| # import urllib.request | |
| # import streamlit as st | |
| # import os | |
| # from datasets import load_from_disk | |
| # import requests | |
| # with urllib.request.urlopen('https://huggingface.co/datasets/Seetha/Visualization') as response: | |
| # data = response.read() | |
| # with open('./level2.json','r+') as fi: | |
| # data = fi.read() | |
| # st.write('before change', data) | |
| # fi.seek(0) | |
| # fi.write('Hello world!') | |
| # fi.truncate() | |
| # st.write(os.path.abspath("./level2.json")) | |
| # with open('./level2.json','w') as dat: | |
| # dat.write('hello hello') | |
| # #st.write(data_after) | |
| # # bin_file = open('./level2.json', 'rb') | |
| # # # Execute the request | |
| # # response = requests.post('https://huggingface.co/datasets/Seetha/Visualization', files={'file': bin_file}) | |
| # # # Close the file | |
| # # bin_file.close() | |
| # from datasets import load_dataset | |
| # # Load the dataset | |
| # dataset = load_dataset("Seetha/Visualization") | |
| # # Make changes to the dataset | |
| # # ... | |
| # # Save the changed dataset to a file | |
| # dataset.save_to_disk('./level.json') | |
| # # In your Streamlit app, load the dataset from the file | |
| # dataset = load_dataset('json', data_files='./level.json') | |
| import streamlit as st | |
| import urllib # the lib that handles the url stuff | |
| from PyPDF2 import PdfReader | |
| text_list = [] | |
| target_url = 'https://huggingface.co/datasets/Seetha/Visualization/raw/main/AFLAC_Wyatt_notag.pdf' | |
| if st.button('PDF1'): | |
| data = urllib.request.urlopen(target_url) | |
| for line in data.read(): | |
| st.write(line) | |
| if data is not None: | |
| reader = PdfReader(data) | |
| for page in reader.pages: | |
| text = page.extract_text() | |
| text_list.append(text) | |
| st.write(text_list) | |
| else: | |
| st.error("Please upload your own PDF to be analyzed") | |
| st.stop() | |
| else: | |
| st.write('Goodbye') | |