From c30561bc896e964b9d0c17c22cd5e892c7a0315e Mon Sep 17 00:00:00 2001
From: adish-rmr <adish@hotmail.it>
Date: Mon, 8 Dec 2025 12:23:27 +0100
Subject: [PATCH] update fix masking agent scraper

---
 src/pif_compiler/functions/common_func.py | 56 +++++++++++++++++++++--
 1 file changed, 52 insertions(+), 4 deletions(-)

diff --git a/src/pif_compiler/functions/common_func.py b/src/pif_compiler/functions/common_func.py
index 8cb8683..0145e4e 100644
--- a/src/pif_compiler/functions/common_func.py
+++ b/src/pif_compiler/functions/common_func.py
@@ -26,10 +26,58 @@ async def generate_pdf(link: str, name: str):
 
     try:
         async with async_playwright() as p:
-            browser = await p.chromium.launch()
-            page = await browser.new_page()
-            await page.goto(link, wait_until='networkidle')
-            await page.pdf(path=pdf_path)
+            # Launch browser with stealth options to bypass WAF
+            browser = await p.chromium.launch(
+                headless=True,
+                args=[
+                    '--disable-blink-features=AutomationControlled',
+                    '--disable-dev-shm-usage',
+                    '--no-sandbox',
+                    '--disable-setuid-sandbox',
+                ]
+            )
+
+            # Create context with realistic browser fingerprint
+            context = await browser.new_context(
+                viewport={'width': 1920, 'height': 1080},
+                user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+                locale='en-US',
+                timezone_id='Europe/Rome',
+                extra_http_headers={
+                    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
+                    'Accept-Encoding': 'gzip, deflate, br',
+                    'Accept-Language': 'en-US,en;q=0.9,it;q=0.8',
+                    'Cache-Control': 'max-age=0',
+                    'Sec-Ch-Ua': '"Chromium";v="131", "Not_A Brand";v="24"',
+                    'Sec-Ch-Ua-Mobile': '?0',
+                    'Sec-Ch-Ua-Platform': '"Windows"',
+                    'Sec-Fetch-Dest': 'document',
+                    'Sec-Fetch-Mode': 'navigate',
+                    'Sec-Fetch-Site': 'none',
+                    'Sec-Fetch-User': '?1',
+                    'Upgrade-Insecure-Requests': '1',
+                }
+            )
+
+            page = await context.new_page()
+
+            # Remove webdriver property to avoid detection
+            await page.add_init_script("""
+                Object.defineProperty(navigator, 'webdriver', {
+                    get: () => undefined
+                });
+            """)
+
+            # Navigate to the page
+            await page.goto(link, wait_until='networkidle', timeout=60000)
+
+            # Wait a bit to ensure everything is loaded
+            await page.wait_for_timeout(2000)
+
+            # Generate PDF
+            await page.pdf(path=pdf_path, format='A4', print_background=True)
+
+            await context.close()
             await browser.close()
 
         if os.path.exists(pdf_path):