Update app.py

app.py

@@ -47,57 +47,34 @@ st.markdown(
 
 
 #---------------------PDF OVERVIEW----------------------
-def get_pdf_details(folder_path):
-    pdf_details = []
-    for filename in os.listdir(folder_path):
-        if filename.lower().endswith('.pdf'):
-            pdf_path = os.path.join(folder_path, filename)
-            try:
-                with open(pdf_path, "rb") as file:
-                    pdf_reader = PdfReader(file)
-                    page_count = len(pdf_reader.pages)
-                    pdf_details.append({"Berkas Putusan": filename, "Jumlah Halaman": page_count})
-            except Exception as e:
-                st.warning(f"Could not read {filename}: {str(e)}")
-    return pdf_details
-
-pdf_list = get_pdf_details(pdf_folder)
-pdf_df = pd.DataFrame(pdf_list)
-
-col1, col2= st.columns(2)
-with col1:
-    if not pdf_df.empty:
-        with st.expander('PDF Overview'):
-            st.dataframe(pdf_df)
-    else:
-        st.warning("No PDFs found in the specified folder.")
-       
-
-#---------------------MULTISELECT AND TEXT EXTRACTION----------------------
-
-pdf_files = [f for f in os.listdir(pdf_folder) if f.lower().endswith('.pdf')]
-with col2:
-    with st.expander('PDF Documents'):
-        selected_pdfs = st.multiselect("Select PDFs", pdf_files)
-    def extract_text_from_pdf(uploaded_file, start_page, end_page):
-        text = extract_text(uploaded_file, page_numbers=range(start_page, end_page+1))
-        return text
-
-pdf_texts = {}
-
-for selected_pdf in selected_pdfs:
-    pdf_path = os.path.join(pdf_folder, selected_pdf)
-    uploaded_file = open(pdf_path, 'rb')
-    pdf_reader = PdfReader(uploaded_file)
-    total_pages = len(pdf_reader.pages)
-    
-    # Extract text from the first 3 pages and the last 3 pages
-    extracted_text_first = extract_text_from_pdf(uploaded_file, 1, min(3, total_pages))
-    extracted_text_last = extract_text_from_pdf(uploaded_file, max(1, total_pages - 2), total_pages)
-    
-    extracted_text = extracted_text_first + "\n" + extracted_text_last
-    
-    pdf_texts[selected_pdf] = extracted_text
+# Function to read PDF file
+def read_pdf(file):
+    try:
+        pdf_reader = PdfFileReader(file)
+        num_pages = pdf_reader.numPages
+        pdf_text = ""
+        for page_number in range(num_pages):
+            page = pdf_reader.getPage(page_number)
+            pdf_text += page.extractText()
+        return pdf_text
+    except PdfReadError as e:
+        st.error(f"Error reading PDF: {e}")
+        return None
+
+# Sidebar
+st.sidebar.title("PDF Viewer")
+
+# File uploader for PDFs
+uploaded_files = st.sidebar.file_uploader("Upload PDF", type=["pdf"], accept_multiple_files=True)
+
+# Display uploaded PDFs
+if uploaded_files:
+    for uploaded_file in uploaded_files:
+        file_details = {"Filename": uploaded_file.name, "Filesize": uploaded_file.size}
+        st.sidebar.write(file_details)
+        pdf_text = read_pdf(uploaded_file)
+        if pdf_text:
+            st.write(pdf_text)