Update app.py

app.py

@@ -3,16 +3,20 @@ from swarm import Swarm, Agent
 from bs4 import BeautifulSoup
 import requests
 import os
+import json
+from io import BytesIO
+from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
 
 # Function to fetch OpenAI API key
 def fetch_openai_api_key():
-    """Fetch the OpenAI API key from Hugging Face secrets."""
+    """Fetch the OpenAI API key from Streamlit secrets."""
     try:
         secret_key = st.secrets.get("OPENAI_API_KEY", "")
         if secret_key:
             os.environ['OPENAI_API_KEY'] = secret_key
         else:
-            st.warning("⚠️ OpenAI API Key is missing! Please check your Hugging Face secrets configuration.")
+            st.warning("⚠️ OpenAI API Key is missing! Please check your secrets configuration.")
     except Exception as e:
         st.error(f"Error retrieving OpenAI API Key: {str(e)}")
 
@@ -27,73 +31,60 @@ def scrape_website(url):
         response = requests.get(url)
         response.raise_for_status()
         soup = BeautifulSoup(response.text, 'html.parser')
-        return soup.get_text()  # Return the text content from the HTML
+
+        # Extract metadata
+        metadata = {
+            "title": soup.title.string if soup.title else "N/A",
+            "description": soup.find("meta", {"name": "description"})["content"] if soup.find("meta", {"name": "description"}) else "N/A",
+            "keywords": soup.find("meta", {"name": "keywords"})["content"] if soup.find("meta", {"name": "keywords"}) else "N/A",
+        }
+
+        text_content = soup.get_text()  # Extract text content
+        return {"text": text_content, "metadata": metadata}
     except requests.exceptions.RequestException as e:
         return f"Error during scraping: {str(e)}"
 
-# Scraper Agent
-scraper_agent = Agent(
-    name="Scraper Agent",
-    instructions="You are an agent that scrapes content from websites.",
-    functions=[scrape_website]
-)
-
-# Define the analysis function
+# Enhanced summarization function
 def analyze_content(content):
     """Analyzes the scraped content for key points."""
-    summary = f"Summary of content: {content[:200]}..."  # A simple placeholder summarization
+    summary = f"Summary of content: {content[:500]}..."  
     return summary
 
-# Research Agent
-research_agent = Agent(
-    name="Research Agent",
-    instructions="You are an agent that analyzes content and extracts key insights.",
-    functions=[analyze_content]
-)
-
 # Define the writing function
 def write_summary(context_variables):
     """Writes a summary based on the analysis."""
     analysis = context_variables.get('analysis', '')
-    summary = f"Here's a detailed report based on the research: {analysis}"
-    return summary
-
-# Writer Agent
-writer_agent = Agent(
-    name="Writer Agent",
-    instructions="You are an agent that writes summaries of research.",
-    functions=[write_summary]
-)
-
-# Orchestrate the workflow
-def orchestrate_workflow(client, url):
-    # Step 1: Scrape the website
-    scrape_result = client.run(
-        agent=scraper_agent,
-        messages=[{"role": "user", "content": f"Scrape the following website: {url}"}]
+    metadata = context_variables.get('metadata', {})
+
+    detailed_report = (
+        f"### Metadata:\n"
+        f"**Title:** {metadata.get('title')}\n"
+        f"**Description:** {metadata.get('description')}\n"
+        f"**Keywords:** {metadata.get('keywords')}\n\n"
+        f"### Content Summary:\n{analysis}"
     )
-    scraped_content = scrape_result.messages[-1]["content"]
-
-    # Check for any error during scraping
-    if "Error during scraping" in scraped_content:
-        return scraped_content
-
-    # Step 2: Analyze the scraped content
-    research_result = client.run(
-        agent=research_agent,
-        messages=[{"role": "user", "content": f"Analyze the following content: {scraped_content}"}]
-    )
-    analysis_summary = research_result.messages[-1]["content"]
-
-    # Step 3: Write the summary based on the analysis
-    writer_result = client.run(
-        agent=writer_agent,
-        messages=[{"role": "user", "content": f"Write a summary based on this analysis: {analysis_summary}"}],
-        context_variables={"analysis": analysis_summary}
-    )
-
-    final_summary = writer_result.messages[-1]["content"]
-    return final_summary
+    return detailed_report
+
+# Generate PDF report
+def generate_pdf(report):
+    """Generate a PDF file from the report."""
+    buffer = BytesIO()
+    pdf_canvas = canvas.Canvas(buffer, pagesize=letter)
+    pdf_canvas.drawString(100, 750, "Web Content Analyzer Report")
+    pdf_canvas.drawString(100, 735, "-" * 50)
+    
+    lines = report.split('\n')
+    y = 700  # Start position for the text
+    for line in lines:
+        if y < 50:  # Create a new page if content exceeds one page
+            pdf_canvas.showPage()
+            y = 750
+        pdf_canvas.drawString(100, y, line)
+        y -= 15
+    
+    pdf_canvas.save()
+    buffer.seek(0)
+    return buffer
 
