diff --git a/ai_ta_backend/crawlee_ext_scrape.py b/ai_ta_backend/crawlee_ext_scrape.py
index 0528332e..8c118db8 100644
--- a/ai_ta_backend/crawlee_ext_scrape.py
+++ b/ai_ta_backend/crawlee_ext_scrape.py
@@ -4,7 +4,7 @@
 
 SCRAPE_LOG = {}
 
-def crawlee_scrape(course_name: str, urls: list):
+def crawlee_scrape(course_name: str, urls: list, exclude_urls: list):
     """
     This function takes in a pre-defined set of URLs and scrapes the content from each URL.
     """
@@ -15,12 +15,12 @@ def crawlee_scrape(course_name: str, urls: list):
                 "url": "",
                 "scrapeStrategy": "equal-and-below",
                 "match": "",
-                "maxPagesToCrawl": 10000,
+                "maxPagesToCrawl": 15000,
                 "maxTokens": 2000000,
                 "maxConcurrency": 20,
                 "maxRequestsPerMinute": 120,
                 "courseName": course_name,
-                "exclude": ""
+                "exclude": exclude_urls
             }
     }
 
@@ -31,8 +31,7 @@ def crawlee_scrape(course_name: str, urls: list):
     for url in urls:
         payload["params"]["url"] = url
         payload["params"]["match"] = "http?(s)://" + url.split("//")[1] + "/**"
-        
-        
+
         print("Scraping URL:", url)
         start_time = time.monotonic()
         response = requests.post(api_endpoint, json=payload)
diff --git a/ai_ta_backend/main.py b/ai_ta_backend/main.py
index 31576561..8027b294 100644
--- a/ai_ta_backend/main.py
+++ b/ai_ta_backend/main.py
@@ -32,6 +32,7 @@
 from ai_ta_backend.web_scrape import WebScrape, mit_course_download
 from ai_ta_backend.crawlee_ext_scrape import crawlee_scrape
 
+
 # Sentry.io error logging
 sentry_sdk.init(
     dsn=os.getenv("SENTRY_DSN"),
@@ -692,7 +693,6 @@ def getTopContextsWithMQR() -> Response:
   response.headers.add('Access-Control-Allow-Origin', '*')
   return response
 
-
 @app.route('/extension-scrape', methods=['POST'])
 def extension_scrape() -> Response:
   """
@@ -701,12 +701,12 @@ def extension_scrape() -> Response:
   data = request.get_json()
   urls: List[str] = data.get('urls', [])
   course_name: str = data.get('course_name', '')
-
+  exclude_urls: List[str] = data.get('exclude_urls', [])
   if course_name == '' or urls == []:
     # proper web error "400 Bad request"
     abort(400, description=f"Missing required parameter: 'course_name' and 'urls' must be provided.")
   
-  result = crawlee_scrape(course_name, urls)
+  result = crawlee_scrape(course_name, urls, exclude_urls)
   response = jsonify(result)
   response.headers.add('Access-Control-Allow-Origin', '*')
   return response