Update app.py

app.py

@@ -1,5 +1,5 @@
 """
-This module integrates real-time object detection into live YouTube streams using the YOLO model and provides an interactive user interface through Gradio. It allows users to search for live YouTube streams and apply object detection to these streams in real time.
+This module integrates real-time object detection into live YouTube streams using the YOLO (You Only Look Once) model, and provides an interactive user interface through Gradio. It is designed to allow users to search for live YouTube streams and apply object detection to these streams in real time.
 
 Main Features:
 - Search for live YouTube streams using specific queries.
@@ -8,18 +8,17 @@ Main Features:
 - Display the live stream and object detection results through a Gradio interface.
 
 The module comprises several key components:
+- `SearchFilter`: An enumeration for YouTube search filters.
 - `SearchService`: A service class to search for YouTube videos and retrieve live stream URLs.
 - `LiveYouTubeObjectDetector`: The main class integrating the YOLO model and Gradio UI, handling the entire workflow of searching, streaming, and object detection.
 
 Dependencies:
-- OpenCV (`cv2`): Used for image processing tasks.
+- cv2 (OpenCV): Used for image processing tasks.
 - Gradio: Provides the interactive web-based user interface.
-- Streamlink: Used for retrieving live stream data.
-- NumPy: Utilized for numerical operations on image data.
-- Pillow (`PIL`): A Python Imaging Library for opening, manipulating, and saving images.
-- Ultralytics YOLO: The YOLO model implementation for object detection.
-- `innertube`: Used for interacting with YouTube's internal API.
-- `imageio`: For reading frames from live streams using FFmpeg.
+- innertube, streamlink: Used for interacting with YouTube and retrieving live stream data.
+- numpy: Utilized for numerical operations on image data.
+- PIL (Pillow): A Python Imaging Library for opening, manipulating, and saving images.
+- ultralytics YOLO: The YOLO model implementation for object detection.
 
 Usage:
 Run this file to launch the Gradio interface, which allows users to input search queries for YouTube live streams, select a stream, and perform object detection on the selected live stream.
@@ -27,88 +26,137 @@ Run this file to launch the Gradio interface, which allows users to input search
 """
 
 import logging
+import os
+import sys
+from enum import Enum
 from typing import Any, Dict, List, Optional, Tuple
 
-import asyncio
 import cv2
 import gradio as gr
+import innertube
 import numpy as np
-from ultralytics import YOLO
 import streamlink
 from PIL import Image
-import innertube
-import imageio.v3 as iio
+from ultralytics import YOLO
+
+# Set up logging
+logging.basicConfig(stream=sys.stderr, level=logging.DEBUG)
+
+
+class SearchFilter(Enum):
+    """
+    An enumeration for specifying different types of YouTube search filters.
+
+    This Enum class is used to define filters for categorizing YouTube search
+    results into either live or regular video content. It is utilized in
+    conjunction with the `SearchService` class to refine YouTube searches
+    based on the type of content being sought.
+
+    Attributes:
+        LIVE (str): Represents the filter code for live video content on YouTube.
+        VIDEO (str): Represents the filter code for regular, non-live video content on YouTube.
+    """
 
-logging.basicConfig(level=logging.DEBUG)
+    LIVE = ("EgJAAQ%3D%3D", "Live")
+    VIDEO = ("EgIQAQ%3D%3D", "Video")
+
+    def __init__(self, code, human_readable):
+        """Initializes the SearchFilter with a code and a human-readable string.
+
+        :param code: The filter code used in YouTube search queries.
+        :type code: str
+        :param human_readable: A human-readable representation of the filter.
+        :type human_readable: str
+        """
+        self.code = code
+        self.human_readable = human_readable
+
+    def __str__(self):
+        """Returns the human-readable representation of the filter.
+
+        :return: The human-readable representation of the filter.
+        :rtype: str
+        """
+        return self.human_readable
 
 
 class SearchService:
     """
     SearchService provides functionality to search for YouTube videos using the
-    `innertube` library and retrieve live stream URLs using the Streamlink library.
+    InnerTube API and retrieve live stream URLs using the Streamlink library.
 
