app.py

import requests
from bs4 import BeautifulSoup
import pandas as pd
import gradio as gr
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import creds  # Assuming creds.py holds your API key as creds.api_key

# Step 1: Scrape the free courses from Analytics Vidhya
url = "https://courses.analyticsvidhya.com/pages/all-free-courses"
response = requests.get(url)
soup = BeautifulSoup(response.content, 'html.parser')

courses = []

# Extracting course title, image, and course link
for course_card in soup.find_all('header', class_='course-card__img-container'):
    img_tag = course_card.find('img', class_='course-card__img')
    
    if img_tag:
        title = img_tag.get('alt')
        image_url = img_tag.get('src')
        
        link_tag = course_card.find_previous('a')
        if link_tag:
            course_link = link_tag.get('href')
            if not course_link.startswith('http'):
                course_link = 'https://courses.analyticsvidhya.com' + course_link

            courses.append({
                'title': title,
                'image_url': image_url,
                'course_link': course_link
            })

# Step 2: Create DataFrame
df = pd.DataFrame(courses)

# Step 3: Text Processing for Improved Relevance
def preprocess_text(text):
    text = text.lower()
    text = text.replace("-", " ")
    return text

df['processed_title'] = df['title'].apply(preprocess_text)

# Step 4: Generate TF-IDF Vectors for Titles
vectorizer = TfidfVectorizer(stop_words='english')
tfidf_matrix = vectorizer.fit_transform(df['processed_title'])

def search_courses(query):
    # Process query and generate its TF-IDF vector
    processed_query = preprocess_text(query)
    query_vector = vectorizer.transform([processed_query])
    
    # Calculate cosine similarity
    similarities = cosine_similarity(query_vector, tfidf_matrix).flatten()
    df['relevance_score'] = similarities
    
    # Filter and sort courses based on relevance score
    relevant_courses = df[df['relevance_score'] >= 0.3].sort_values(by='relevance_score', ascending=False)
    results = []
    
    for _, course in relevant_courses.iterrows():
        results.append({
            'title': course['title'],
            'image_url': course['image_url'],
            'course_link': course['course_link'],
            'score': course['relevance_score']
        })
    
    return results[:10]

def gradio_search(query):
    result_list = search_courses(query)
    
    if result_list:
        html_output = '<div class="results-container">'
        for item in result_list:
            course_title = item['title']
            course_image = item['image_url']
            course_link = item['course_link']
            relevance_score = round(item['score'] * 100, 2)
            
            html_output += f'''
            <div class="course-card">
                <img src="{course_image}" alt="{course_title}" class="course-image"/>
                <div class="course-info">
                    <h3>{course_title}</h3>
                    <p>Relevance: {relevance_score}%</p>
                    <a href="{course_link}" target="_blank" class="course-link">View Course</a>
                </div>
            </div>'''
        html_output += '</div>'
        return html_output
    else:
        return '<p class="no-results">No results found. Please try a different query.</p>'

# Dark-themed CSS
custom_css = """
body {
    font-family: Arial, sans-serif;
    background-color: #121212;
    color: #E0E0E0;
}
.container {
    max-width: 800px;
    margin: 0 auto;
    padding: 20px;
    color: #E0E0E0;
}
.results-container {
    display: flex;
    flex-wrap: wrap;
    justify-content: space-between;
}
.course-card {
    background-color: #1E1E1E;
    border-radius: 8px;
    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.5);
    margin-bottom: 20px;
    overflow: hidden;
    width: 48%;
    transition: transform 0.2s;
}
.course-card:hover {
    transform: translateY(-5px);
}
.course-image {
    width: 100%;
    height: 150px;
    object-fit: cover;
}
.course-info {
    padding: 15px;
}
.course-info h3 {
    margin-top: 0;
    font-size: 18px;
    color: #E0E0E0;
}
.course-info p {
    color: #B0B0B0;
    font-size: 14px;
    margin-bottom: 10px;
}
.course-link {
    display: inline-block;
    background-color: #007bff;
    color: white;
    padding: 8px 12px;
    text-decoration: none;
    border-radius: 4px;
    font-size: 14px;
    transition: background-color 0.2s;
}
.course-link:hover {
    background-color: #0056b3;
}
.no-results {
    text-align: center;
    color: #B0B0B0;
    font-style: italic;
}
"""

# Gradio interface
iface = gr.Interface(
    fn=gradio_search,
    inputs=gr.Textbox(label="Enter your search query", placeholder="e.g., machine learning, data science, python"),
    outputs=gr.HTML(label="Search Results"),
    title="Analytics Vidhya Smart Course Search",
    description="Find the most relevant courses from Analytics Vidhya based on your query.",
    theme="huggingface",
    css=custom_css,
    examples=[
        ["machine learning for beginners"],
        ["advanced data visualization techniques"],
        ["python programming basics"], 
        ["Business Analytics"]
    ],
)

if __name__ == "__main__":
    iface.launch()