Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -96,25 +96,26 @@ def process_youtube():
|
|
| 96 |
return jsonify({"error": "No YouTube URL provided"}), 400
|
| 97 |
|
| 98 |
try:
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
# Concatenate the text from each segment into a single transcript
|
| 107 |
-
transcript = " ".join([segment['text'] for segment in transcript_data])
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
except Exception as e:
|
| 111 |
-
print(f"Error fetching transcript for video ID {video_id}: {e}")
|
| 112 |
|
| 113 |
-
|
| 114 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
|
| 116 |
# Send the transcript to the Gemini API for structured data
|
| 117 |
structured_data = query_gemini_api(transcript)
|
|
|
|
| 118 |
|
| 119 |
# Return the structured data
|
| 120 |
return jsonify(structured_data)
|
|
|
|
| 96 |
return jsonify({"error": "No YouTube URL provided"}), 400
|
| 97 |
|
| 98 |
try:
|
| 99 |
+
|
| 100 |
+
"""
|
| 101 |
+
Fetches the transcript of a YouTube video using the YouTube Transcript API.
|
| 102 |
+
"""
|
| 103 |
+
|
| 104 |
+
# Extract the video ID from the YouTube URL
|
| 105 |
+
video_id = youtube_url.split("v=")[-1].split("&")[0]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
|
| 107 |
+
# Fetch the transcript for the given video ID
|
| 108 |
+
transcript_data = YouTubeTranscriptApi.get_transcript(video_id)
|
| 109 |
+
|
| 110 |
+
# Print transcript to console
|
| 111 |
+
print(f"Transcript for video ID {video_id}:")
|
| 112 |
+
transcript = " ".join([segment['text'] for segment in transcript_data])
|
| 113 |
+
|
| 114 |
+
|
| 115 |
|
| 116 |
# Send the transcript to the Gemini API for structured data
|
| 117 |
structured_data = query_gemini_api(transcript)
|
| 118 |
+
|
| 119 |
|
| 120 |
# Return the structured data
|
| 121 |
return jsonify(structured_data)
|