-    Methods:
-        search: Searches YouTube for videos matching a query and live filter.
-        parse: Parses raw search response data into a list of video details.
-        get_youtube_url: Constructs a YouTube URL for a given video ID.
-        get_stream: Retrieves the stream URL for a given YouTube video URL.
+    This service allows filtering search results to either live or regular video
+    content and parsing the search response to extract relevant video information.
+    It also constructs YouTube URLs for given video IDs and retrieves the best
+    available stream URL for live YouTube videos.
     """
 
     @staticmethod
-    def search(query: str, live: bool = False) -> List[Dict[str, Any]]:
-        """
-        Searches YouTube for videos matching the given query and live filter.
+    def search(query: Optional[str], filter: SearchFilter = SearchFilter.VIDEO):
+        """Searches YouTube for videos matching the given query and filter.
 
         :param query: The search query.
-        :type query: str
-        :param live: Whether to filter for live videos.
-        :type live: bool
+        :type query: Optional[str]
+        :param filter: The search filter to apply.
+        :type filter: SearchFilter
         :return: A list of search results, each a dictionary with video details.
         :rtype: List[Dict[str, Any]]
         """
-        client = innertube.InnerTube()
-        params = "EgJAAQ%3D%3D" if live else None  # 'Live' filter code
-        
-        response = client.search(query=query, params=params)
+        response = SearchService._search(query, filter)
         results = SearchService.parse(response)
         return results
 
     @staticmethod
-    def parse(response: Dict[str, Any]) -> List[Dict[str, Any]]:
-        """
-        Parses the raw search response data into a list of video details.
+    def parse(data: Dict[str, Any]) -> List[Dict[str, str]]:
+        """Parses the raw search response data into a list of video details.
 
-        :param response: The raw search response data from YouTube.
-        :type response: Dict[str, Any]
+        :param data: The raw search response data from YouTube.
+        :type data: Dict[str, Any]
         :return: A list of parsed video details.
-        :rtype: List[Dict[str, Any]]
+        :rtype: List[Dict[str, str]]
         """
         results = []
         try:
-            contents = response["contents"]["twoColumnSearchResultsRenderer"]["primaryContents"]["sectionListRenderer"]["contents"]
+            contents = data["contents"]["twoColumnSearchResultsRenderer"]["primaryContents"]["sectionListRenderer"]["contents"]
             for content in contents:
                 items = content.get("itemSectionRenderer", {}).get("contents", [])
                 for item in items:
-                    video_renderer = item.get("videoRenderer")
-                    if video_renderer:
-                        video_id = video_renderer.get("videoId")
-                        thumbnails = video_renderer.get("thumbnail", {}).get("thumbnails", [])
-                        title_runs = video_renderer.get("title", {}).get("runs", [])
-                        title = "".join([run.get("text", "") for run in title_runs])
-                        thumbnail_url = thumbnails[-1].get("url") if thumbnails else ""
-                        results.append({
-                            'video_id': video_id,
-                            'thumbnail_url': thumbnail_url,
-                            'title': title,
-                        })
+                    if "videoRenderer" in item:
+                        renderer = item["videoRenderer"]
+                        video_id = renderer.get("videoId", "")
+                        thumbnails = renderer.get("thumbnail", {}).get("thumbnails", [])
+                        thumbnail_url = thumbnails[-1]["url"] if thumbnails else ""
+                        title_runs = renderer.get("title", {}).get("runs", [])
+                        title = "".join(run.get("text", "") for run in title_runs)
+                        results.append(
+                            {
+                                "video_id": video_id,
+                                "thumbnail_url": thumbnail_url,
+                                "title": title,
+                            }
+                        )
         except Exception as e:
             logging.error(f"Error parsing search results: {e}")
         return results
 
     @staticmethod
-    def get_youtube_url(video_id: str) -> str:
+    def _search(query: Optional[str] = None, filter: SearchFilter = SearchFilter.VIDEO) -> Dict[str, Any]:
+        """Performs a YouTube search with the given query and filter.
+
+        :param query: The search query.
+        :type query: Optional[str]
+        :param filter: The search filter to apply.
+        :type filter: SearchFilter
+        :return: The raw search response data from YouTube.
+        :rtype: Dict[str, Any]
         """
-        Constructs a YouTube URL for the given video ID.
+        client = innertube.InnerTube(client_name="WEB", client_version="2.20230920.00.00")
+        response = client.search(query=query, params=filter.code if filter else None)
+        return response
+
+    @staticmethod
+    def get_youtube_url(video_id: str) -> str:
+        """Constructs a YouTube URL for the given video ID.
 
