Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
 import nltk
+from youtube_transcript_api import YouTubeTranscriptApi
 
 # Download NLTK data
 nltk.download('punkt')
@@ -12,11 +13,21 @@ captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-ba
 tokenizer = AutoTokenizer.from_pretrained("fabiochiu/t5-base-tag-generation")
 model = AutoModelForSeq2SeqLM.from_pretrained("fabiochiu/t5-base-tag-generation")
 
+# Function to fetch YouTube transcript
+def fetch_transcript(url):
+ video_id = url.split('watch?v=')[-1]
+ try:
+ transcript = YouTubeTranscriptApi.get_transcript(video_id)
+ transcript_text = ' '.join([entry['text'] for entry in transcript])
+ return transcript_text
+ except Exception as e:
+ return str(e)
+
 # Streamlit app title
 st.title("Multi-purpose Machine Learning App")
 
 # Create tabs for different functionalities
-tab1, tab2 = st.tabs(["Image Captioning", "Text Tag Generation"])
+tab1, tab2, tab3 = st.tabs(["Image Captioning", "Text Tag Generation", "YouTube Transcript"])
 
 # Image Captioning Tab
 with tab1:
@@ -71,4 +82,22 @@ with tab2:
  else:
  st.warning("Please enter some text to generate tags.")
 
-# To run this app, save this code to a file (e.g., `app.py`) and run `streamlit run app.py` in your terminal.
+# YouTube Transcript Tab
+with tab3:
+ st.header("YouTube Video Transcript Extractor")
+ 
+ # Input for YouTube URL
+ youtube_url = st.text_input("Enter YouTube URL:")
+ 
+ # Button to get transcript
+ if st.button("Get Transcript"):
+ if youtube_url:
+ transcript = fetch_transcript(youtube_url)
+ if "error" not in transcript.lower():
+ st.success("Transcript successfully fetched!")
+ st.text_area("Transcript", transcript, height=300)
+ else:
+ st.error(f"An error occurred: {transcript}")
+ else:
+ st.warning("Please enter a URL.")
+