Upload 4 files

app.py

@@ -0,0 +1,50 @@
+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.")

extractor.py

@@ -0,0 +1,41 @@
+import re
+
+def extract_multi_records(text):
+    lines = text.split("\n")
+    data = []
+
+    for line in lines:
+        line = line.strip()
+
+        # Skip empty lines
+        if not line:
+            continue
+
+        words = line.split()
+
+        # Skip header row
+        if any(word.lower() in ["name", "date", "amount"] for word in words):
+            continue
+
+        # Find date
+        date = re.findall(r'\d{2}[-/]\d{2}[-/]\d{4}', line)
+
+        # Find amount (last number in line)
+        amount = re.findall(r'\d+', line)
+
+        # Extract name (first word only if valid)
+        name = words[0] if words else "Unknown"
+
+        # Validate name (should not be numeric or date)
+        if name.isdigit():
+            continue
+
+        # Save record if valid
+        if date and amount:
+            data.append({
+                "Name": name,
+                "Date": date[0],
+                "Amount": amount[-1]
+            })
+
+    return data

packages.txt

@@ -0,0 +1 @@
+tesseract-ocr

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+pytesseract
+opencv-python-headless
+numpy
+pandas
+pillow
+openpyxl