Update app.py

app.py

@@ -14,6 +14,7 @@ from pdf2image.exceptions import (
 import fitz  # PyMuPDF
 from PIL import Image
 import io
+import base64
 
 def clean_text(text):
     nlp = spacy.load("en_core_web_sm", disable=["tagger", "parser", "ner", "textcat"])
@@ -38,8 +39,8 @@ def pdf_to_text(file):
         image_list = page.get_images(full=True)
         for img in image_list:
             xref, name, ext, color_space, width, height, bpc, image_data, image_mask, smask_data = img
-            print(type(image_data))  # Print the type of image_data
-            print(image_data[:100])  # Print the first 100 characters of image_data
+            # Decode image_data from base64 before opening it
+            image_data = base64.b64decode(image_data)
             image = Image.open(io.BytesIO(image_data))
             latex_code = image_to_latex(image)
             page_text += "\n" + latex_code  # Add LaTeX code to page text