Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| from txtai.pipeline import Summary, Textractor | |
| from PyPDF2 import PdfReader | |
| from deep_translator import GoogleTranslator | |
| st.set_page_config(layout="wide") | |
| def text_summary(text, translate_fa, maxlength=None): | |
| if(len(text) > 2000): | |
| translatedtext1 = GoogleTranslator(source='auto', target='en').translate(text[0:2000]) | |
| translatedtext2 = GoogleTranslator(source='auto', target='en').translate(text[2000:(len(text))]) | |
| translatedtext = translatedtext1 + translatedtext2 | |
| print(translatedtext1 + " .....WITH..... " + translatedtext2) | |
| else: | |
| translatedtext = GoogleTranslator(source='auto', target='en').translate(text) | |
| print(translatedtext) | |
| #create summary instance | |
| summary = Summary() | |
| result = summary(translatedtext) | |
| if translate_fa: | |
| result = GoogleTranslator(source='auto', target='fa').translate(result) | |
| return result | |
| def extract_text_from_pdf(file_path): | |
| # Open the PDF file using PyPDF2 | |
| with open(file_path, "rb") as f: | |
| reader = PdfReader(f) | |
| page = reader.pages[0] | |
| text = page.extract_text() | |
| return text | |
| choice = st.selectbox("Select your choice", ["Summarize Text", "Summarize Document"]) | |
| translate_fa = st.toggle('Translate to Persian', value=True) | |
| if choice == "Summarize Text": | |
| st.subheader("Summarize Text") | |
| input_text = st.text_area("Enter your text here") | |
| if input_text is not None: | |
| if st.button("Summarize Text"): | |
| col1, col2 = st.columns([1,1]) | |
| with col1: | |
| st.markdown("**Summary Result**") | |
| result = text_summary(input_text, translate_fa) | |
| st.success(result) | |
| elif choice == "Summarize Document": | |
| st.subheader("Summarize Document") | |
| input_file = st.file_uploader("Upload your document here", type=['pdf']) | |
| if input_file is not None: | |
| if st.button("Summarize Document"): | |
| with open("doc_file.pdf", "wb") as f: | |
| f.write(input_file.getbuffer()) | |
| col1, col2 = st.columns([1,1]) | |
| with col1: | |
| st.info("File uploaded successfully") | |
| extracted_text = extract_text_from_pdf("doc_file.pdf") | |
| st.markdown("**Extracted Text is Below:**") | |
| st.info(extracted_text) | |
| with col2: | |
| st.markdown("**Summary Result**") | |
| text = extract_text_from_pdf("doc_file.pdf") | |
| doc_summary = text_summary(text, translate_fa) | |
| st.success(doc_summary) | |