Update extract_text.py to include User-Agent header in PDF download requests

extract_text.py

@@ -6,10 +6,10 @@ def download_pdf(url, id):
     id = id.replace("/", "-")
     directory = "downloads"
     os.makedirs(directory, exist_ok=True)
-    file_path = os.path.join(directory, f"{id}.pdf")  # Use a unique name based on id
+    file_path = os.path.join(directory, f"{id}.pdf")
     try:
-        response = requests.get(url)
-        response.raise_for_status()  # Raise an error for bad responses
+        response = requests.get(url, headers={"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"})
+        response.raise_for_status()
         with open(file_path, "wb") as file:
             file.write(response.content)
     except Exception as e: