| import streamlit as st | |
| import PyPDF2 | |
| import tempfile | |
| import os | |
| def extract_text_from_pdf(uploaded_file): | |
| text = "" | |
| with tempfile.NamedTemporaryFile(delete=False) as tmp_file: | |
| tmp_file.write(uploaded_file.read()) | |
| tmp_file.seek(0) | |
| with open(tmp_file.name, "rb") as f: | |
| reader = PyPDF2.PdfReader(f) | |
| num_pages = len(reader.pages) | |
| for page_num in range(num_pages): | |
| page = reader.pages[page_num] | |
| text += page.extract_text() | |
| return text | |
| def main(): | |
| st.title("PDF Text Extractor") | |
| st.write("Upload your pdf:") | |
| uploaded_file = st.file_uploader("Select PDF file", type=['pdf']) | |
| if uploaded_file is not None: | |
| st.write("PDF file Upload:", uploaded_file.name) | |
| st.write("File size:", uploaded_file.size) | |
| if st.button("Extract Text"): | |
| text = extract_text_from_pdf(uploaded_file) | |
| st.write("Extracted Text:") | |
| st.write(text) | |
| if __name__ == "__main__": | |
| main() | |