import streamlit as st
import requests
from transformers import pipeline
from deepface import DeepFace
from PIL import Image
import torch
import torchvision.transforms as transforms
import cv2
import numpy as np
from bs4 import BeautifulSoup
import re

# Load Fake News Detection Model
fake_news_pipeline = pipeline("text-classification", model="mrm8488/bert-tiny-finetuned-fake-news-detection")

def classify_text(news_text):
    result = fake_news_pipeline(news_text)[0]
    label = result['label'].lower()
    score = result['score'] * 100  # Convert to percentage
    return ("Fake" if label == "fake" else "Real"), round(score, 2)

def analyze_image(image):
    try:
        result = DeepFace.analyze(image, actions=['emotion'], enforce_detection=False)
        return "Fake" if result[0]['dominant_emotion'] in ['disgust', 'fear', 'sad'] else "Real"
    except:
        return "Error in analyzing image."

def analyze_video(video_url):
    return "Video analysis feature coming soon!"

def verify_news(news_text):
    search_url = f"https://www.google.com/search?q={'+'.join(news_text.split())}"
    return search_url

def scrape_verification_links(news_text):
    sources = [
        "https://www.bbc.com/news",
        "https://www.cnn.com",
        "https://www.reuters.com",
        "https://factcheck.org",
        "https://www.snopes.com",
        "https://www.politifact.com"
    ]
    verification_links = {}
    for source in sources:
        try:
            response = requests.get(source)
            soup = BeautifulSoup(response.text, 'html.parser')
            for link in soup.find_all('a', href=True):
                if re.search(news_text[:5], link.text, re.IGNORECASE):
                    verification_links[link.text] = source + link['href']
        except:
            continue
    return verification_links

# Streamlit UI
st.set_page_config(page_title="Fake News Detector", layout="wide")
st.title("📰 Fake News Detector")

# Sidebar for Input Selection
st.sidebar.title("Select Input Type")
option = st.sidebar.radio("Choose an option", ["Text", "Image", "Video Link"])

# Input Section
if option == "Text":
    news_text = st.text_area("Enter the news content to check:", height=200)
    analyze_text_clicked = st.button("Analyze News")
    if analyze_text_clicked and news_text.strip():
        result, accuracy = classify_text(news_text)
        verification_links = scrape_verification_links(news_text)
        st.subheader("📊 Analysis Results")
        st.error(f"❌ This news is likely **Fake**! (Accuracy: {accuracy}%)") if result == "Fake" else st.success(f"✅ This news is likely **Real**! (Accuracy: {accuracy}%)")
        st.subheader("🔍 Verification & Trusted Sources")
        for title, link in verification_links.items():
            st.markdown(f"[🔗 {title}]({link})")
        st.markdown(f"[🔎 Verify on Google]({verify_news(news_text)})")

elif option == "Image":
    uploaded_image = st.file_uploader("Upload a news image", type=["jpg", "png", "jpeg"])
    analyze_image_clicked = st.button("Analyze Image")
    if uploaded_image and analyze_image_clicked:
        image = Image.open(uploaded_image)
        st.image(image, caption="Uploaded Image", use_column_width=True)
        result = analyze_image(np.array(image))
        st.error("❌ This image is likely **Fake**!") if result == "Fake" else st.success("✅ This image is likely **Real**!")

elif option == "Video Link":
    video_url = st.text_input("Enter the video link:")
    analyze_video_clicked = st.button("Analyze Video")
    if analyze_video_clicked and video_url.strip():
        st.video(video_url)
        result = analyze_video(video_url)
        st.info(result)