faa0704737
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>
97 lines
3.2 KiB
Python
97 lines
3.2 KiB
Python
#!/usr/bin/env python3
|
|
"""Quick test of API interceptor with manual response dumping"""
|
|
import json
|
|
import logging
|
|
import time
|
|
from pathlib import Path
|
|
from seleniumbase import SB
|
|
from modules.api_interceptor import GoogleMapsAPIInterceptor
|
|
|
|
# Set up logging
|
|
logging.basicConfig(level=logging.INFO, format="[%(levelname)s] %(message)s")
|
|
|
|
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"
|
|
|
|
print("[INFO] Starting browser with UC mode...")
|
|
with SB(uc=True, headless=False) as sb:
|
|
print("[INFO] Loading Google Maps page...")
|
|
sb.open(url)
|
|
sb.sleep(3)
|
|
|
|
# Inject interceptor EARLY
|
|
print("[INFO] Injecting API interceptor...")
|
|
interceptor = GoogleMapsAPIInterceptor(sb.driver)
|
|
interceptor.inject_response_interceptor()
|
|
sb.sleep(2)
|
|
|
|
# Click reviews tab
|
|
print("[INFO] Looking for reviews tab...")
|
|
try:
|
|
sb.click('.LRkQ2', timeout=5)
|
|
print("[INFO] Clicked reviews tab")
|
|
except Exception as e:
|
|
print(f"[WARN] Could not click reviews tab: {e}")
|
|
|
|
sb.sleep(5)
|
|
|
|
# Scroll to trigger API calls
|
|
print("[INFO] Scrolling to load reviews...")
|
|
for i in range(5):
|
|
sb.execute_script("window.scrollBy(0, 800)")
|
|
sb.sleep(2)
|
|
print(f" Scroll {i+1}/5...")
|
|
|
|
# Wait a bit more
|
|
print("[INFO] Waiting for API responses...")
|
|
sb.sleep(3)
|
|
|
|
# Get intercepted responses
|
|
responses = interceptor.get_intercepted_responses()
|
|
print(f"\n[SUCCESS] Captured {len(responses)} API responses!")
|
|
|
|
if not responses:
|
|
print("[WARN] No responses captured. Exiting.")
|
|
exit(0)
|
|
|
|
# Dump to files
|
|
output_dir = Path("debug_api_dump")
|
|
output_dir.mkdir(exist_ok=True)
|
|
|
|
for i, resp in enumerate(responses):
|
|
# Full response
|
|
resp_file = output_dir / f"response_{i}.json"
|
|
with open(resp_file, 'w', encoding='utf-8') as f:
|
|
json.dump(resp, f, indent=2, ensure_ascii=False)
|
|
|
|
# Just body
|
|
body_file = output_dir / f"response_{i}_body.txt"
|
|
with open(body_file, 'w', encoding='utf-8') as f:
|
|
f.write(resp.get('body', ''))
|
|
|
|
url_str = resp.get('url', 'unknown')
|
|
size = resp.get('size', len(resp.get('body', '')))
|
|
print(f"\n [{i}] {url_str[:80]}... ({size} bytes)")
|
|
print(f" Full: {resp_file}")
|
|
print(f" Body: {body_file}")
|
|
|
|
print(f"\n[SUCCESS] Dumped {len(responses)} responses to: {output_dir}/")
|
|
|
|
# Try to parse
|
|
print("\n[INFO] Attempting to parse reviews from responses...")
|
|
try:
|
|
parsed_reviews = interceptor.parse_reviews_from_responses(responses)
|
|
print(f"[INFO] Parsed {len(parsed_reviews)} reviews")
|
|
|
|
for i, review in enumerate(parsed_reviews[:5]):
|
|
print(f"\n Review {i+1}:")
|
|
print(f" ID: {review.review_id[:50] if review.review_id else 'N/A'}")
|
|
print(f" Author: {review.author}")
|
|
print(f" Rating: {review.rating}")
|
|
print(f" Text: {review.text[:80] if review.text else 'N/A'}...")
|
|
except Exception as e:
|
|
print(f"[ERROR] Failed to parse: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
|
|
print("\n[DONE]")
|