Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import os | |
| import tempfile | |
| import PyPDF2 | |
| def main(): | |
| st.title("PDF Metadata Extractor") | |
| with st.expander("ℹ️ About"): | |
| st.markdown("""This app extracts metadata from PDF files. | |
| You can upload one or more PDF files and view their metadata.""") | |
| st.markdown("""(c) 2024 [Louie F. Cervantes, M.Eng. (Informaation Enfineering)] | |
| (https://huggingface.co/spaces/louiecerv)""") | |
| # Folder uploader (using the st.file_uploader with multiple file selection) | |
| uploaded_files = st.file_uploader("Upload PDF files:", type="pdf", accept_multiple_files=True) | |
| if not uploaded_files: | |
| st.warning("Please upload PDF files.") | |
| return | |
| try: | |
| # Create a temporary directory | |
| with tempfile.TemporaryDirectory() as temp_dir: | |
| pdf_files = [] | |
| # Save uploaded files to the temporary directory and collect their names | |
| for uploaded_file in uploaded_files: | |
| with open(os.path.join(temp_dir, uploaded_file.name), "wb") as f: | |
| f.write(uploaded_file.read()) | |
| pdf_files.append(uploaded_file.name) | |
| if not pdf_files: | |
| st.warning("No PDF files found in the uploaded selection.") | |
| return | |
| st.subheader("Detected PDF Files:") | |
| for pdf_file in pdf_files: | |
| st.write(pdf_file) | |
| if st.button("Extract Metadata"): | |
| st.subheader("PDF Metadata:") | |
| for pdf_file in pdf_files: | |
| try: | |
| pdf_path = os.path.join(temp_dir, pdf_file) | |
| with open(pdf_path, 'rb') as f: | |
| pdf_reader = PyPDF2.PdfReader(f) | |
| pdf_info = pdf_reader.metadata | |
| st.write(f"**File:** {pdf_file}") | |
| for key, value in pdf_info.items(): | |
| st.write(f"{key}: {value}") | |
| st.write("---") | |
| except Exception as e: | |
| st.error(f"Error processing {pdf_file}: {e}") | |
| except Exception as e: | |
| st.error(f"An error occurred: {e}") | |
| return | |
| if __name__ == "__main__": | |
| main() |