 # Streamlit App UI
 st.markdown(
@@ -108,15 +99,11 @@ st.markdown(
     unsafe_allow_html=True,
 )
 
-st.markdown('<div class="title">🔎 Swarm-based Web Content Analyzer</div>', unsafe_allow_html=True)
-st.markdown('<div class="description">Effortlessly extract, analyze, and summarize web content.</div>', unsafe_allow_html=True)
-
-st.write("")
-st.write("")
+st.markdown('<div class="title">🔎 Multi-Agent Web Content Analyzer</div>', unsafe_allow_html=True)
+st.markdown('<div class="description">Extract, analyze, and summarize web content with advanced capabilities.</div>', unsafe_allow_html=True)
 
 fetch_openai_api_key()
 
-# Initialize Swarm client only after API key is set
 if 'OPENAI_API_KEY' in os.environ and os.environ['OPENAI_API_KEY']:
     client = initialize_swarm_client()
 
@@ -125,20 +112,55 @@ if 'OPENAI_API_KEY' in os.environ and os.environ['OPENAI_API_KEY']:
     url = st.text_input("Enter the URL of the website you want to scrape", placeholder="https://example.com")
 
     # Run Workflow button
-    st.write("")
-
     if st.button("Run Workflow"):
         if url:
             with st.spinner("Running the multi-agent workflow... This may take a moment."):
-                final_report = orchestrate_workflow(client, url)
-            st.success("✅ Workflow complete!")
-            st.write("### 📜 Final Report:")
-            st.write(final_report)
+                scrape_result = scrape_website(url)
+                if isinstance(scrape_result, str):  # Error handling
+                    st.error(scrape_result)
+                else:
+                    content = scrape_result["text"]
+                    metadata = scrape_result["metadata"]
+
+                    # Analysis and writing
+                    analysis_summary = analyze_content(content)
+                    final_summary = write_summary({
+                        "analysis": analysis_summary,
+                        "metadata": metadata,
+                    })
+
+                    st.success("✅ Workflow complete!")
+                    st.write("### 📜 Final Report:")
+                    st.markdown(final_summary, unsafe_allow_html=True)
+
+                    # Prepare downloadable content
+                    report_file_json = json.dumps({
+                        "metadata": metadata,
+                        "summary": analysis_summary
+                    }, indent=4)
+                    report_file_txt = final_summary
+                    report_file_pdf = generate_pdf(final_summary)
+
+                    # Download options
+                    st.download_button(
+                        label="Download Report as JSON",
+                        data=report_file_json,
+                        file_name="report.json",
+                        mime="application/json"
+                    )
+                    st.download_button(
+                        label="Download Report as TXT",
+                        data=report_file_txt,
+                        file_name="report.txt",
+                        mime="text/plain"
+                    )
+                    st.download_button(
+                        label="Download Report as PDF",
+                        data=report_file_pdf,
+                        file_name="report.pdf",
+                        mime="application/pdf"
+                    )
         else:
             st.error("❌ Please enter a valid URL.")
 else:
-    st.sidebar.warning("⚠️ OpenAI API Key not set. Please check your Hugging Face secrets configuration.")
-
-# Footer with credits
-st.divider()
-st.markdown('<div class="ack">Acknowledgement: </div>', unsafe_allow_html=True)
+    st.sidebar.warning("⚠️ OpenAI API Key not set. Please check your secrets configuration.")