Update app.py

app.py

@@ -1,50 +1,78 @@
-import streamlit as st
-import cv2
-import pytesseract
-import numpy as np
-import pandas as pd
-from extractor import extract_multi_records
-import pytesseract
-# ✅ Tesseract path (IMPORTANT)
-# pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
-
-st.set_page_config(page_title="Document Extractor", layout="wide")
-
-st.title("📄 Smart Multi-Document Data Extractor")
-
-uploaded_file = st.file_uploader("Upload Image", type=["jpg", "png", "jpeg"])
-
-# OCR Function
-def extract_text(img):
-    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-    return pytesseract.image_to_string(gray)
-
-if uploaded_file:
-    file_bytes = np.asarray(bytearray(uploaded_file.read()), dtype=np.uint8)
-    img = cv2.imdecode(file_bytes, 1)
-
-    st.image(img, caption="Uploaded Image", use_container_width=True)
-
-    if st.button("🚀 Extract Data"):
-
-        with st.spinner("Processing..."):
-
-            text = extract_text(img)
-
-            # 🔥 Multi-record extraction
-            records = extract_multi_records(text)
-
-            df = pd.DataFrame(records)
-
-        st.success("✅ Extraction Complete!")
-
-        if not df.empty:
-            st.dataframe(df)
-
-            # Save Excel
-            df.to_excel("output.xlsx", index=False)
-
-            with open("output.xlsx", "rb") as f:
-                st.download_button("📥 Download Excel", f, file_name="output.xlsx")
-        else:
-            st.warning("⚠️ No structured data found. Try a clearer image.")
+import streamlit as st
+import cv2
+import pytesseract
+import numpy as np
+import pandas as pd
+from extractor import extract_multi_records
+
+st.set_page_config(page_title="Smart Multi-Document Data Extractor", layout="wide")
+
+st.title("📄 Smart Multi-Document Data Extractor")
+
+# OCR Function (Improved)
+def extract_text(img):
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    gray = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY)[1]
+    return pytesseract.image_to_string(gray)
+
+# File uploader (multiple files supported)
+uploaded_files = st.file_uploader(
+    "Upload Images",
+    type=["jpg", "png", "jpeg"],
+    accept_multiple_files=True
+)
+
+if uploaded_files:
+
+    all_data = []
+
+    for uploaded_file in uploaded_files:
+        try:
+            file_bytes = np.asarray(bytearray(uploaded_file.read()), dtype=np.uint8)
+            img = cv2.imdecode(file_bytes, 1)
+
+            # Check image valid
+            if img is None:
+                st.error(f"❌ Could not read image: {uploaded_file.name}")
+                continue
+
+            # Show image
+            st.image(img, caption=uploaded_file.name, use_container_width=True)
+
+            # Extract text
+            text = extract_text(img)
+
+            if not text.strip():
+                st.warning(f"⚠️ No text found in {uploaded_file.name}")
+                continue
+
+            # Extract structured data
+            records = extract_multi_records(text)
+
+            if not records:
+                st.warning(f"⚠️ No structured data found in {uploaded_file.name}")
+                continue
+
+            all_data.extend(records)
+
+        except Exception as e:
+            st.error(f"❌ Error processing {uploaded_file.name}: {str(e)}")
+
+    # Show final data
+    if all_data:
+        df = pd.DataFrame(all_data)
+
+        st.success("✅ Extraction Complete!")
+        st.dataframe(df)
+
+        # Download Excel
+        df.to_excel("output.xlsx", index=False)
+
+        with open("output.xlsx", "rb") as f:
+            st.download_button(
+                "📥 Download Excel",
+                f,
+                file_name="output.xlsx"
+            )
+    else:
+        st.warning("⚠️ No data extracted from uploaded files.")