import gradio as gr
import json
import requests
from bs4 import BeautifulSoup

try:
    from sentence_transformers import SentenceTransformer, util
    from transformers import pipeline
    MODULES_AVAILABLE = True
except (ModuleNotFoundError, ImportError):
    print("Warning: Required ML modules are missing. Running in fallback mode.")
    MODULES_AVAILABLE = False

class URLValidator:
    def __init__(self):
        if MODULES_AVAILABLE:
            self.similarity_model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
            self.sentiment_analyzer = pipeline("text-classification", model="cardiffnlp/twitter-roberta-base-sentiment")
        else:
            self.similarity_model = None
            self.sentiment_analyzer = None

    def fetch_page_content(self, url):
        """Fetches webpage text content."""
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
        }
        try:
            response = requests.get(url, headers=headers, 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 "ERROR: Unable to fetch webpage content."

    def rate_url_validity(self, user_query, url):
        """Validates URL credibility."""
        content = self.fetch_page_content(url)
        if not content:
            return {
                "status": "error",
                "message": "ERROR: Failed to retrieve webpage content.",
                "suggestion": "Try another URL or check if the website blocks bots."
            }

        if not MODULES_AVAILABLE:
            return {
                "status": "warning",
                "message": "Machine learning models unavailable.",
                "suggestion": "Install necessary ML modules."
            }

        similarity_score = int(util.pytorch_cos_sim(
            self.similarity_model.encode(user_query),
            self.similarity_model.encode(content)
        ).item() * 100)

        sentiment_result = self.sentiment_analyzer(content[:512])[0]
        bias_score = 100 if sentiment_result["label"].upper() == "POSITIVE" else 50 if sentiment_result["label"].upper() == "NEUTRAL" else 30
        final_score = round((0.5 * similarity_score) + (0.5 * bias_score), 2)

        return {
            "Content Relevance Score": f"{similarity_score} / 100",
            "Bias Score": f"{bias_score} / 100",
            "Final Validity Score": f"{final_score} / 100"
        }

# Sample queries and URLs
sample_queries = [
    "What are the symptoms of the flu?",
    "How can I bake a chocolate cake step by step?",
    "Give a brief history of Ancient Rome.",
    "What are the side effects of ibuprofen?",
    "What are the best exercises for weight loss?",
    "How can I improve my sleep quality naturally?",
    "What are the latest advancements in AI?",
    "How should I prepare for a job interview effectively?",
    "Can you explain the theory of relativity in simple terms?",
    "What are some beginner-friendly programming languages for 2025?"
]

sample_urls = [
    "https://www.bbc.com/news/world-us-canada-64879434",
    "https://www.nytimes.com",
    "https://www.nature.com",
    "https://www.who.int/health-topics/coronavirus",
    "https://www.cdc.gov/flu/about/index.html",
    "https://www.nasa.gov/press-release/nasa-shares-stunning-new-images-of-galaxies",
    "https://en.wikipedia.org/wiki/Influenza",
    "https://www.python.org",
    "https://www.openai.com",
    "https://arxiv.org"
]

validator = URLValidator()

def validate_url(user_query, url):
    """Gradio function to validate URLs."""
    result = validator.rate_url_validity(user_query, url)
    return json.dumps(result, indent=2)

with gr.Blocks() as demo:
    gr.Markdown("# URL Credibility Validator")
    gr.Markdown("### Validate the credibility of any webpage using AI")

    user_query = gr.Dropdown(choices=sample_queries, label="Select a search query:")
    url_input = gr.Dropdown(choices=sample_urls, label="Select a URL to validate:")
    
    output = gr.Textbox(label="Validation Results")  
    
    validate_button = gr.Button("Validate URL")
    validate_button.click(validate_url, inputs=[user_query, url_input], outputs=output)

if __name__ == "__main__":
    demo.launch(server_name="0.0.0.0", server_port=7860)