Create app.py

app.py

@@ -0,0 +1,146 @@
+import json
+import numpy as np
+from sentence_transformers import SentenceTransformer, util
+import gradio as gr
+import requests
+from bs4 import BeautifulSoup
+import time
+import torch
+import traceback
+
+# Extended sample data with business analyst courses
+SAMPLE_COURSES = [
+    {
+        "title": "Business Analysis and Process Management Specialization",
+        "description": "Learn core business analysis skills, process mapping, and improvement techniques for organizational efficiency.",
+        "link": "https://www.coursera.org/specializations/business-analysis-process-management",
+        "source": "coursera"
+    },
+    {
+        "title": "Business Analytics Fundamentals",
+        "description": "Master data-driven decision making, Excel, SQL, and visualization tools for business analysis.",
+        "link": "https://www.udemy.com/course/business-analytics-fundamentals",
+        "source": "udemy"
+    },
+    {
+        "title": "Agile Business Analysis Professional",
+        "description": "Learn agile methodologies, user stories, and modern BA practices for software projects.",
+        "link": "https://www.coursera.org/professional-certificates/agile-business-analysis",
+        "source": "coursera"
+    },
+    # Original sample courses...
+    {
+        "title": "Python Programming for Beginners",
+        "description": "Learn Python from scratch. Covers basic concepts, data structures, and programming fundamentals.",
+        "link": "https://www.udemy.com/course/python-for-beginners",
+        "source": "udemy"
+    },
+    {
+        "title": "Machine Learning Specialization",
+        "description": "Comprehensive machine learning course covering supervised learning, neural networks, and practical ML projects.",
+        "link": "https://www.coursera.org/specializations/machine-learning",
+        "source": "coursera"
+    }
+]
+
+def scrape_courses(query):
+    """
+    Scrape courses based on search query from multiple sources
+    """
+    courses = []
+    
+    # Udemy API endpoint (you would need to register for API access)
+    udemy_url = f"https://www.udemy.com/api-2.0/courses/?search={query}&price=price-free"
+    
+    # Coursera API endpoint (you would need to register for API access)
+    coursera_url = f"https://api.coursera.org/api/courses.v1?q=search&query={query}&includes=free"
+    
+    try:
+        # Here you would implement the actual API calls
+        # For now, we'll filter the sample courses based on the query
+        query_terms = query.lower().split()
+        for course in SAMPLE_COURSES:
+            if any(term in course['title'].lower() or term in course['description'].lower() 
+                  for term in query_terms):
+                courses.append(course)
+        
+        return courses
+    except Exception as e:
+        print(f"Error scraping courses: {e}")
+        return []
+
+def search_courses(query):
+    if not query.strip():
+        return "Please enter a search query."
+
+    try:
+        # Get relevant courses based on the query
+        relevant_courses = scrape_courses(query)
+        
+        if not relevant_courses:
+            return "No courses found for your search query."
+            
+        # Initialize the model
+        device = torch.device('cpu')
+        model = SentenceTransformer("all-MiniLM-L6-v2")
+        model = model.to(device)
+        
+        # Generate embeddings
+        course_descriptions = [f"{course['title']} {course['description']}" for course in relevant_courses]
+        course_embeddings = model.encode(course_descriptions, convert_to_tensor=True)
+        
+        # Generate query embedding
+        query_embedding = model.encode(f"course about {query}", convert_to_tensor=True)
+        
+        # Calculate similarities
+        similarities = util.pytorch_cos_sim(query_embedding, course_embeddings)[0]
+        top_indices = np.argsort((-similarities).numpy())[:5]
+        
+        results = []
+        for idx in top_indices:
+            similarity_score = similarities[idx].item()
+            course = relevant_courses[idx]
+            results.append({
+                "Title": course["title"],
+                "Description": course["description"],
+                "Link": course["link"],
+                "Source": course["source"],
+                "Relevance": f"{similarity_score:.2%}"
+            })
+        
+        return results
+    except Exception as e:
+        print(f"Search error: {str(e)}")
+        traceback.print_exc()
+        return []
+
+def search_interface(query):
+    try:
+        print(f"\nSearching for: {query}")
+        results = search_courses(query)
+        
+        if isinstance(results, str):
+            return results
+        if not results:
+            return "No matching courses found. Please try a different search term."
+            
+        display_text = "\n\n".join(
+            [f"**Title**: {result['Title']}\n\n**Description**: {result['Description']}\n\n**Source:** {result['Source']}\n\n**Relevance:** {result['Relevance']}\n\n[Go to course]({result['Link']})" 
+             for result in results]
+        )
+        return display_text
+    except Exception as e:
+        traceback.print_exc()
+        return f"An error occurred: {str(e)}"
+
+# Create and launch the Gradio interface
+iface = gr.Interface(
+    fn=search_interface,
+    inputs="text",
+    outputs="markdown",
+    title="Free Course Search Engine",
+    description="Enter a topic or keywords to find relevant free courses from Udemy and Coursera.",
+    examples=["Python", "Business Analyst", "Data Science", "Web Development"]
+)
+
+iface.launch(share=True)