app.py

import streamlit as st
from textsumm import summarizer
from pdfsum import extract_text_from_pdf, summarize_text, split_text_into_chunks
from pdfpass import remove_pdf_password
from papersearch import fetch_papers, filter_papers_by_year
from io import BytesIO
from datetime import datetime
from pypdf import PdfReader, PdfWriter

# Streamlit App Config
st.set_page_config(page_title="PDF Tools Suite", page_icon="📄", layout="wide")

# Sidebar Navigation
st.sidebar.title("📄 PDF Tools Suite")
page = st.sidebar.radio("Select a tool", ["Text Summarizer", "PDF Summarizer", "PDF Password Remover", "Research Paper Search", "PDF Merger", "PDF Splitter", "PDF to Text Converter"])

# Tool: Text Summarizer
if page == "Text Summarizer":
    st.title("📝 Text Summarizer")
    user_input = st.text_area("Enter text to summarize")
    if st.button("Summarize"):
        summary = summarizer(user_input, max_length=130, min_length=30, do_sample=False)
        st.subheader("Summary")
        st.write(summary[0]["summary_text"])

# Tool: PDF Summarizer
elif page == "PDF Summarizer":
    st.title("📜 PDF Summarizer")
    uploaded_file = st.file_uploader("Upload your PDF", type=["pdf"])
    if uploaded_file is not None:
        pdf_text = extract_text_from_pdf(uploaded_file)
        chunks = split_text_into_chunks(pdf_text)
        summaries = summarize_text(chunks)
        full_summary = " ".join(summaries)
        st.subheader("Summary")
        st.write(full_summary)

# Tool: PDF Password Remover
elif page == "PDF Password Remover":
    st.title("🔑 Remove PDF Password")
    uploaded_file = st.file_uploader("Choose a password-protected PDF", type=["pdf"])
    password = st.text_input("Enter the PDF password", type="password")
    if uploaded_file and password and st.button("Remove Password"):
        output = remove_pdf_password(uploaded_file, password)
        if isinstance(output, BytesIO):
            st.success("Password removed successfully!")
            st.download_button("Download PDF", data=output, file_name="unlocked_pdf.pdf", mime="application/pdf")
        else:
            st.error(f"Error: {output}")

# Tool: Research Paper Search
elif page == "Research Paper Search":
    st.title("🔍 Research Paper Search (arXiv)")
    query = st.text_input("Enter topic or keywords", placeholder="e.g., machine learning")
    max_results = st.slider("Number of results", 1, 50, 10)
    col1, col2 = st.columns(2)
    with col1:
        start_year = st.number_input("Start Year", min_value=1900, max_value=datetime.now().year, value=2000)
    with col2:
        end_year = st.number_input("End Year", min_value=1900, max_value=datetime.now().year, value=datetime.now().year)
    if st.button("Search"):
        papers = fetch_papers(query, max_results)
        papers_filtered = filter_papers_by_year(papers, start_year, end_year)
        if papers_filtered:
            for idx, paper in enumerate(papers_filtered, start=1):
                st.write(f"### {idx}. {paper['title']}")
                st.write(f"**Authors**: {', '.join(paper['authors'])}")
                st.write(f"**Published**: {paper['published']}")
                st.write(f"[Read More]({paper['link']})")
                st.write("---")
        else:
            st.warning("No papers found in the selected range.")

# Tool: PDF Merger
elif page == "PDF Merger":
    st.title("📎 Merge Multiple PDFs")
    uploaded_files = st.file_uploader("Upload multiple PDF files", type=["pdf"], accept_multiple_files=True)
    if uploaded_files and st.button("Merge PDFs"):
        pdf_writer = PdfWriter()
        for file in uploaded_files:
            pdf_reader = PdfReader(file)
            for page in pdf_reader.pages:
                pdf_writer.add_page(page)
        output = BytesIO()
        pdf_writer.write(output)
        output.seek(0)
        st.download_button("Download Merged PDF", data=output, file_name="merged.pdf", mime="application/pdf")

# Tool: PDF Splitter
elif page == "PDF Splitter":
    st.title("✂️ Split PDF into Pages")
    uploaded_file = st.file_uploader("Upload a PDF", type=["pdf"])
    if uploaded_file:
        pdf_reader = PdfReader(uploaded_file)
        for i, page in enumerate(pdf_reader.pages):
            pdf_writer = PdfWriter()
            pdf_writer.add_page(page)
            output = BytesIO()
            pdf_writer.write(output)
            output.seek(0)
            st.download_button(f"Download Page {i+1}", data=output, file_name=f"page_{i+1}.pdf", mime="application/pdf")

# Tool: PDF to Text Converter
elif page == "PDF to Text Converter":
    st.title("📜 Extract Text from PDF")
    uploaded_file = st.file_uploader("Upload a PDF", type=["pdf"])
    if uploaded_file:
        pdf_text = extract_text_from_pdf(uploaded_file)
        st.text_area("Extracted Text", pdf_text, height=300)