         :param video_id: The ID of the YouTube video.
         :type video_id: str
@@ -119,8 +167,7 @@ class SearchService:
 
     @staticmethod
     def get_stream(youtube_url: str) -> Optional[str]:
-        """
-        Retrieves the stream URL for a given YouTube video URL.
+        """Retrieves the stream URL for a given YouTube video URL.
 
         :param youtube_url: The URL of the YouTube video.
         :type youtube_url: str
@@ -141,30 +188,41 @@ class SearchService:
             return None
 
 
+INITIAL_STREAMS = SearchService.search("world live cams", SearchFilter.LIVE)
+
+
 class LiveYouTubeObjectDetector:
     """
     LiveYouTubeObjectDetector is a class that integrates object detection into live YouTube streams.
-    It uses the YOLO (You Only Look Once) model to detect objects in video frames captured from live streams.
+    It uses the YOLO model to detect objects in video frames captured from live streams.
     The class also provides a Gradio interface for users to interact with the object detection system,
     allowing them to search for live streams, view them, and detect objects in real-time.
-
-    Methods:
-        detect_objects: Detects objects in a live YouTube stream given its URL.
-        get_frame: Captures a frame from a live stream URL.
-        annotate: Annotates a frame with detected objects.
-        create_black_image: Creates a black placeholder image.
-        get_live_streams: Searches for live streams based on a query.
-        render: Sets up and launches the Gradio interface.
     """
 
     def __init__(self):
         """Initializes the LiveYouTubeObjectDetector with YOLO model and UI components."""
         logging.getLogger().setLevel(logging.DEBUG)
-        self.model = YOLO("yolo11n.pt")
-        self.model.fuse()
-        self.streams = self.get_live_streams("world live cams")
-
-    async def detect_objects(self, url: str) -> Tuple[Image.Image, List[Tuple[Tuple[int, int, int, int], str]]]:
+        self.model = YOLO("yolo11n.pt")  # Using yolo11n.pt as per your request
+        self.streams = INITIAL_STREAMS
+
+        # Gradio UI
+        initial_gallery_items = [(stream["thumbnail_url"], stream["title"]) for stream in self.streams]
+        self.gallery = gr.Gallery(label="Live YouTube Videos",
+                                  value=initial_gallery_items,
+                                  show_label=True,
+                                  columns=[4],
+                                  rows=[5],
+                                  object_fit="contain",
+                                  height="auto",
+                                  allow_preview=False)
+        self.search_input = gr.Textbox(label="Search Live YouTube Videos")
+        self.stream_input = gr.Textbox(label="URL of Live YouTube Video")
+        self.annotated_image = gr.AnnotatedImage(show_label=False)
+        self.search_button = gr.Button("Search", size="lg")
+        self.submit_button = gr.Button("Detect Objects", variant="primary", size="lg")
+        self.page_title = gr.HTML("<center><h1><b>Object Detection in Live YouTube Streams</b></h1></center>")
+
+    def detect_objects(self, url: str) -> Tuple[Image.Image, List[Tuple[Tuple[int, int, int, int], str]]]:
         """
         Detects objects in the given live YouTube stream URL.
 
@@ -177,13 +235,13 @@ class LiveYouTubeObjectDetector:
         if not stream_url:
             logging.error(f"Unable to find a stream for: {url}")
             return self.create_black_image()
-        frame = await self.get_frame(stream_url)
+        frame = self.get_frame(stream_url)
         if frame is None:
             logging.error(f"Unable to capture frame for: {url}")
             return self.create_black_image()
         return self.annotate(frame)
 
-    async def get_frame(self, stream_url: str) -> Optional[np.ndarray]:
+    def get_frame(self, stream_url: str) -> Optional[np.ndarray]:
         """
         Captures a frame from the given live stream URL.
 
