app.py

from llama_parse import LlamaParse
from llama_index.core import SimpleDirectoryReader
import os
from dotenv import load_dotenv
load_dotenv()
import tempfile
import requests
import streamlit as st

read_file_path = "160/task_for_you.pdf"
def check_pdf(read_file_path):
    try:
        parser = LlamaParse(result_type="markdown", api_key=os.environ['LLAMA_CLOUD_API_KEY'], ignore_errors=False)
        file_extractor = {".pdf": parser}
        markdown_data = SimpleDirectoryReader(input_files=[read_file_path], file_extractor=file_extractor).load_data()
        if markdown_data == []:
            raise Exception("No markdown data found")
        return True
    except Exception as e:
        print(f"An error occurred: {e}")
        return False

def download_file_from_url(url, filename):
    print(f"Downloading file from {url} to {filename}")
    os.makedirs(os.path.dirname(filename), exist_ok=True)
    response = requests.get(url, stream=True)
    if response.status_code == 200:
        with open(filename, 'wb') as file:
            for chunk in response.iter_content(chunk_size=1024):
                file.write(chunk)
        print(f"File downloaded and saved as {filename}")
        return True
    else:
        print(f"Failed to download file. Status code: {response.status_code}")
        return False
        
url = st.text_input("Enter URL", key="url")

if url:
    with tempfile.TemporaryDirectory() as temp_dir:

        if download_file_from_url(url, os.path.join(temp_dir, "task_for_you.pdf")):
            if check_pdf(os.path.join(temp_dir, "task_for_you.pdf")):
                st.success("File downloaded successfully")
            else:
                st.error("File is corrupted or not a PDF file")
        else:
            st.error("Failed to download file")