Update app.py

app.py

@@ -288,7 +288,44 @@ def clean_text(text):
     text = re.sub(r"^```|```$", '', text)
     text = re.sub(r'^srt', '', text, flags=re.MULTILINE)
     return text
+def split_srt_file(input_file, max_chars=3000):
+    # Read the contents of the SRT file
+    with open(input_file, 'r', encoding='utf-8') as file:
+        content = file.read()
 
+    # Split the content into individual subtitles
+    subtitles = content.strip().split('\n\n')
+
+    # Prepare to write the split files
+    output_files = []
+    current_file_content = ''
+    current_file_index = 1
+
+    for subtitle in subtitles:
+        # Check if adding this subtitle would exceed the character limit
+        if len(current_file_content) + len(subtitle) + 2 > max_chars:  # +2 for \n\n
+            # Write the current file
+            output_file_name = f'split_{current_file_index}.srt'
+            with open(output_file_name, 'w', encoding='utf-8') as output_file:
+                output_file.write(current_file_content.strip())
+            output_files.append(output_file_name)
+
+            # Prepare for the next file
+            current_file_index += 1
+            current_file_content = subtitle + '\n\n'
+        else:
+            # If it fits, add the subtitle
+            current_file_content += subtitle + '\n\n'
+
+    # Write any remaining content to a new SRT file
+    if current_file_content:
+        output_file_name = f'split_{current_file_index}.srt'
+        with open(output_file_name, 'w', encoding='utf-8') as output_file:
+            output_file.write(current_file_content.strip())
+        output_files.append(output_file_name)
+
+    return output_files
+    
 def enhance_text(api_key, text):
     url = "https://api.one-api.ir/chatbot/v1/gpt4o/"
 
@@ -380,9 +417,14 @@ def process_video(url, type):
     subtitle_file = generate_subtitle_file(language=language, segments=segments, input_video_name=input_video_name)
     source_language = "en"
     target_language = "fa"
-    srt_string = read_srt_file(subtitle_file)
-    google_translate = enhance_text(api_key, srt_string)
-    write_google(google_translate)
+    #srt_string = read_srt_file(subtitle_file)
+    srt_files=split_srt_file(subtitle_file)
+    for i in srt_files:
+        srt_string = read_srt_file(f"/content/{i}")
+    #google_translate = translate_text(api_key, source_language, target_language, srt_string)
+        google_translate = enhance_text(api_key, srt_string)
+        write_google(google_translate)
+        time.sleep(15)
     srt = read_srt_file("google_translate.srt")
     return srt, input_video