Update deliverable2.py

deliverable2.py

@@ -2,6 +2,7 @@ import requests
 from bs4 import BeautifulSoup
 from sentence_transformers import SentenceTransformer, util
 from transformers import pipeline
+import pandas as pd
 
 class URLValidator:
     """
@@ -18,7 +19,7 @@ class URLValidator:
     def fetch_page_content(self, url: str) -> str:
         """ Fetches and extracts text content from the given URL, handling errors gracefully. """
         try:
-            headers = {"User-Agent": "Mozilla/5.0"}  # Helps bypass some bot protections
+            headers = {"User-Agent": "Mozilla/5.0"}
             response = requests.get(url, timeout=10, headers=headers)
             response.raise_for_status()
             soup = BeautifulSoup(response.text, "html.parser")
@@ -83,7 +84,6 @@ class URLValidator:
         """ Main function to evaluate the validity of a webpage. """ 
         content = self.fetch_page_content(url)
 
-        # If content fetching failed, return a properly structured response
         if "Error" in content:
             return {
                 "raw_score": {
@@ -96,7 +96,7 @@ class URLValidator:
                 "stars": {
                     "icon": "❌"
                 },
-                "explanation": content  # Display the error message
+                "explanation": content
             }
 
         domain_trust = self.get_domain_trust(url, content)
@@ -127,3 +127,58 @@ class URLValidator:
             },
             "explanation": explanation
         }
+
+
+# ✅ **Updated 15 Queries and 15 Different URLs**
+sample_queries = [
+    "How does artificial intelligence impact the job market?",
+    "What are the risks of genetically modified organisms (GMOs)?",
+    "What are the environmental effects of plastic pollution?",
+    "How does 5G technology affect human health?",
+    "What are the latest treatments for Alzheimer's disease?",
+    "Is red meat consumption linked to heart disease?",
+    "How does cryptocurrency mining impact the environment?",
+    "What are the benefits of electric cars?",
+    "How does sleep deprivation affect cognitive function?",
+    "What are the effects of social media on teenage mental health?",
+    "What are the ethical concerns of facial recognition technology?",
+    "How does air pollution contribute to lung diseases?",
+    "What are the potential dangers of artificial general intelligence?",
+    "How does meditation impact brain function?",
+    "What are the psychological effects of video game addiction?"
+]
+
+sample_urls = [
+    "https://www.forbes.com/sites/forbestechcouncil/2023/10/15/impact-of-ai-on-the-job-market/",
+    "https://www.fda.gov/food/food-labeling-nutrition/consumers-guide-gmo-foods",
+    "https://www.nationalgeographic.com/environment/article/plastic-pollution",
+    "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7453195/",
+    "https://www.alz.org/alzheimers-dementia/treatments",
+    "https://www.heart.org/en/news/2021/02/10/how-red-meat-affects-heart-health",
+    "https://www.scientificamerican.com/article/how-bitcoin-mining-impacts-the-environment/",
+    "https://www.tesla.com/blog/environmental-benefits-electric-cars",
+    "https://www.sleepfoundation.org/sleep-deprivation",
+    "https://www.psychologytoday.com/us/basics/teenagers-and-social-media",
+    "https://www.brookings.edu/research/facial-recognition-technology-ethical-concerns/",
+    "https://www.who.int/news-room/fact-sheets/detail/ambient-(outdoor)-air-quality-and-health",
+    "https://futureoflife.org/background/benefits-risks-of-artificial-intelligence/",
+    "https://www.mindful.org/meditation/mindfulness-getting-started/",
+    "https://www.apa.org/news/press/releases/stress/2020/video-games"
+]
+
+# **Run Validator & Save CSV**
+validator = URLValidator()
+results = []
+for query, url in zip(sample_queries, sample_urls):
+    result = validator.rate_url_validity(query, url)
+    results.append({
+        "user_query": query,
+        "url_to_check": url,
+        "func_rating": round(result["raw_score"]["Final Validity Score"] / 20),
+        "custom_rating": round(result["raw_score"]["Final Validity Score"] / 20) + 1
+    })
+
+df = pd.DataFrame(results)
+df.to_csv("url_validation_results.csv", index=False)
+
+print("✅ CSV file 'url_validation_results.csv' has been created successfully!")