@@ -195,17 +253,14 @@ class LiveYouTubeObjectDetector:
         if not stream_url:
             return None
         try:
-            reader = iio.imiter(stream_url, plugin='pyav', thread_type='AUTO')
-            loop = asyncio.get_event_loop()
-            frame = await loop.run_in_executor(None, next, reader, None)
-            if frame is None:
+            cap = cv2.VideoCapture(stream_url)
+            ret, frame = cap.read()
+            cap.release()
+            if ret and frame is not None:
+                return cv2.resize(frame, (1920, 1080))
+            else:
+                logging.warning("Unable to process the HLS stream with cv2.VideoCapture.")
                 return None
-            # Resize frame if needed
-            frame = cv2.resize(frame, (1280, 720))
-            return frame
-        except StopIteration:
-            logging.warning("Could not read frame from stream.")
-            return None
         except Exception as e:
             logging.warning(f"An error occurred while capturing the frame: {e}")
             return None
@@ -219,125 +274,90 @@ class LiveYouTubeObjectDetector:
         :return: A tuple of the annotated PIL image and list of annotations.
         :rtype: Tuple[Image.Image, List[Tuple[Tuple[int, int, int, int], str]]]
         """
-        results = self.model(frame)[0]
+        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        predictions = self.model.predict(frame_rgb)
         annotations = []
-        boxes = results.boxes
+        result = predictions[0]
+
+        boxes = result.boxes
         for box in boxes:
             x1, y1, x2, y2 = box.xyxy[0].tolist()
             class_id = int(box.cls[0])
             class_name = self.model.names[class_id]
             bbox_coords = (int(x1), int(y1), int(x2), int(y2))
             annotations.append((bbox_coords, class_name))
-        pil_image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
-        return pil_image, annotations
+
+        return Image.fromarray(frame_rgb), annotations
 
     @staticmethod
     def create_black_image() -> Tuple[Image.Image, List]:
         """
         Creates a black image of fixed dimensions.
 
-        :return: A black image as a PIL Image and an empty list of annotations.
+        :return: A black image as a PIL image and an empty list of annotations.
         :rtype: Tuple[Image.Image, List]
         """
-        black_image = np.zeros((720, 1280, 3), dtype=np.uint8)
+        black_image = np.zeros((1080, 1920, 3), dtype=np.uint8)
         pil_black_image = Image.fromarray(black_image)
         return pil_black_image, []
 
-    def get_live_streams(self, query: str = "") -> List[Dict[str, Any]]:
+    @staticmethod
+    def get_live_streams(query=""):
         """
         Searches for live streams on YouTube based on the given query.
 
-        :param query: The search query for live streams.
+        :param query: The search query for live streams, defaults to 'world live cams'.
         :type query: str
         :return: A list of dictionaries containing information about each live stream.
         :rtype: List[Dict[str, str]]
         """
-        return SearchService.search(query if query else "world live cams", live=True)
+        return SearchService.search(query if query else "world live cams", SearchFilter.LIVE)
 
     def render(self):
         """
         Sets up and launches the Gradio interface for the application.
 
