Upload Deliverable2.py

Deliverable2.py

@@ -0,0 +1,101 @@
+# -*- coding: utf-8 -*-
+"""Untitled2.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1UPM7vEPoqKmrXRZqw6b0A2nri9S6mawa
+"""
+
+import requests
+from bs4 import BeautifulSoup
+from sentence_transformers import SentenceTransformer, util
+from transformers import pipeline
+
+class URLValidator:
+    def __init__(self):
+        self.similarity_model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
+        self.fake_news_classifier = pipeline("text-classification", model="mrm8488/bert-tiny-finetuned-fake-news-detection")
+        self.sentiment_analyzer = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-sentiment")
+
+    def fetch_page_content(self, url: str) -> str:
+        try:
+            response = requests.get(url, timeout=10)
+            response.raise_for_status()
+            soup = BeautifulSoup(response.text, "html.parser")
+            return " ".join([p.text for p in soup.find_all("p")])
+        except requests.RequestException:
+            return ""
+
+    def compute_similarity_score(self, user_query: str, content: str) -> int:
+        if not content:
+            return 0
+        return int(util.pytorch_cos_sim(self.similarity_model.encode(user_query), self.similarity_model.encode(content)).item() * 100)
+
+    def detect_bias(self, content: str) -> int:
+        if not content:
+            return 50
+        sentiment_result = self.sentiment_analyzer(content[:512])[0]
+        return 100 if sentiment_result["label"] == "POSITIVE" else 50 if sentiment_result["label"] == "NEUTRAL" else 30
+
+    def rate_url_validity(self, user_query: str, url: str) -> dict:
+        content = self.fetch_page_content(url)
+        similarity_score = self.compute_similarity_score(user_query, content)
+        bias_score = self.detect_bias(content)
+        return {
+            "Query": user_query,
+            "URL": url,
+            "Content Relevance": similarity_score,
+            "Bias Score": bias_score,
+        }
+
+queries_urls = [
+    ("Climate change effects", "https://www.nationalgeographic.com/environment/article/climate-change-overview"),
+    ("COVID-19 vaccine effectiveness", "https://www.cdc.gov/coronavirus/2019-ncov/vaccines/effectiveness.html"),
+    ("Latest AI advancements", "https://www.technologyreview.com/topic/artificial-intelligence"),
+    ("Stock market trends", "https://www.bloomberg.com/markets"),
+    ("Healthy diet tips", "https://www.healthline.com/nutrition/healthy-eating-tips"),
+    ("Space exploration missions", "https://www.nasa.gov/missions"),
+    ("Electric vehicle benefits", "https://www.tesla.com/benefits"),
+    ("History of the internet", "https://www.history.com/topics/inventions/history-of-the-internet"),
+    ("Python programming tutorials", "https://realpython.com"),
+    ("Mental health awareness", "https://www.who.int/news-room/fact-sheets/detail/mental-health-strengthening-our-response")
+]
+
+validator = URLValidator()
+results = [validator.rate_url_validity(query, url) for query, url in queries_urls]
+
+for result in results:
+    print(result)
+
+# Generate formatted output for the 10 predefined queries and URLs
+queries_urls = [
+    ("Climate change effects", "https://www.nationalgeographic.com/environment/article/climate-change-overview"),
+    ("COVID-19 vaccine effectiveness", "https://www.cdc.gov/coronavirus/2019-ncov/vaccines/effectiveness.html"),
+    ("Latest AI advancements", "https://www.technologyreview.com/topic/artificial-intelligence"),
+    ("Stock market trends", "https://www.bloomberg.com/markets"),
+    ("Healthy diet tips", "https://www.healthline.com/nutrition/healthy-eating-tips"),
+    ("Space exploration missions", "https://www.nasa.gov/missions"),
+    ("Electric vehicle benefits", "https://www.tesla.com/benefits"),
+    ("History of the internet", "https://www.history.com/topics/inventions/history-of-the-internet"),
+    ("Python programming tutorials", "https://realpython.com"),
+    ("Mental health awareness", "https://www.who.int/news-room/fact-sheets/detail/mental-health-strengthening-our-response")
+]
+
+# Placeholder function ratings for demonstration
+import random
+
+formatted_output = []
+
+for query, url in queries_urls:
+    output_entry = {
+        "Query": query,
+        "URL": url,
+        "Function Rating": random.randint(1, 5),  # Simulated rating
+        "Custom Rating": random.randint(1, 5)  # Simulated rating
+    }
+    formatted_output.append(output_entry)
+
+# Display the formatted output
+formatted_output
+