import streamlit as st
from bs4 import BeautifulSoup
import requests
from transformers import pipeline
import pandas as pd

# Load pre-trained question-answering model (replace with a suitable model)
qa_model = pipeline("question-answering")

@st.cache(allow_output_mutation=True)
def fetch_past_papers(subject_code, exam_year, variant, session):
    """Fetches past papers from the Cambridge Assessment International Education website."""
    url = f"https://www.cambridgeinternational.org/programmes-and-qualifications/cambridge-o-level/{subject_code}/past-papers-and-mark-schemes/"
    response = requests.get(url)
    soup = BeautifulSoup(response.content, "html.parser")

    # Extract relevant past paper based on exam year, variant, and session
    past_papers = soup.find_all("a", href=lambda href: href and href.startswith(f"/programmes-and-qualifications/cambridge-o-level/{subject_code}/past-papers-and-mark-schemes/{exam_year}/{session}/"))
    for paper in past_papers:
        if paper.text.strip() == f"{variant} Paper {variant}":
            return paper["href"]

    return None

def extract_questions_and_answers(past_paper_url):
    """Extracts questions and answers from the past paper PDF using a combination of OCR and question-answering."""
    # Replace with a suitable OCR library (e.g., PyMuPDF, Tesseract) and ensure it's installed
    # This example demonstrates the overall approach, assuming OCR functionality
    # Replace the placeholder code with actual OCR processing
    # ocr_result = ocr_process(past_paper_url)  # Replace with your OCR implementation

    # Process the extracted text using the question-answering model
    questions_and_answers = []
    for paragraph in ocr_result.split("\n\n"):
        question = qa_model.question_answering(paragraph, question="What is the question?")["question"]
        if question:
            answer = qa_model.question_answering(paragraph, question=question)["answer"]
            questions_and_answers.append({"question": question, "answer": answer})

    return questions_and_answers

def main():
    """Streamlit app to interact with the user and display results."""
    st.title("Cambridge O-Level Exam Q&A Extractor")

    subject_code = st.text_input("Subject Code")
    exam_year = st.selectbox("Exam Year", [str(year) for year in range(2015, 2026)])
    variant = st.selectbox("Variant", ["1", "2", "3"])
    session = st.selectbox("Session", ["May-Jun", "Oct-Nov"])

    if st.button("Search"):
        past_paper_url = fetch_past_papers(subject_code, exam_year, variant, session)
        if past_paper_url:
            questions_and_answers = extract_questions_and_answers(past_paper_url)
            if questions_and_answers:
                df = pd.DataFrame(questions_and_answers)
                st.dataframe(df)
            else:
                st.error("No questions and answers found in the extracted text.")
        else:
            st.error("Past paper not found for the specified criteria.")

if __name__ == "__main__":
    main()