Update app.py

app.py

@@ -2,39 +2,45 @@ import requests
 from bs4 import BeautifulSoup
 import pandas as pd
 import gradio as gr
-import os
 from groq import Groq
 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')
+def scrape_courses():
+    url = "https://courses.analyticsvidhya.com/pages/all-free-courses"
+    try:
+        response = requests.get(url)
+        response.raise_for_status()  # Raise an error for bad status codes
+    except requests.RequestException as e:
+        print(f"Error fetching data: {e}")
+        return []
 
-courses = []
+    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')
+    # 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')
         
-        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
-            })
+        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
+                })
+    return courses
 
 # Step 2: Create DataFrame
-df = pd.DataFrame(courses)
+df = pd.DataFrame(scrape_courses())
 
 # Step 3: Initialize the Groq client and set the API key
 client = Groq(api_key=creds.api_key)  # Properly passing the API key
@@ -44,9 +50,6 @@ def search_courses(query):
         print(f"Searching for: {query}")
         print(f"Number of courses in database: {len(df)}")
 
-        # Normalize the query to lowercase for case-insensitive comparison
-        normalized_query = query.lower()
-
         # Prepare the prompt for Groq
         prompt = f"""Given the following query: "{query}"
         Please analyze the query and rank the following courses based on their relevance to the query. 
@@ -80,27 +83,22 @@ def search_courses(query):
             if line.startswith('Title:'):
                 title = line.split('Title:')[1].strip()
                 print(f"Found title: {title}")
-
-                # Normalize the title to lowercase for comparison
-                normalized_title = title.lower()
-
-                # Check if the normalized title contains the normalized query
-                if normalized_query in normalized_title:
-                    relevance = float(line.split('Relevance:')[1].strip())
-                    print(f"Relevance for {title}: {relevance}")
-                    if relevance >= 0.5:
-                        matching_courses = df[df['title'] == title]
-                        if not matching_courses.empty:
-                            course = matching_courses.iloc[0]
-                            results.append({
-                                'title': title,
-                                'image_url': course['image_url'],
-                                'course_link': course['course_link'],
-                                'score': relevance
-                            })
-                            print(f"Added course: {title}")
-                        else:
-                            print(f"Warning: Course not found in database: {title}")
+            elif line.startswith('Relevance:'):
+                relevance = float(line.split('Relevance:')[1].strip())
+                print(f"Relevance for {title}: {relevance}")
+                if relevance >= 0.5:
+                    matching_courses = df[df['title'] == title]
+                    if not matching_courses.empty:
+                        course = matching_courses.iloc[0]
+                        results.append({
+                            'title': title,
+                            'image_url': course['image_url'],
+                            'course_link': course['course_link'],
+                            'score': relevance
+                        })
+                        print(f"Added course: {title}")
+                    else:
+                        print(f"Warning: Course not found in database: {title}")
 
         print(f"Number of results found: {len(results)}")
         return sorted(results, key=lambda x: x['score'], reverse=True)[:10]  # Return top 10 results