app.py

# app.py
import gradio as gr
import requests
from bs4 import BeautifulSoup
from transformers import pipeline
import PyPDF2
import docx
import os
from typing import List, Tuple, Optional
from smolagents import CodeAgent, HfApiModel, Tool

class ContentAnalyzer:
    def __init__(self):
        # Initialize models
        self.summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
        self.sentiment_analyzer = pipeline("sentiment-analysis")
        self.zero_shot = pipeline("zero-shot-classification")
        
    def read_file(self, file_obj) -> str:
        """Read content from different file types."""
        if file_obj is None:
            return ""
            
        file_ext = os.path.splitext(file_obj.name)[1].lower()
        
        try:
            if file_ext == '.txt':
                return file_obj.read().decode('utf-8')
                
            elif file_ext == '.pdf':
                pdf_reader = PyPDF2.PdfReader(file_obj)
                text = ""
                for page in pdf_reader.pages:
                    text += page.extract_text() + "\n"
                return text
                
            elif file_ext == '.docx':
                doc = docx.Document(file_obj)
                return "\n".join([paragraph.text for paragraph in doc.paragraphs])
                
            else:
                return f"Unsupported file type: {file_ext}"
                
        except Exception as e:
            return f"Error reading file: {str(e)}"

    def fetch_web_content(self, url: str) -> str:
        """Fetch content from URL."""
        try:
            response = requests.get(url, timeout=10)
            response.raise_for_status()
            soup = BeautifulSoup(response.text, 'html.parser')
            
            # Remove scripts and styles
            for script in soup(["script", "style"]):
                script.decompose()
            
            text = soup.get_text(separator='\n')
            lines = (line.strip() for line in text.splitlines())
            return "\n".join(line for line in lines if line)
            
        except Exception as e:
            return f"Error fetching URL: {str(e)}"

    def analyze_content(self, 
                       text: Optional[str] = None,
                       url: Optional[str] = None,
                       file: Optional[object] = None,
                       analysis_types: List[str] = ["summarize"]) -> dict:
        """Analyze content from text, URL, or file."""
        try:
            # Get content from appropriate source
            if url:
                content = self.fetch_web_content(url)
            elif file:
                content = self.read_file(file)
            else:
                content = text or ""

            if not content or content.startswith("Error"):
                return {"error": content or "No content provided"}

            results = {
                "original_text": content[:1000] + "..." if len(content) > 1000 else content
            }

            # Perform requested analyses
            if "summarize" in analysis_types:
                summary = self.summarizer(content[:1024], max_length=130, min_length=30)
                results["summary"] = summary[0]['summary_text']

            if "sentiment" in analysis_types:
                sentiment = self.sentiment_analyzer(content[:512])
                results["sentiment"] = {
                    "label": sentiment[0]['label'],
                    "score": round(sentiment[0]['score'], 3)
                }

            if "topics" in analysis_types:
                topics = self.zero_shot(
                    content[:512],
                    candidate_labels=["technology", "science", "business", 
                                    "politics", "entertainment", "education", 
                                    "health", "sports"]
                )
                results["topics"] = [
                    {"label": label, "score": round(score, 3)}
                    for label, score in zip(topics['labels'], topics['scores'])
                    if score > 0.1
                ]

            return results

        except Exception as e:
            return {"error": f"Analysis error: {str(e)}"}

def create_interface():
    analyzer = ContentAnalyzer()
    
    with gr.Blocks(title="Content Analyzer") as demo:
        gr.Markdown("# 📑 Content Analyzer")
        gr.Markdown("Analyze text content from various sources using AI.")
        
        with gr.Tabs():
            # Text Input Tab
            with gr.Tab("Text Input"):
                text_input = gr.Textbox(
                    label="Enter Text",
                    placeholder="Paste your text here...",
                    lines=5
                )
                
            # URL Input Tab
            with gr.Tab("Web URL"):
                url_input = gr.Textbox(
                    label="Enter URL",
                    placeholder="https://example.com"
                )
                
            # File Upload Tab
            with gr.Tab("File Upload"):
                file_input = gr.File(
                    label="Upload File",
                    file_types=[".txt", ".pdf", ".docx"]
                )
        
        # Analysis Options
        analysis_types = gr.CheckboxGroup(
            choices=["summarize", "sentiment", "topics"],
            value=["summarize"],
            label="Analysis Types"
        )
        
        analyze_btn = gr.Button("Analyze", variant="primary")
        
        # Output Sections
        with gr.Tabs():
            with gr.Tab("Original Text"):
                original_text = gr.Markdown()
            with gr.Tab("Summary"):
                summary_output = gr.Markdown()
            with gr.Tab("Sentiment"):
                sentiment_output = gr.Markdown()
            with gr.Tab("Topics"):
                topics_output = gr.Markdown()
        
        def process_analysis(text, url, file, types):
            # Get analysis results
            results = analyzer.analyze_content(text, url, file, types)
            
            if "error" in results:
                return results["error"], "", "", ""
            
            # Format outputs
            original = results.get("original_text", "")
            summary = results.get("summary", "")
            
            sentiment = ""
            if "sentiment" in results:
                sent = results["sentiment"]
                sentiment = f"**Sentiment:** {sent['label']} (Confidence: {sent['score']})"
            
            topics = ""
            if "topics" in results:
                topics = "**Detected Topics:**\n" + "\n".join([
                    f"- {t['label']}: {t['score']}"
                    for t in results["topics"]
                ])
            
            return original, summary, sentiment, topics
        
        # Connect the interface
        analyze_btn.click(
            fn=process_analysis,
            inputs=[text_input, url_input, file_input, analysis_types],
            outputs=[original_text, summary_output, sentiment_output, topics_output]
        )
    
    return demo

# Launch the app
if __name__ == "__main__":
    demo = create_interface()
    demo.launch()