Use tqdm for processing

app.py

@@ -114,8 +114,8 @@ with gr.Blocks(css="style.css") as demo:
         You can browse your video from the local file system, or enter a video URL/YouTube video link to start processing.
 
         **Note**: 
-        - It will take a bit of time to complete (~40% of the original video length), so stay tuned!
-        - If the YouTube downloader return errors, you can try again later or download video to your computer and then upload it to the app
+        - It will take some time to complete (~ half of the original video length), so stay tuned!
+        - If the YouTube video link doesn't work, you can try again later or download video to your computer and then upload it to the app
         - Remember to press Enter if you are using an external URL
         """,
             elem_id="container",
@@ -176,7 +176,7 @@ with gr.Blocks(css="style.css") as demo:
                     file_url = gr.Textbox(
                         value="",
                         label="Upload your file",
-                        placeholder="Enter a video url or YouTube link",
+                        placeholder="Enter a video url or YouTube video link",
                         show_label=False,
                     )
                 with gr.Column(scale=1, min_width=160):

bg_modeling.py

@@ -1,7 +1,7 @@
+import cv2
 import os
-import time
 import sys
-import cv2
+from tqdm import tqdm
 from utils import resize_image_frame
 
 
@@ -38,7 +38,9 @@ def capture_slides_bg_modeling(
         print("Unable to open video file: ", video_path)
         sys.exit()
 
-    start = time.time()
+    num_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    prog_bar = tqdm(total=num_frames)
+
     # Loop over subsequent frames.
     while cap.isOpened():
         ret, frame = cap.read()
@@ -66,21 +68,16 @@ def capture_slides_bg_modeling(
 
             png_filename = f"{screenshots_count:03}.jpg"
             out_file_path = os.path.join(output_dir_path, png_filename)
-            print(f"Saving file at: {out_file_path}")
             cv2.imwrite(out_file_path, orig_frame, [cv2.IMWRITE_JPEG_QUALITY, 75])
+            prog_bar.set_postfix_str(f"Total Screenshots: {screenshots_count}")
 
         # p_non_zero >= MIN_PERCENT_THRESH, indicates motion/animations.
         # Hence wait till the motion across subsequent frames has settled down.
         elif capture_frame and p_non_zero >= MIN_PERCENT_THRESH:
             capture_frame = False
+        
+        prog_bar.update(1)
 
-    end_time = time.time()
-    print("***" * 10, "\n")
-    print("Statistics:")
-    print("---" * 10)
-    print(f"Total Time taken: {round(end_time-start, 3)} secs")
-    print(f"Total Screenshots captured: {screenshots_count}")
-    print("---" * 10, "\n")
-
-    # Release Video Capture object.
+    # Release progress bar and video capture object.
+    prog_bar.close()
     cap.release()

convert_to_pdf.py

@@ -0,0 +1,22 @@
+import argparse
+from utils import convert_slides_to_pdf
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="This script is used to convert video frames into slide PDFs."
+    )
+    parser.add_argument(
+        "-f", "--folder", help="Path to the image folder", type=str
+    )
+    parser.add_argument(
+        "-o",
+        "--out_path",
+        help="Path to the output PDF file. If None, the image directory will be used to store the output file.",
+        type=str,
+    )
+    args = parser.parse_args()
+
+    img_dir = args.folder
+    output_path = args.out_path
+
+    convert_slides_to_pdf(img_dir, output_path)

download_video.py

@@ -15,8 +15,8 @@ def download_video_from_url(url, output_dir=DOWNLOAD_DIR):
 
         content_type = response.headers.get("content-type")
         if "video" not in content_type:
-            print("The given URL is not a valid video")
-            return None
+            print("The given URL is not a valid video URL")
+            return
         file_extension = mimetypes.guess_extension(content_type)
 
         os.makedirs(output_dir, exist_ok=True)
@@ -32,7 +32,7 @@ def download_video_from_url(url, output_dir=DOWNLOAD_DIR):
 
     except requests.exceptions.RequestException as e:
         print("An error occurred while downloading the video:", str(e))
-        return None
+        return
 
 
 def download_video_from_youtube(url, output_dir=DOWNLOAD_DIR):
@@ -52,7 +52,7 @@ def download_video_from_youtube(url, output_dir=DOWNLOAD_DIR):
 
     except Exception as e:
         print("An error occurred while downloading the video:", str(e))
-        return None
+        return
 
 
 def download_video(url, output_dir=DOWNLOAD_DIR):

frame_differencing.py

@@ -1,7 +1,7 @@
 import cv2
 import os
-import time
 import sys
+from tqdm import tqdm
 
 
 def capture_slides_frame_diff(
@@ -24,12 +24,12 @@ def capture_slides_frame_diff(
         sys.exit()
 
     success, first_frame = cap.read()
+    num_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
+    prog_bar = tqdm(total=num_frames)
 
     print("Using frame differencing for Background Subtraction...")
     print("---" * 10)
 
