result = driver.execute_script("""
|
|
const info = {
|
|
tabs: [],
|
|
reviewCount: null,
|
|
businessName: null,
|
|
rating: null,
|
|
searchResults: []
|
|
};
|
|
|
|
const isSearchPage = window.location.href.includes('/search/');
|
|
|
|
// Get business name
|
|
const nameElem = document.querySelector('h1.DUwDvf, [role="main"] h1, h1.fontHeadlineLarge');
|
|
if (nameElem) {
|
|
info.businessName = nameElem.textContent.trim();
|
|
}
|
|
|
|
// Get rating
|
|
const ratingElem = document.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]);
|
|
}
|
|
}
|
|
|
|
// Get all tabs
|
|
const tabs = document.querySelectorAll('button[role="tab"]');
|
|
tabs.forEach((tab, i) => {
|
|
const text = tab.textContent || '';
|
|
const ariaLabel = tab.getAttribute('aria-label') || '';
|
|
info.tabs.push({
|
|
index: i,
|
|
text: text,
|
|
ariaLabel: ariaLabel
|
|
});
|
|
|
|
// Try to extract review count from tabs
|
|
const reviewPattern = /\\((\\d[\\d,\\.]*)\\)/;
|
|
const numberPattern = /(\\d[\\d,\\.]*)\\s*(?:review|reseña|avis)/i;
|
|
|
|
let match = text.match(reviewPattern);
|
|
if (!match) match = text.match(numberPattern);
|
|
if (!match) match = ariaLabel.match(reviewPattern);
|
|
if (!match) match = ariaLabel.match(numberPattern);
|
|
|
|
if (match) {
|
|
const num = parseInt(match[1].replace(/[,\\.\\s]/g, ''));
|
|
if (num > 0 && num < 1000000) {
|
|
info.reviewCount = num;
|
|
}
|
|
}
|
|
});
|
|
|
|
// If on search results, try to get review count from search panel
|
|
if (isSearchPage || !info.reviewCount) {
|
|
const numberPattern = /(\\d[\\d,\\.]*)\\s*(?:review|reseña|avis)/i;
|
|
|
|
// Check all elements
|
|
const allElements = document.querySelectorAll('a, span, div');
|
|
for (let elem of allElements) {
|
|
const text = elem.textContent || '';
|
|
if (text.length > 0 && text.length < 150) {
|
|
const match = text.match(numberPattern);
|
|
if (match) {
|
|
const num = parseInt(match[1].replace(/[,\\.\\s]/g, ''));
|
|
if (num > 0 && num < 1000000) {
|
|
info.searchResults.push({
|
|
tag: elem.tagName,
|
|
class: elem.className,
|
|
text: text,
|
|
number: num
|
|
});
|
|
|
|
if (!info.reviewCount) {
|
|
info.reviewCount = num;
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
return info;
|
|
""")
|
|
|
|
print("="*80)
|
|
print("BUSINESS INFO:")
|
|
print("="*80)
|
|
print(f"Name: {result['businessName']}")
|
|
print(f"Rating: {result['rating']}")
|
|
print(f"Review Count: {result['reviewCount']}\n")
|
|
|
|
print("="*80)
|
|
print("TABS FOUND:")
|
|
print("="*80)
|
|
for tab in result['tabs']:
|
|
print(f"\nTab {tab['index']}:")
|
|
print(f" Text: {tab['text']}")
|
|
print(f" Aria-label: {tab['ariaLabel']}")
|
|
|
|
if result['searchResults']:
|
|
print(f"\n{'='*80}")
|
|
print("SEARCH RESULTS WITH NUMBERS (first 10):")
|
|
print("="*80)
|
|
for i, sr in enumerate(result['searchResults'][:10], 1):
|
|
print(f"\n{i}. <{sr['tag']}> class='{sr['class'][:40]}'")
|
|
print(f" Number found: {sr['number']}")
|
|
print(f" Text: {sr['text'][:100]}")
|
|
|
|
driver.quit()
|