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>
This commit is contained in:
Alejandro Gutiérrez
305
header_capture_scraper.py
Normal file
305
header_capture_scraper.py
Normal file
@@ -0,0 +1,305 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Header Capture Scraper - Capture COMPLETE request from browser (headers + cookies).
|
||||
|
||||
This captures the exact request the browser makes, including ALL headers and cookies,
|
||||
then replays it for fast API scraping.
|
||||
"""
|
||||
import json
|
||||
import logging
|
||||
import time
|
||||
from typing import List, Optional, Tuple
|
||||
import requests
|
||||
from seleniumbase import SB
|
||||
from modules.api_interceptor import GoogleMapsAPIInterceptor, InterceptedReview
|
||||
|
||||
logging.basicConfig(level=logging.INFO, format='[%(levelname)s] %(message)s')
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class HeaderCaptureScraper:
|
||||
"""Capture complete request, then replay for fast scraping."""
|
||||
|
||||
def __init__(self, url: str, headless: bool = False):
|
||||
self.url = url
|
||||
self.headless = headless
|
||||
self.captured_request = None
|
||||
self.place_id = None
|
||||
self.session = requests.Session()
|
||||
self.interceptor = GoogleMapsAPIInterceptor(None)
|
||||
|
||||
def capture_request(self) -> bool:
|
||||
"""
|
||||
Capture a complete API request (URL, headers, cookies) from browser.
|
||||
"""
|
||||
log.info("="*60)
|
||||
log.info("Capturing request from browser...")
|
||||
log.info("="*60)
|
||||
|
||||
sb_context = None
|
||||
sb = None
|
||||
|
||||
try:
|
||||
log.info("Starting browser...")
|
||||
sb_context = SB(uc=True, headless=self.headless)
|
||||
sb = sb_context.__enter__()
|
||||
|
||||
sb.open(self.url)
|
||||
time.sleep(2)
|
||||
|
||||
# Dismiss cookies
|
||||
try:
|
||||
sb.click('button[aria-label*="Accept" i],button[aria-label*="Aceptar" i]', timeout=3)
|
||||
except:
|
||||
pass
|
||||
|
||||
# Click reviews
|
||||
try:
|
||||
sb.click('.LRkQ2', timeout=5)
|
||||
log.info("✓ Opened reviews")
|
||||
time.sleep(2)
|
||||
except:
|
||||
pass
|
||||
|
||||
# Enable CDP network monitoring
|
||||
sb.driver.execute_cdp_cmd('Network.enable', {})
|
||||
log.info("✓ Network monitoring enabled")
|
||||
|
||||
# Scroll to trigger API call
|
||||
log.info("Scrolling to trigger API request...")
|
||||
sb.execute_script("window.scrollBy(0, 800)")
|
||||
time.sleep(3)
|
||||
|
||||
# Get network logs from CDP
|
||||
log.info("Checking network logs...")
|
||||
logs = sb.driver.get_log('browser')
|
||||
|
||||
# Alternatively, use execute_cdp_cmd to get network events
|
||||
# But simpler: Let's inject JS to capture the request
|
||||
capture_script = """
|
||||
window.__capturedRequest = null;
|
||||
|
||||
const originalFetch = window.fetch;
|
||||
window.fetch = function(...args) {
|
||||
const url = args[0].toString();
|
||||
if (url.includes('listugcposts')) {
|
||||
console.log('[CAPTURE] Intercepted request to:', url);
|
||||
window.__capturedRequest = {
|
||||
url: url,
|
||||
method: 'GET'
|
||||
};
|
||||
}
|
||||
return originalFetch.apply(this, args);
|
||||
};
|
||||
|
||||
const originalXHR = window.XMLHttpRequest;
|
||||
window.XMLHttpRequest = function() {
|
||||
const xhr = new originalXHR();
|
||||
const originalOpen = xhr.open;
|
||||
|
||||
xhr.open = function(method, url, ...rest) {
|
||||
if (url.includes('listugcposts')) {
|
||||
console.log('[CAPTURE] Intercepted XHR:', url);
|
||||
window.__capturedRequest = {
|
||||
url: url,
|
||||
method: method
|
||||
};
|
||||
}
|
||||
return originalOpen.apply(this, [method, url, ...rest]);
|
||||
};
|
||||
|
||||
return xhr;
|
||||
};
|
||||
|
||||
console.log('[CAPTURE] Request interceptor ready');
|
||||
"""
|
||||
|
||||
sb.execute_script(capture_script)
|
||||
log.info("✓ Request interceptor injected")
|
||||
|
||||
# Scroll again to trigger request
|
||||
log.info("Scrolling to capture request...")
