drewThomasson commited on
Commit
225af8d
·
verified ·
1 Parent(s): 51a779d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -15,7 +15,7 @@ def ocr_pdf(file_path):
15
  extracted_text = ""
16
  for i, image in enumerate(images):
17
  text = pytesseract.image_to_string(image)
18
- extracted_text += f"--- Page {i+1} ---\n{text}\n\n"
19
 
20
  # Save the extracted text to a .txt file in a persistent location
21
  output_txt_path = os.path.join(temp_dir, "extracted_text.txt")
 
15
  extracted_text = ""
16
  for i, image in enumerate(images):
17
  text = pytesseract.image_to_string(image)
18
+ extracted_text += f"\n{text}\n\n"
19
 
20
  # Save the extracted text to a .txt file in a persistent location
21
  output_txt_path = os.path.join(temp_dir, "extracted_text.txt")