Update request headers in scraper.py for improved compatibility

- Modify User-Agent to reflect a Windows environment for better request handling
- Simplify headers by removing unnecessary fields while retaining essential ones
- Enhance scraping reliability by ensuring headers mimic a typical browser request

Author: Adriano Sanges

real-estate-etl/scraper.py

@@ -15,16 +15,8 @@ def parse_price(price_str):
 
 def parse_page(url: str) -> Dict[str, Optional[any]]:
     headers = {
-        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36',
-        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
-        'Accept-Language': 'en-US,en;q=0.9',
-        'Accept-Encoding': 'gzip, deflate, br',
-        'Connection': 'keep-alive',
-        'Upgrade-Insecure-Requests': '1',
-        'Sec-Fetch-Dest': 'document',
-        'Sec-Fetch-Mode': 'navigate',
-        'Sec-Fetch-Site': 'none',
-        'Sec-Fetch-User': '?1',
+         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
+        "Accept-Language": "en-US,en;q=0.9"
     }
     logging.debug("Parsing page: %s", url)
     response = requests.get(url, headers=headers)