-    start = time.time()
-
     # The 1st frame should always be present in the output directory.
     # Hence capture and save the 1st frame.
     if success:
@@ -42,10 +42,10 @@ def capture_slides_frame_diff(
 
         filename = f"{screenshots_count:03}.jpg"
         out_file_path = os.path.join(output_dir_path, filename)
-        print(f"Saving file at: {out_file_path}")
 
         # Save frame.
         cv2.imwrite(out_file_path, first_frame, [cv2.IMWRITE_JPEG_QUALITY, 75])
+        prog_bar.update(1)
 
     # Loop over subsequent frames.
     while cap.isOpened():
@@ -79,18 +79,13 @@ def capture_slides_frame_diff(
 
                 filename = f"{screenshots_count:03}.jpg"
                 out_file_path = os.path.join(output_dir_path, filename)
-                print(f"Saving file at: {out_file_path}")
 
                 cv2.imwrite(out_file_path, frame, [cv2.IMWRITE_JPEG_QUALITY, 75])
+                prog_bar.set_postfix_str(f"Total Screenshots: {screenshots_count}")
 
         prev_frame = curr_frame
+        prog_bar.update(1)
 
-    end_time = time.time()
-    print("***" * 10, "\n")
-    print("Statistics:")
-    print("---" * 5)
-    print(f"Total Time taken: {round(end_time-start, 3)} secs")
-    print(f"Total Screenshots captured: {screenshots_count}")
-    print("---" * 10, "\n")
-
+    # Release progress bar and video capture object.
+    prog_bar.close()
     cap.release()

post_process.py

@@ -2,6 +2,7 @@ import imagehash
 import os
 from collections import deque
 from PIL import Image
+from tqdm import tqdm
 
 
 def find_similar_images(
@@ -16,31 +17,30 @@ def find_similar_images(
 
     print("---" * 5, "Finding similar files", "---" * 5)
 
-    for file in snapshots_files:
-        read_file = Image.open(os.path.join(base_dir, file))
-        comp_hash = hashfunc(read_file, hash_size=hash_size)
-        duplicate = False
-
-        if comp_hash not in hash_dict:
-            hash_dict[comp_hash] = file
-            # Compare with hash queue to find out potential duplicates
-            for img_hash in hash_queue:
-                if img_hash - comp_hash <= threshold:
-                    duplicate = True
-                    break
-
-            if not duplicate:
-                hash_queue.append(comp_hash)
-        else:
-            duplicate = True
-
-        if duplicate:
-            print("Duplicate file: ", file)
-            duplicates.append(file)
-            num_duplicates += 1
-
-    print("\nTotal duplicate files:", num_duplicates)
-    print("-----" * 10)
+    with tqdm(snapshots_files) as t:
+        for file in t:
+            read_file = Image.open(os.path.join(base_dir, file))
+            comp_hash = hashfunc(read_file, hash_size=hash_size)
+            duplicate = False
+
+            if comp_hash not in hash_dict:
+                hash_dict[comp_hash] = file
+                # Compare with hash queue to find out potential duplicates
+                for img_hash in hash_queue:
+                    if img_hash - comp_hash <= threshold:
+                        duplicate = True
+                        break
+
+                if not duplicate:
+                    hash_queue.append(comp_hash)
+            else:
+                duplicate = True
+
+            if duplicate:
+                duplicates.append(file)
+                num_duplicates += 1
+                t.set_postfix_str(f"Duplicate files: {num_duplicates}")
+
     return hash_dict, duplicates
 
 

requirements.txt

@@ -1,11 +1,11 @@
-opencv-contrib-python==4.7.0.72
 numpy
 Pillow
 scipy
 six
 ImageHash
-imutils
 img2pdf
+imutils
 pytube
 validators
-requests
+requests
+tqdm