Update app.py

app.py

@@ -7,6 +7,11 @@ import wikipedia
 import re
 import time
 import random
+import os
+import zipfile
+import gradio as gr
+import ffmpeg
+
 
 nltk.download('maxent_ne_chunker') #Chunker
 nltk.download('stopwords') #Stop Words List (Mainly Roman Languages)
@@ -288,6 +293,47 @@ def splittext(string):
     linenumber += 1
   return FinalOutput[2:]   
 
+def VideotoSegment(video_file, subtitle_file):
+    # Read the subtitle file and extract the timings for each subtitle
+    timings = []
+    for line in subtitle_file:
+        if '-->' in line:
+            start, end = line.split('-->')
+            start_time = start.strip().replace(',', '.')
+            end_time = end.strip().replace(',', '.')
+            timings.append((start_time, end_time))
+
+    # Cut the video into segments based on the subtitle timings
+    video_segments = []
+    for i, (start_time, end_time) in enumerate(timings):
+        output_file = f'segment_{i}.mp4'
+        ffmpeg.input(video_file, ss=start_time, to=end_time).output(output_file, codec='copy').run()
+        video_segments.append(output_file)
+
+    # Convert each segment to an MP3 audio file using FFmpeg
+    audio_segments = []
+    for i in range(len(timings)):
+        output_file = f'segment_{i}.mp3'
+        ffmpeg.input(video_segments[i]).output(output_file, codec='libmp3lame', qscale='4').run()
+        audio_segments.append(output_file)
+
+    # Create a ZIP archive containing all of the segmented files
+    zip_file = zipfile.ZipFile('segmented_files.zip', 'w')
+    for segment in video_segments + audio_segments:
+        zip_file.write(segment)
+        os.remove(segment)
+    zip_file.close()
+
+    # Return the ZIP archive for download
+    return 'segmented_files.zip'
+
+
+# Define the Gradio interface inputs and outputs for video split
+spvvideo_file_input = gr.File(label='Video File')
+spvsubtitle_file_input = gr.File(label='Subtitle File')
+spvdownload_output = gr.File(label='Download Segmented Files')
+
+
 groupinput_text = gr.inputs.Textbox(lines=2, label="Enter a list of words")
 groupoutput_text = gr.outputs.Textbox(label="Grouped words")
 
@@ -330,7 +376,7 @@ with gr.Blocks() as lliface:
       <p>My One Word Theory = We only use more words than needed when we have to or are bored --> Headings exist because title is not sufficient, subheadings exist because headings are not sufficient, Book Text exists because subheadings are not sufficient</p>
       <p>Big Picture = Expand the Heading and the subheadings and compare them to each other</p>
       <p>Application of Knowledge = App Version of the text (eg. Jupyter Notebooks) is what you create and learn first</p>
-	  """)  
+	  """)    
   with gr.Tab("Beginner - Songs - Chorus"):
       gr.HTML("Essentially if the sounds are repeated or long notes they are easy to remember")
       gr.Interface(fn=TTSforListeningPractice, inputs="text", outputs="text", title="Placeholder - paste chorus here and use TTS or make notes to save here")
@@ -355,6 +401,8 @@ with gr.Blocks() as lliface:
         with gr.Row():
             MergeOutput = gr.TextArea(label="Output")
             MergeButton.click(merge_lines, inputs=[RomanFile, W4WFile, FullMeanFile, MacaronicFile], outputs=[MergeOutput])
+    with gr.Tab("Split video to segments"):
+        gr.Interface(VideotoSegment, inputs=[spvvideo_file_input, spvsubtitle_file_input], outputs=spvdownload_output)
     with gr.Tab("Sentence to Format"):
         gr.Interface(fn=split_verbs_nouns , inputs="text", outputs=["text", "text"], title="Comprehension reading and Sentence Format Creator")
         gr.Text("Text to Closed Class + Adjectives + Punctuation or Noun Verb + Punctuation ")