Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -88,6 +88,42 @@ def process_audio():
|
|
88 |
print(f"Temporary WAV file deleted: {temp_audio_path}")
|
89 |
|
90 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
@app.route('/process-youtube', methods=['POST'])
|
92 |
def process_youtube():
|
93 |
youtube_url = request.json.get('youtube_url')
|
@@ -96,28 +132,29 @@ def process_youtube():
|
|
96 |
return jsonify({"error": "No YouTube URL provided"}), 400
|
97 |
|
98 |
try:
|
99 |
-
|
100 |
-
|
101 |
# Extract the video ID from the YouTube URL
|
102 |
video_id = youtube_url.split("v=")[-1].split("&")[0]
|
|
|
103 |
|
104 |
-
|
105 |
-
|
|
|
|
|
|
|
|
|
106 |
|
107 |
-
#
|
108 |
-
print(f"Transcript for video ID {video_id}:")
|
109 |
transcript = " ".join([segment['text'] for segment in transcript_data])
|
|
|
110 |
|
111 |
-
|
112 |
-
|
113 |
-
# Send the transcript to the Gemini API for structured data
|
114 |
structured_data = query_gemini_api(transcript)
|
115 |
-
|
116 |
|
117 |
-
# Return
|
118 |
return jsonify(structured_data)
|
119 |
|
120 |
except Exception as e:
|
|
|
121 |
return jsonify({"error": str(e)}), 500
|
122 |
|
123 |
|
|
|
88 |
print(f"Temporary WAV file deleted: {temp_audio_path}")
|
89 |
|
90 |
|
91 |
+
# @app.route('/process-youtube', methods=['POST'])
|
92 |
+
# def process_youtube():
|
93 |
+
# youtube_url = request.json.get('youtube_url')
|
94 |
+
|
95 |
+
# if not youtube_url:
|
96 |
+
# return jsonify({"error": "No YouTube URL provided"}), 400
|
97 |
+
|
98 |
+
# try:
|
99 |
+
|
100 |
+
|
101 |
+
# # Extract the video ID from the YouTube URL
|
102 |
+
# video_id = youtube_url.split("v=")[-1].split("&")[0]
|
103 |
+
|
104 |
+
# # Fetch the transcript for the given video ID
|
105 |
+
# transcript_data = YouTubeTranscriptApi.get_transcript(video_id)
|
106 |
+
|
107 |
+
# # Print transcript to console
|
108 |
+
# print(f"Transcript for video ID {video_id}:")
|
109 |
+
# transcript = " ".join([segment['text'] for segment in transcript_data])
|
110 |
+
|
111 |
+
|
112 |
+
|
113 |
+
# # Send the transcript to the Gemini API for structured data
|
114 |
+
# structured_data = query_gemini_api(transcript)
|
115 |
+
|
116 |
+
|
117 |
+
# # Return the structured data
|
118 |
+
# return jsonify(structured_data)
|
119 |
+
|
120 |
+
# except Exception as e:
|
121 |
+
# return jsonify({"error": str(e)}), 500
|
122 |
+
|
123 |
+
|
124 |
+
import logging
|
125 |
+
logging.basicConfig(level=logging.DEBUG)
|
126 |
+
|
127 |
@app.route('/process-youtube', methods=['POST'])
|
128 |
def process_youtube():
|
129 |
youtube_url = request.json.get('youtube_url')
|
|
|
132 |
return jsonify({"error": "No YouTube URL provided"}), 400
|
133 |
|
134 |
try:
|
|
|
|
|
135 |
# Extract the video ID from the YouTube URL
|
136 |
video_id = youtube_url.split("v=")[-1].split("&")[0]
|
137 |
+
logging.debug(f"Processing video ID: {video_id}")
|
138 |
|
139 |
+
try:
|
140 |
+
# Fetch transcript
|
141 |
+
transcript_data = YouTubeTranscriptApi.get_transcript(video_id)
|
142 |
+
except YouTubeTranscriptApiException as e:
|
143 |
+
logging.error(f"Error fetching transcript for {video_id}: {e}")
|
144 |
+
return jsonify({"error": f"Could not retrieve transcript for video {video_id}: {str(e)}"}), 500
|
145 |
|
146 |
+
# Concatenate transcript
|
|
|
147 |
transcript = " ".join([segment['text'] for segment in transcript_data])
|
148 |
+
logging.debug(f"Transcript: {transcript}")
|
149 |
|
150 |
+
# Send to Gemini API
|
|
|
|
|
151 |
structured_data = query_gemini_api(transcript)
|
|
|
152 |
|
153 |
+
# Return structured data
|
154 |
return jsonify(structured_data)
|
155 |
|
156 |
except Exception as e:
|
157 |
+
logging.error(f"Unexpected error: {str(e)}")
|
158 |
return jsonify({"error": str(e)}), 500
|
159 |
|
160 |
|