import streamlit as st
from transformers import pipeline
from heapq import nlargest
from keybert import KeyBERT

# Function to extract text from SRT-formatted text
def extract_text_from_srt_text(srt_text):
    lines = srt_text.strip().split("\n\n")  # Split by empty lines to separate subtitles
    texts = [subtitle.split("\n")[2] for subtitle in lines if subtitle.strip()]  # Extract text from the third line of each subtitle
    return " ".join(texts)

# Function to generate summary from text
def generate_summary(text, summary_length):
    summarizer = pipeline("summarization")
    summary = summarizer(text, max_length=summary_length, min_length=30, do_sample=False)
    summary_text = summary[0]["summary_text"]
    return summary_text

# Function to extract top 4 topics from text
def extract_top_topics(text, n_top_topics):
    model = KeyBERT('distilbert-base-nli-mean-tokens')
    keywords = model.extract_keywords(text, keyphrase_ngram_range=(1, 3), stop_words='english', use_maxsum=True, nr_candidates=20, top_n=n_top_topics)
    return keywords

# Streamlit app
st.title("SRT Summarization")

# Logo image URL
logo_url = "https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQ6uQl0omK_PHXBbyaCHdmh3VjCo_Yvgwavmcs5XRF9Rkjx5FpflxyO4yfux6d2ojKsCOA&usqp=CAU"  # Replace with your logo image URL

# Display logo
st.image(logo_url, width=364)

# Text area for user to input SRT-formatted text
srt_text_input = st.text_area("Paste SRT-formatted text here:")

# Button to trigger summarization
if st.button("Summarize"):
    # Check if text area is not empty
    if srt_text_input.strip():
        # Show loading spinner while processing
        with st.spinner("Summarizing..."):
            # Extract text from SRT-formatted text
            text_to_summarize = extract_text_from_srt_text(srt_text_input)
            # Generate summary
            summary = generate_summary(text_to_summarize, 150)  # You can adjust the summary length as needed
            # Display summary
            st.subheader("Summary:")
            st.write(summary)
            # Extract top 4 topics
            top_topics = extract_top_topics(text_to_summarize, 4)
            # Display top 4 topics
            st.subheader("Top 4 Topics:")
            for topic in top_topics:
                st.write(f"- {topic}")
    else:
        st.warning("Please enter some SRT-formatted text.")