Update app.py

app.py

@@ -8,6 +8,7 @@ from pydantic import BaseModel, Field
 import fitz  
 import json
 from PIL import Image
+
 ocr = PaddleOCR(use_angle_cls=True, lang='es')
 
 st.set_page_config(layout="wide")
@@ -57,26 +58,41 @@ st.title("Vehicle Information Extractor")
 st.write("Upload a PDF file to extract vehicle information.")
 
 uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
+use_default = st.checkbox("Use Default Pdf")
+
+doc = None
+
+if use_default:
+    default_pdf_path = "pedido V.O.pdf"
+    if os.path.exists(default_pdf_path):
+        print("Present")
+        doc = fitz.open(default_pdf_path)
+        st.write("Using default PDF:")
+    else:
+        st.error("Default PDF not found.")
+
+else:
+    if uploaded_file is not None:
+        with open("temp.pdf", "wb") as f:
+            f.write(uploaded_file.read())
+        doc = fitz.open("temp.pdf")
+        st.write("Uploaded PDF:")
 
-if uploaded_file is not None:
-    with open("temp.pdf", "wb") as f:
-        f.write(uploaded_file.read())
-
+if doc:
     col1, col2 = st.columns(2)
 
     with col1:
-        doc = fitz.open("temp.pdf")
-        st.write("Uploaded PDF:")
         for page_num in range(len(doc)):
             page = doc.load_page(page_num)
             pix = page.get_pixmap()
             img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
-            st.image(img, caption=f"Page {page_num+1}", use_column_width=True)
+            st.image(img, caption=f"Page {page_num + 1}", use_column_width=True)
 
-    content = ocr.ocr("temp.pdf")
+    # Perform OCR
+    ocr_result = ocr.ocr(default_pdf_path if use_default else "temp.pdf")
 
     extracted_text = []
-    for page in content:
+    for page in ocr_result:
         for result in page:
             text = result[1][0]
             extracted_text.append(text)
@@ -104,4 +120,4 @@ if uploaded_file is not None:
 
     with col2:
         st.write("Extracted Vehicle Information (Table):")
-        st.table(output)
+        st.table(output)