Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import requests | |
| from transformers import pipeline | |
| from PIL import Image | |
| import torchvision.transforms as transforms | |
| import torch | |
| import cv2 | |
| import numpy as np | |
| # Load Fake News Detection Model | |
| fake_news_pipeline = pipeline("text-classification", model="roberta-base-openai-detector") | |
| # Function to classify text news | |
| 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) | |
| # Function to verify news with Google Fact Check API | |
| def verify_news(news_text): | |
| search_url = f"https://toolbox.google.com/factcheck/explorer/search/{'+'.join(news_text.split())}" | |
| return search_url | |
| # Function to analyze images for fake news | |
| def analyze_image(image): | |
| transform = transforms.Compose([transforms.Resize((224, 224)), transforms.ToTensor()]) | |
| image_tensor = transform(image).unsqueeze(0) | |
| # Convert to OpenCV format | |
| image_cv = np.array(image) | |
| image_cv = cv2.cvtColor(image_cv, cv2.COLOR_RGB2BGR) | |
| # Apply Fake Image Detection (Basic Example) | |
| edges = cv2.Canny(image_cv, 100, 200) | |
| edge_percentage = np.sum(edges) / (image_cv.shape[0] * image_cv.shape[1]) | |
| if edge_percentage > 0.1: | |
| return "❌ This image might be **manipulated** or **deepfake**!" | |
| else: | |
| return "✅ This image appears to be **authentic**." | |
| # Function to analyze video metadata | |
| def analyze_video(video_url): | |
| api_url = f"https://noembed.com/embed?url={video_url}" | |
| response = requests.get(api_url).json() | |
| if "title" in response: | |
| title = response["title"] | |
| source = response["provider_name"] | |
| return f"🎥 Video Title: {title}\n🔗 Source: {source}" | |
| else: | |
| return "❌ Unable to fetch video details! Check if the link is correct." | |
| # Streamlit UI | |
| st.set_page_config(page_title="Fake News Detector", layout="wide") | |
| st.title("📰 Fake News Detector") | |
| # Sidebar Navigation | |
| st.sidebar.title("Select Input Type") | |
| option = st.sidebar.radio("Choose an option", ["Text", "Image", "Video Link"]) | |
| # Input Sections | |
| col1, col2, col3 = st.columns(3) | |
| # Text Analysis Section | |
| with col1: | |
| st.subheader("📄 Text News Check") | |
| news_text = st.text_area("Enter the news content:", height=200) | |
| if st.button("Analyze News"): | |
| if not news_text.strip(): | |
| st.warning("Please enter some text.") | |
| else: | |
| result, accuracy = classify_text(news_text) | |
| verification_link = verify_news(news_text) | |
| if result == "Fake": | |
| st.error(f"❌ Likely **Fake News**! (Confidence: {accuracy}%)") | |
| else: | |
| st.success(f"✅ Likely **Real News**! (Confidence: {accuracy}%)") | |
| st.markdown(f"[🔎 Verify on Google Fact Check]({verification_link})") | |
| # Image Upload Section | |
| with col2: | |
| st.subheader("🖼️ Image News Check") | |
| uploaded_image = st.file_uploader("Upload a news image", type=["jpg", "png", "jpeg"]) | |
| if uploaded_image and st.button("Analyze Image"): | |
| image = Image.open(uploaded_image) | |
| st.image(image, caption="Uploaded Image", use_column_width=True) | |
| result = analyze_image(image) | |
| st.info(result) | |
| # Video Link Section | |
| with col3: | |
| st.subheader("🎥 Video News Check") | |
| video_url = st.text_input("Enter the video link:") | |
| if st.button("Analyze Video"): | |
| if not video_url.strip(): | |
| st.warning("Please enter a valid video link.") | |
| else: | |
| st.video(video_url) | |
| result = analyze_video(video_url) | |
| st.info(result) | |