Update deliverable2.py

deliverable2.py

@@ -1,5 +1,6 @@
 import requests
 from bs4 import BeautifulSoup
+import pandas as pd
 from sentence_transformers import SentenceTransformer, util
 from transformers import pipeline
 
@@ -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")
@@ -81,7 +82,7 @@ class URLValidator:
 
     def rate_url_validity(self, user_query: str, url: str):
         """ Main function to evaluate the validity of a webpage. """ 
-        content = self.fetch_page_content(url)  # ✅ Properly indented and referenced with self
+        content = self.fetch_page_content(url)
 
         # Handle errors
         if "Error" in content:
@@ -115,3 +116,49 @@ class URLValidator:
             },
             "explanation": explanation
         }
+
+
+# **✅ Sample Queries and URLs (10 Each)**
+sample_queries = [
+    "How does climate change impact global weather?",
+    "What are the latest advancements in AI?",
+    "How does diet influence mental health?",
+    "What are the effects of space travel on astronauts?",
+    "Is cryptocurrency a safe investment?",
+    "What are the advantages of renewable energy?",
+    "How does deep learning work?",
+    "What are the health risks of 5G technology?",
+    "Is intermittent fasting effective for weight loss?",
+    "How do electric vehicles compare to gas cars?"
+]
+
+sample_urls = [
+    "https://www.nationalgeographic.com/environment/article/climate-change",
+    "https://www.technologyreview.com/2023/05/01/latest-ai-advancements/",
+    "https://www.health.harvard.edu/mind-and-mood/foods-linked-to-better-brainpower",
+    "https://www.nasa.gov/hrp/long-term-health-risks-of-space-travel",
+    "https://www.investopedia.com/terms/c/cryptocurrency.asp",
+    "https://www.energy.gov/eere/renewable-energy",
+    "https://www.ibm.com/cloud/deep-learning",
+    "https://www.who.int/news-room/questions-and-answers/item/radiation-5g-mobile-networks-and-health",
+    "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6167940/",
+    "https://www.tesla.com/blog/benefits-of-electric-vehicles"
+]
+
+# **✅ Running the Validator and Saving to CSV**
+validator = URLValidator()
+
+data_rows = []
+for query, url in zip(sample_queries, sample_urls):
+    result = validator.rate_url_validity(query, url)
+    func_rating = round(result["raw_score"]["Final Validity Score"] / 20)  # Convert 100-scale to 1-5
+    custom_rating = func_rating + 1 if func_rating < 5 else func_rating  # User-adjusted rating
+
+    data_rows.append([query, url, func_rating, custom_rating])
+
+# Save to CSV
+csv_filename = "url_validation_results.csv"
+df = pd.DataFrame(data_rows, columns=["user_prompt", "url_to_check", "func_rating", "custom_rating"])
+df.to_csv(csv_filename, index=False)
+
+print(f"✅ CSV file '{csv_filename}' has been created successfully!")