Update app.py

app.py

@@ -1,71 +1,53 @@
 import streamlit as st
 import pytesseract
-from pdf2image import convert_from_path
 from PIL import Image
-import pandas as pd
-from docx import Document
-import io
-import tempfile
+import docx
+import pdf2image
 
-# OCR function to convert image-based PDF to text
-def extract_text_from_image_pdf(uploaded_file):
-    # Save the uploaded file to a temporary file
-    with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
-        tmp_file.write(uploaded_file.read())  # Write the file content to the temporary file
-        tmp_file_path = tmp_file.name  # Get the temporary file path
-    
-    # Convert PDF to images using pdf2image
-    images = convert_from_path(tmp_file_path)
-    extracted_text = []
-    
-    for image in images:
-        # Use pytesseract to do OCR on the image
-        text = pytesseract.image_to_string(image)
-        extracted_text.append(text)
-    
-    return "\n".join(extracted_text)
+# Set Tesseract path if not set already
+pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
 
-# Save text to Word document
-def save_to_word(text, output_filename):
-    doc = Document()
-    doc.add_paragraph(text)
-    doc.save(output_filename)
+def extract_text_from_image_pdf(pdf_file):
+  """Extracts text from a PDF by converting it to images and performing OCR."""
 
-# Save text to Excel document
-def save_to_excel(text, output_filename):
-    # Split the text into rows and columns (simplified, adjust based on your data)
-    rows = text.split("\n")
-    table_data = [row.split() for row in rows if row]  # You can adjust this for proper column splitting
-    
-    df = pd.DataFrame(table_data)
-    df.to_excel(output_filename, index=False)
+  # Read the PDF file
+  with open(pdf_file, 'rb') as f:
+    pdf_bytes = f.read()
+
+  # Extract images from the PDF
+  images = pdf2image.convert_from_bytes(pdf_bytes)
+
+  # Perform OCR on each image and combine the text
+  extracted_text = ''
+  for image in images:
+    text = pytesseract.image_to_string(image)
+    extracted_text += text + '\n'  # Add newline for better readability
+
+  return extracted_text
 
-# Main function
 def main():
-    st.title("PDF (Image-based) to Text-based Document Converter")
+  """Streamlit app for converting PDF images to text."""
 
-    # File uploader widget in Streamlit
-    uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
+  # Title and description
+  st.title("PDF to Text Converter")
+  st.subheader("Convert your PDF images to editable text documents.")
 
-    if uploaded_file is not None:
-        # Convert image-based PDF to text using OCR
-        extracted_text = extract_text_from_image_pdf(uploaded_file)
+  # Upload PDF file
+  uploaded_file = st.file_uploader("Choose a PDF file to convert:", type="pdf")
 
-        st.write("Extracted Text:")
-        st.text_area("Text from PDF", extracted_text, height=300)
+  if uploaded_file is not None:
+    # Extract text from the PDF
+    extracted_text = extract_text_from_image_pdf(uploaded_file.name)
 
-        # Convert the extracted text to Word or Excel
-        if st.button("Save as Word"):
-            # Save to Word file
-            word_filename = "extracted_text.docx"
-            save_to_word(extracted_text, word_filename)
-            st.success(f"Saved to {word_filename}")
+    # Display extracted text
+    st.success("Text extracted from PDF:")
+    st.write(extracted_text)
 
-        if st.button("Save as Excel"):
-            # Save to Excel file
-            excel_filename = "extracted_text.xlsx"
-            save_to_excel(extracted_text, excel_filename)
-            st.success(f"Saved to {excel_filename}")
+    # Download option (optional)
+    if st.button("Download text as .txt file"):
+      with open("extracted_text.txt", "w") as f:
+        f.write(extracted_text)
+      st.success("Text downloaded!")
 
 if __name__ == "__main__":
-    main()
+  main()