|
||||
for i in range(3):
|
||||
sb.execute_script("window.scrollBy(0, 600)")
|
||||
time.sleep(2)
|
||||
|
||||
captured = sb.execute_script("return window.__capturedRequest")
|
||||
if captured:
|
||||
log.info(f"✓ Captured request URL!")
|
||||
self.captured_request = captured
|
||||
break
|
||||
|
||||
if not self.captured_request:
|
||||
log.error("Failed to capture request")
|
||||
return False
|
||||
|
||||
# Extract place ID from URL
|
||||
url = self.captured_request['url']
|
||||
if '!1s' in url:
|
||||
import urllib.parse
|
||||
parsed = urllib.parse.urlparse(url)
|
||||
params = urllib.parse.parse_qs(parsed.query)
|
||||
pb = params.get('pb', [''])[0]
|
||||
if '!1s' in pb:
|
||||
self.place_id = pb.split('!1s')[1].split('!')[0]
|
||||
|
||||
# Now capture ALL cookies via CDP
|
||||
cdp_cookies = sb.driver.execute_cdp_cmd('Network.getAllCookies', {})
|
||||
all_cookies = cdp_cookies.get('cookies', [])
|
||||
|
||||
# Set cookies in session
|
||||
for cookie in all_cookies:
|
||||
self.session.cookies.set(
|
||||
name=cookie['name'],
|
||||
value=cookie['value'],
|
||||
domain=cookie.get('domain', '.google.com'),
|
||||
path=cookie.get('path', '/')
|
||||
)
|
||||
|
||||
# Get user agent
|
||||
user_agent = sb.execute_script("return navigator.userAgent")
|
||||
|
||||
# Set headers to match browser
|
||||
self.session.headers.update({
|
||||
'User-Agent': user_agent,
|
||||
'Accept': '*/*',
|
||||
'Accept-Language': 'es,es-ES;q=0.9,en;q=0.8',
|
||||
'Referer': 'https://www.google.com/maps/',
|
||||
'Origin': 'https://www.google.com',
|
||||
'X-Requested-With': 'XMLHttpRequest',
|
||||
})
|
||||
|
||||
log.info(f"\n✅ Request captured successfully!")
|
||||
log.info(f" Place ID: {self.place_id}")
|
||||
log.info(f" Cookies: {len(all_cookies)}")
|
||||
log.info(f" Cookie names: {', '.join([c['name'] for c in all_cookies[:10]])}")
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
log.error(f"Capture failed: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
return False
|
||||
|
||||
finally:
|
||||
if sb_context:
|
||||
try:
|
||||
log.info("Closing browser...")
|
||||
sb_context.__exit__(None, None, None)
|
||||
log.info("✓ Browser closed\n")
|
||||
except:
|
||||
pass
|
||||
|
||||
def fetch_reviews_page(self, continuation_token: Optional[str] = None) -> Tuple[List[InterceptedReview], Optional[str]]:
|
||||
"""Fetch reviews using captured session."""
