Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
from youtube_transcript_api import YouTubeTranscriptApi
|
| 3 |
+
|
| 4 |
+
def get_youtube_transcript(video_id: str) -> str:
|
| 5 |
+
"""
|
| 6 |
+
Fetches and formats the transcript for a given YouTube video ID.
|
| 7 |
+
|
| 8 |
+
Args:
|
| 9 |
+
video_id (str): The YouTube video ID (e.g., 'dQw4w9WgXcQ').
|
| 10 |
+
|
| 11 |
+
Returns:
|
| 12 |
+
str: A formatted string containing the full transcript and detailed segments,
|
| 13 |
+
or an error message if the transcript cannot be retrieved.
|
| 14 |
+
"""
|
| 15 |
+
if not video_id:
|
| 16 |
+
return "Please enter a YouTube video ID."
|
| 17 |
+
|
| 18 |
+
try:
|
| 19 |
+
# Fetch the transcript list
|
| 20 |
+
transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
|
| 21 |
+
|
| 22 |
+
# Extract full transcript text
|
| 23 |
+
full_transcript_text = " ".join([item['text'] for item in transcript_list])
|
| 24 |
+
|
| 25 |
+
# Prepare detailed transcript segments
|
| 26 |
+
detailed_segments = []
|
| 27 |
+
for segment in transcript_list:
|
| 28 |
+
detailed_segments.append(
|
| 29 |
+
f"Start: {segment['start']:.2f}s, Duration: {segment['duration']:.2f}s, Text: {segment['text']}"
|
| 30 |
+
)
|
| 31 |
+
|
| 32 |
+
# Combine results into a single string for Gradio output
|
| 33 |
+
output = (
|
| 34 |
+
"Full Transcript:\n"
|
| 35 |
+
f"{full_transcript_text}\n\n"
|
| 36 |
+
"Detailed Transcript Segments:\n"
|
| 37 |
+
f"{'\\n'.join(detailed_segments)}"
|
| 38 |
+
)
|
| 39 |
+
return output
|
| 40 |
+
|
| 41 |
+
except Exception as e:
|
| 42 |
+
# Handle potential errors during transcript fetching
|
| 43 |
+
error_message = (
|
| 44 |
+
f"An error occurred: {e}\n"
|
| 45 |
+
"Possible reasons: No transcript available for this video, "
|
| 46 |
+
"invalid video ID, or network issues. "
|
| 47 |
+
"Please ensure the video ID is correct and the video has captions enabled."
|
| 48 |
+
)
|
| 49 |
+
return error_message
|
| 50 |
+
|
| 51 |
+
# Create the Gradio interface
|
| 52 |
+
iface = gr.Interface(
|
| 53 |
+
fn=get_youtube_transcript,
|
| 54 |
+
inputs=gr.Textbox(
|
| 55 |
+
label="YouTube Video ID",
|
| 56 |
+
placeholder="e.g., dQw4w9WgXcQ (from youtube.com/watch?v=dQw4w9WgXcQ)"
|
| 57 |
+
),
|
| 58 |
+
outputs=gr.Textbox(
|
| 59 |
+
label="Transcript Output",
|
| 60 |
+
lines=20, # Adjust number of lines for better display of long transcripts
|
| 61 |
+
interactive=False # Make the output box read-only
|
| 62 |
+
),
|
| 63 |
+
title="YouTube Transcript Fetcher",
|
| 64 |
+
description="Enter a YouTube video ID to get its full transcript and detailed segments."
|
| 65 |
+
)
|
| 66 |
+
|
| 67 |
+
# Launch the Gradio app
|
| 68 |
+
if __name__ == "__main__":
|
| 69 |
+
iface.launch()
|