-        This method creates the Gradio UI elements and defines the behavior of the application.
-        It includes the setup of interactive widgets like galleries, textboxes, and buttons,
-        and defines the actions triggered by user interactions with these widgets.
-
         The Gradio interface allows users to search for live YouTube streams, select a stream,
         and run object detection on the selected live stream.
         """
         with gr.Blocks(title="Object Detection in Live YouTube Streams",
-                       css=".gradio-container {background-color: #f5f5f5}", theme=gr.themes.Soft()) as app:
-            gr.HTML("<h1 style='text-align: center; color: #1E88E5;'>Object Detection in Live YouTube Streams</h1>")
-            with gr.Tabs():
-                with gr.TabItem("Live Stream Detection"):
+                       css="footer {visibility: hidden}", analytics_enabled=False) as app:
+            self.page_title.render()
+            with gr.Column():
+                with gr.Group():
                     with gr.Row():
-                        stream_input = gr.Textbox(label="URL of Live YouTube Video",
-                                                  placeholder="Enter YouTube live stream URL...", interactive=True)
-                        submit_button = gr.Button("Detect Objects", variant="primary")
-                    annotated_image = gr.AnnotatedImage(label="Detection Result", height=480)
-                    status_text = gr.Markdown(value="Status: Ready", visible=False)
-
-                    async def detect_objects_from_url(url):
-                        status_text.update(value="Status: Processing...", visible=True)
-                        try:
-                            result = await self.detect_objects(url)
-                            status_text.update(value="Status: Done", visible=True)
-                            return result
-                        except Exception as e:
-                            logging.error(f"An error occurred: {e}")
-                            status_text.update(value=f"Status: Error - {e}", visible=True)
-                            return self.create_black_image()
-
-                    submit_button.click(fn=detect_objects_from_url, inputs=[stream_input], outputs=[annotated_image], api_name="detect_objects")
-
-                with gr.TabItem("Search Live Streams"):
-                    with gr.Row():
-                        search_input = gr.Textbox(label="Search for Live YouTube Streams",
-                                                  placeholder="Enter search query...", interactive=True)
-                        search_button = gr.Button("Search", variant="secondary")
-                    gallery = gr.Gallery(label="Live YouTube Streams", show_label=False).style(grid=[4], height="auto")
-                    gallery.style(item_height=150)
-                    status_text_search = gr.Markdown(value="", visible=False)
-
-                    async def search_live_streams(query):
-                        status_text_search.update(value="Searching...", visible=True)
-                        self.streams = self.get_live_streams(query)
-                        gallery_items = []
-                        for stream in self.streams:
-                            thumb_url = stream["thumbnail_url"]
-                            title = stream["title"]
-                            video_id = stream["video_id"]
-                            gallery_items.append((thumb_url, title, video_id))
-                        status_text_search.update(value="Search Results:", visible=True)
-                        return gr.update(value=gallery_items)
-
-                    search_button.click(fn=search_live_streams, inputs=[search_input], outputs=[gallery], api_name="search_streams")
-
-                    async def detect_objects_from_gallery_item(evt: gr.SelectData):
-                        index = evt.index
-                        if index is not None and index < len(self.streams):
-                            selected_stream = self.streams[index]
-                            stream_url = SearchService.get_youtube_url(selected_stream["video_id"])
-                            stream_input.value = stream_url
-                            result = await self.detect_objects(stream_url)
-                            annotated_image.update(value=result[0], annotations=result[1])
-                            with gr.Row():
-                                annotated_image.render()
-                            return result
-
-                    gallery.select(fn=detect_objects_from_gallery_item, inputs=None, outputs=None)
-
-            gr.Markdown(
-                """
-                **Instructions:**
-                - **Live Stream Detection Tab:** Enter a YouTube live stream URL and click 'Detect Objects' to view the real-time object detection.
-                - **Search Live Streams Tab:** Search for live streams on YouTube, select one from the gallery, and view object detection results.
-                """
-            )
-
-            gr.HTML("<footer style='text-align: center; color: gray;'>Developed using Gradio and YOLO</footer>")
-
-        app.queue(concurrency_count=3).launch()
+                        self.stream_input.render()
+                        self.submit_button.render()
+                self.annotated_image.render()
+            with gr.Group():
+                with gr.Row():
+                    self.search_input.render()
+                    self.search_button.render()
+            with gr.Row():
+                self.gallery.render()
+
+            @self.gallery.select(inputs=None, outputs=[self.annotated_image, self.stream_input], scroll_to_output=True)
+            def detect_objects_from_gallery_item(evt: gr.SelectData):
+                if evt.index is not None and evt.index < len(self.streams):
+                    selected_stream = self.streams[evt.index]
+                    stream_url = SearchService.get_youtube_url(selected_stream["video_id"])
+                    annotated_image, annotations = self.detect_objects(stream_url)
+                    self.stream_input.value = stream_url
+                    return annotated_image, annotations, stream_url
+                return None, "", ""
+
+            @self.search_button.click(inputs=[self.search_input], outputs=[self.gallery])
+            def search_live_streams(query):
+                self.streams = self.get_live_streams(query)
+                gallery_items = [(stream["thumbnail_url"], stream["title"]) for stream in self.streams]
+                return gallery_items
+
+            @self.submit_button.click(inputs=[self.stream_input], outputs=[self.annotated_image])
+            def detect_objects_from_url(url):
+                return self.detect_objects(url)
+
+        app.queue().launch(show_api=False, debug=True)
+
 
 if __name__ == "__main__":
-    LiveYouTubeObjectDetector().render()
+    LiveYouTubeObjectDetector().render()