|
||||
|
||||
if continuation_token:
|
||||
pb = f"!1m6!1s{self.place_id}!6m4!4m1!1e1!4m1!1e3!2m2!1i10!2s{continuation_token}!5m2!1sByJsaaTKLK-bi-gPiqKAiQE!7e81!8m9!2b1!3b1!5b1!7b1!12m4!1b1!2b1!4m1!1e1!11m4!1e3!2e1!6m1!1i2!13m1!1e1"
|
||||
else:
|
||||
pb = f"!1m6!1s{self.place_id}!6m4!4m1!1e1!4m1!1e3!2m2!1i10!5m2!1sByJsaaTKLK-bi-gPiqKAiQE!7e81!8m9!2b1!3b1!5b1!7b1!12m4!1b1!2b1!4m1!1e1!11m4!1e3!2e1!6m1!1i2!13m1!1e1"
|
||||
|
||||
params = {
|
||||
'authuser': '0',
|
||||
'hl': 'es',
|
||||
'gl': 'es',
|
||||
'pb': pb
|
||||
}
|
||||
|
||||
try:
|
||||
url = 'https://www.google.com/maps/rpc/listugcposts'
|
||||
response = self.session.get(url, params=params, timeout=10)
|
||||
|
||||
if response.status_code != 200:
|
||||
log.error(f"API error {response.status_code}: {response.text[:200]}")
|
||||
return [], None
|
||||
|
||||
body = response.text
|
||||
if body.startswith(")]}'"):
|
||||
body = body[4:].strip()
|
||||
|
||||
data = json.loads(body)
|
||||
reviews = self.interceptor._parse_listugcposts_response(data)
|
||||
|
||||
next_token = None
|
||||
if isinstance(data, list) and len(data) > 1 and isinstance(data[1], str):
|
||||
next_token = data[1]
|
||||
|
||||
return reviews, next_token
|
||||
|
||||
except Exception as e:
|
||||
log.error(f"Request failed: {e}")
|
||||
return [], None
|
||||
|
||||
def scrape_all(self, max_pages: int = 50) -> List[dict]:
|
||||
"""Main scraping method."""
|
||||
|
||||
if not self.capture_request():
|
||||
return []
|
||||
|
||||
log.info("="*60)
|
||||
log.info("Fast API scraping...")
|
||||
log.info("="*60)
|
||||
|
||||
start_time = time.time()
|
||||
all_reviews = []
|
||||
seen_ids = set()
|
||||
token = None
|
||||
page = 0
|
||||
|
||||
while page < max_pages:
|
||||
page += 1
|
||||
log.info(f"Page {page}...")
|
||||
|
||||
reviews, token = self.fetch_reviews_page(token)
|
||||
|
||||
if not reviews:
|
||||
break
|
||||
|
||||
for review in reviews:
|
||||
rid = review.review_id or f"{review.author}_{review.date_text}"
|
||||
if rid not in seen_ids:
|
||||
seen_ids.add(rid)
|
||||
all_reviews.append({
|
||||
'review_id': review.review_id,
|
||||
'author': review.author,
|
||||
'rating': review.rating,
|
||||
'text': review.text,
|
||||
'date_text': review.date_text,
|
||||
'avatar_url': review.avatar_url,
|
||||
})
|
||||
|
||||
log.info(f" → {len(reviews)} reviews | Total: {len(all_reviews)}")
|
||||
|
||||
if not token:
|
||||
break
|
||||
|
||||
time.sleep(0.2)
|
||||
|
||||
elapsed = time.time() - start_time
|
||||
|
||||
log.info(f"\n{'='*60}")
|
||||
log.info(f"✅ COMPLETED!")
|
||||
log.info(f"{'='*60}")
|
||||
log.info(f"Reviews: {len(all_reviews)}")
|
||||
log.info(f"Time: {elapsed:.2f}s")
|
||||
log.info(f"Speed: {len(all_reviews)/elapsed:.1f} reviews/sec")
|
||||
log.info(f"{'='*60}\n")
|
||||
|
||||
return all_reviews
|
||||
|
||||
|
||||
def main():
|
||||
url = "https://www.google.com/maps/place/Soho+Club/data=!4m7!3m6!1s0x46dd947294b213bf:0x864c7a232527adb4!8m2!3d54.67869!4d25.2667181!16s%2Fg%2F1thhj5ml!19sChIJvxOylHKU3UYRtK0nJSN6TIY?authuser=0&hl=es&rclk=1"
|
||||
|
||||
scraper = HeaderCaptureScraper(url, headless=False)
|
||||
reviews = scraper.scrape_all()
|
||||
|
||||
if reviews:
|
||||
with open('header_capture_reviews.json', 'w', encoding='utf-8') as f:
|
||||
json.dump(reviews, f, indent=2, ensure_ascii=False)
|
||||
log.info(f"Saved to header_capture_reviews.json")
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Reference in New Issue
Block a user