Spaces:
Running
Running
| import streamlit as st | |
| import pymupdf as fitz | |
| import pyperclip | |
| from utils.audit.audit_doc import audit_descriptif | |
| # Function to extract text from PDF | |
| def extract_text_from_pdf(file): | |
| document = fitz.open(stream=file.read(), filetype="pdf") | |
| full_text = "" | |
| for page_num in range(len(document)): | |
| page = document.load_page(page_num) | |
| text = page.get_text("text") | |
| full_text += text | |
| return full_text | |
| # Function to classify file type | |
| def classify_file(file): | |
| if file.type.startswith("image/"): | |
| return "image" | |
| elif file.type == "application/pdf": | |
| return "pdf" | |
| elif file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document": | |
| return "word" | |
| elif file.type.startswith("audio/"): | |
| return "audio" | |
| elif file.type.startswith("text/"): | |
| return "text" | |
| else: | |
| return "unknown" | |
| def main(): | |
| # Streamlit app | |
| st.title("AUDIT DES DOCUMENTS") | |
| if "audit" not in st.session_state: | |
| st.session_state.audit = {} | |
| if "name_file" not in st.session_state: | |
| st.session_state.name_file = "" | |
| # File uploader | |
| uploaded_file = st.file_uploader("Télécharger un documents") | |
| if uploaded_file is not None: | |
| type = classify_file(uploaded_file) | |
| if type == "pdf": | |
| if st.session_state.name_file != uploaded_file.name: | |
| st.session_state.name_file = uploaded_file.name | |
| with st.spinner("Analyse du document..."): | |
| st.session_state.audit = audit_descriptif(uploaded_file) | |
| audit = st.session_state.audit | |
| #global audit | |
| audit_simplified = { | |
| "Nombre de pages": audit["number_of_pages"], | |
| "Nombre d'images": audit["number_of_images"], | |
| "Nombre de liens": audit["number_of_links"], | |
| "Nombre de tableaux": audit["number_of_tables"], | |
| "Nombre de tokens": audit["number_of_tokens"], | |
| "Nombre de mots": audit["number_of_words"] | |
| } | |
| well_formatted_audit = "Audit descriptif\n" | |
| for key, value in audit_simplified.items(): | |
| well_formatted_audit += f"- {key}: {value}\n" | |
| st.write("### Audit de tout le document") | |
| st.code(well_formatted_audit) | |
| #audit par page | |
| with st.expander("Audit par page"): | |
| number = st.number_input("Numéro de page", min_value=1, max_value=audit["number_of_pages"], value=1) | |
| audit_page = audit[f"page_{number-1}"] | |
| audit_page = { | |
| "Nombre d'images": audit_page["number_of_images"], | |
| "Nombre de liens": audit_page["number_of_links"], | |
| "Nombre de tableaux": audit_page["number_of_tables"], | |
| "Nombre de tokens": audit_page["number_of_tokens"], | |
| "Nombre de mots": audit_page["number_of_words"] | |
| } | |
| well_formatted_audit_page = "Audit descriptif\n" | |
| for key, value in audit_page.items(): | |
| well_formatted_audit_page += f"- {key}: {value}\n" | |
| st.code(well_formatted_audit_page) | |
| # # Button to copy text to clipboard | |
| # if st.button("Copy to Clipboard"): | |
| # pyperclip.copy(audit) | |
| # st.success("Text copied to clipboard successfully!") | |
| # else: | |
| # st.info("Please upload a PDF file to extract text.") | |
| if __name__ == "__main__": | |
| main() | |