Update app.py

app.py

@@ -27,31 +27,39 @@ def image_to_latex(image):
     result = subprocess.run(["pix2tex", image_path], capture_output=True, text=True)
     return result.stdout
 
-import fitz
+
 
 def pdf_to_text(file):
     doc = fitz.open(file.name)
     full_text = ''
     for i, page in enumerate(doc):
+        # Extract text
         page_text = page.get_text()
-        image_dict = page.get_images(full=True)
-        if image_dict:
-            for xref, img in image_dict:
-                image_data = img['image']
-                image = Image.open(io.BytesIO(image_data))
-                page_text += image_to_latex(image)
+
+        # Extract images and convert to LaTeX
+        image_list = page.get_images(full=True)
+        for img in image_list:
+            xref, img_properties = img
+            image_data = img_properties['image']
+            image = Image.open(io.BytesIO(image_data))
+            latex_code = image_to_latex(image)
+            page_text += "\n" + latex_code  # Add LaTeX code to page text
+
         page_text = clean_text(page_text)
         if len(page_text.split()) > 5: 
             page_number = i + 1
             page_text = "## Metadata: Page Number " + str(page_number) + "\n" + page_text
             full_text += page_text + "\n\n"
+
     base_name = os.path.splitext(os.path.basename(file.name))[0]
     output_file_name = base_name + ".txt"
     with open(output_file_name, 'w') as f:
         f.write(full_text)
+
     return output_file_name, page_number
 
 
+
 iface = gr.Interface(fn=pdf_to_text,
                      inputs=gr.inputs.File(label="Your PDF"),
                      outputs=gr.outputs.File(label="Download TXT"),