Update app.py

app.py

@@ -1,82 +1,76 @@
-import yt_dlp
+import requests
+from bs4 import BeautifulSoup
+import gradio as gr
 import logging
 
 # Configure logging for debugging purposes
 logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')
 
-# Function to search YouTube videos using yt-dlp for better reliability
-def youtube_search(query, max_results=50):
-    ydl_opts = {
-        'quiet': False,
-        'extract_flat': False,  # Set to False to retrieve full details of each video
-        'logger': logging.getLogger(),  # Use the logging module to capture yt-dlp logs
-        'simulate': True,
-        'noplaylist': True,  # Avoid playlist entries
-        'ignoreerrors': True,  # Continue on errors without stopping
-        'force_generic_extractor': False,  # Use the best extractor available
-        'default_search': 'ytsearch',  # Default search method
+# Function to search YouTube without using the API
+def youtube_search(query, max_results=10):
+    # Create the YouTube search URL
+    search_url = f"https://www.youtube.com/results?search_query={query.replace(' ', '+')}"
+    headers = {
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.83 Safari/537.36"
     }
-    search_url = f"ytsearch{max_results}:{query}"
 
     logging.debug(f"Starting YouTube search for query: {query}")
 
     try:
-        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-            result = ydl.extract_info(search_url, download=False)
+        response = requests.get(search_url, headers=headers)
+        response.raise_for_status()  # Raise an error for bad status codes
 
-            if not result or 'entries' not in result:
-                logging.warning("No entries found in search result.")
-                return []
+        # Parse the HTML response using BeautifulSoup
+        soup = BeautifulSoup(response.text, "html.parser")
 
-            entries = result['entries']
-            logging.debug(f"Number of entries found: {len(entries)}")
+        # Find all video entries
+        videos = soup.find_all("a", {"href": lambda x: x and "/watch?v=" in x}, limit=max_results)
 
-            detailed_entries = []
-            for entry in entries:
-                # Collect and print each field separately
-                print("\n==============================")
-                print("Video Details:")
-                print("==============================")
-                print(f"ID: {entry.get('id', 'N/A')}")
-                print(f"Title: {entry.get('title', 'N/A')}")
-                print(f"Uploader: {entry.get('uploader', 'N/A')}")
-                print(f"Uploader ID: {entry.get('uploader_id', 'N/A')}")
-                print(f"Upload Date: {entry.get('upload_date', 'N/A')}")
-                print(f"Description: {entry.get('description', 'N/A')}")
-                print(f"Duration (seconds): {entry.get('duration', 'N/A')}")
-                print(f"View Count: {entry.get('view_count', 'N/A')}")
-                print(f"Like Count: {entry.get('like_count', 'N/A')}")
-                print(f"Dislike Count: {entry.get('dislike_count', 'N/A')}")
-                print(f"Comment Count: {entry.get('comment_count', 'N/A')}")
-                print(f"Average Rating: {entry.get('average_rating', 'N/A')}")
-                print(f"Thumbnail URL: {entry.get('thumbnail', 'N/A')}")
-                print(f"Webpage URL: {entry.get('webpage_url', 'N/A')}")
-                print(f"Channel URL: {entry.get('channel_url', 'N/A')}")
-                print(f"Categories: {entry.get('categories', 'N/A')}")
-                print(f"Tags: {entry.get('tags', 'N/A')}")
-                print(f"Channel ID: {entry.get('channel_id', 'N/A')}")
-                print(f"Age Restriction: {entry.get('age_limit', 'N/A')}")
-                print(f"Is Live: {entry.get('is_live', 'N/A')}")
-                print(f"FPS: {entry.get('fps', 'N/A')}")
-                print(f"Resolution: {entry.get('resolution', 'N/A')}")
-                print(f"Aspect Ratio: {entry.get('aspect_ratio', 'N/A')}")
-                print(f"Video Codec: {entry.get('vcodec', 'N/A')}")
-                print(f"Audio Codec: {entry.get('acodec', 'N/A')}")
-                print("==============================\n")
+        gallery_items = []
+        for video in videos:
+            # Extract details
+            video_id = video['href'].split('=')[1]
+            video_title = video.get('title', 'No Title')
+            video_url = f"https://www.youtube.com{video['href']}"
+            thumbnail_url = f"https://i.ytimg.com/vi/{video_id}/hqdefault.jpg"
 
-                # Add the entry details to the list if needed
-                detailed_entries.append(entry)
+            # Append video details as a tuple for the gallery display
+            gallery_items.append((thumbnail_url, video_title, video_url))
 
-            return detailed_entries
+        return gallery_items, ""  # Return the list of gallery items and no error message
 
-    except yt_dlp.utils.DownloadError as e:
-        logging.error(f"DownloadError occurred: {e}")
-    except yt_dlp.utils.ExtractorError as e:
-        logging.error(f"ExtractorError occurred: {e}")
+    except requests.exceptions.RequestException as e:
+        error_message = f"Request error occurred: {e}"
+        logging.error(error_message)
+        return [], error_message
     except Exception as e:
-        logging.error(f"An unexpected error occurred: {e}")
-    
-    return []
+        error_message = f"An unexpected error occurred: {e}"
+        logging.error(error_message)
+        return [], error_message
 
-# Test the function with a sample query
-youtube_search("test video")
+# Function to create a gallery for Gradio
+def display_videos(query):
+    gallery_items, error_message = youtube_search(query)
+    if error_message:
+        return gr.update(value=[], label="Error: Unable to fetch videos"), error_message
+
+    # Display thumbnails and titles as gallery items
+    formatted_gallery = [(f"<img src='{item[0]}' width='250'/>", f"<a href='{item[2]}' target='_blank'>{item[1]}</a>") for item in gallery_items]
+    return formatted_gallery, ""
+
+# Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("## YouTube Video Search (Without API)")
+    with gr.Row():
+        with gr.Column(scale=2):
+            search_input = gr.Textbox(label="Search YouTube", placeholder="Enter your search query here")
+            search_button = gr.Button("Search")
+        with gr.Column(scale=4):
+            search_output = gr.Gallery(label="Search Results", columns=2)
+            error_output = gr.Textbox(label="Error Message", interactive=False, visible=False)
+
+    # Define search button behavior
+    search_button.click(display_videos, inputs=search_input, outputs=[search_output, error_output])
+
+# Launch the Gradio interface
+demo.launch()