Create app.py

app.py

@@ -0,0 +1,91 @@
+from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound, VideoUnavailable
+from urllib.parse import urlparse, parse_qs
+import gradio as gr
+from transformers import pipeline
+
+
+# Load Hugging Face summarization model
+text_summary = pipeline("summarization", model="sshleifer/distilbart-xsum-12-6")
+
+# Extract video ID from YouTube URL
+def get_video_id(youtube_url):
+    query = urlparse(youtube_url)
+    if query.hostname == 'youtu.be':
+        return query.path[1:]
+    elif query.hostname in ['www.youtube.com', 'youtube.com']:
+        if query.path == '/watch':
+            return parse_qs(query.query).get('v', [None])[0]
+        elif query.path.startswith('/embed/') or query.path.startswith('/v/'):
+            return query.path.split('/')[2]
+    return None
+
+# Fetch transcript from video ID
+def fetch_transcript(video_url):
+    video_id = get_video_id(video_url)
+    if not video_id:
+        return "❌ Invalid YouTube URL."
+
+    try:
+        transcript = YouTubeTranscriptApi.get_transcript(video_id)
+        return " ".join([entry['text'] for entry in transcript])
+    except (NoTranscriptFound, TranscriptsDisabled, VideoUnavailable) as e:
+        return f"❌ {str(e)}"
+    except Exception:
+        try:
+            transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
+            transcript = transcript_list.find_transcript(['en'])
+            return " ".join([entry['text'] for entry in transcript.fetch()])
+        except Exception as e2:
+            return f"❌ Error fetching transcript: {str(e2)}"
+
+# Split long text safely into small chunks
+def split_text(text, max_words=500):
+    words = text.split()
+    chunks = []
+    for i in range(0, len(words), max_words):
+        chunk = " ".join(words[i:i+max_words])
+        chunks.append(chunk)
+    return chunks
+
+# Main function: fetch + summarize any transcript length
+def summarize_youtube_video(url):
+    transcript = fetch_transcript(url)
+    if transcript.startswith("❌"):
+        return transcript
+
+    try:
+        words = transcript.split()
+        word_count = len(words)
+
+        if word_count <= 500:
+            summary = text_summary(transcript, max_length=150, min_length=60, do_sample=False)
+            return summary[0]['summary_text']
+
+        chunks = split_text(transcript, max_words=500)
+        partial_summaries = []
+
+        for chunk in chunks:
+            summary = text_summary(chunk, max_length=150, min_length=60, do_sample=False)
+            partial_summaries.append(summary[0]['summary_text'])
+
+        combined_summary = " ".join(partial_summaries)
+
+        # Final summary of all summaries
+        final_summary = text_summary(combined_summary, max_length=200, min_length=80, do_sample=False)
+        return final_summary[0]['summary_text']
+
+    except Exception as e:
+        return f"❌ Error during summarization: {str(e)}"
+
+# Gradio UI
+gr.close_all()
+
+demo = gr.Interface(
+    fn=summarize_youtube_video,
+    inputs=gr.Textbox(label="Enter YouTube Video URL", lines=1, placeholder="https://youtu.be/..."),
+    outputs=gr.Textbox(label="Video Summary", lines=10),
+    title="@RosangenAi Project 2: YouTube Video Summarizer",
+    description="Paste any YouTube video link. This app will fetch and summarize even long transcripts using Hugging Face models."
+)
+
+demo.launch()