Update app.py

app.py

@@ -31,16 +31,13 @@ hf_hub_download(
 #     local_dir = "./models"
 # )
 
-def process_document(pdf_path, page_ids=None):
-    extracted_pages = extract_pages(pdf_path, page_numbers=page_ids)
-
+def process_document(pdf_path):
+    extracted_pages = extract_pages(pdf_path)
     page2content = {}
-
     for extracted_page in tqdm(extracted_pages):
         page_id = extracted_page.pageid
         content = process_page(extracted_page)
         page2content[page_id] = content
-
     return page2content
 
 
@@ -196,12 +193,12 @@ def pdf_to_text(files, maxtokens=2048, temperature=0, top_probability=0.95):
         file_name = os.path.basename(file)
         file_name_splt = file_name.split('.')
         if (len(file_name_splt) > 1 and file_name_splt[1] == 'pdf'):
-            page2content = process_document(file, page_ids=[0])
-            pdftext = page2content[1]
-            if (pdftext): #shift this if block to right later
-                anonymized_text = deidentify_doc(pdftext, maxtokens, temperature, top_probability)
-            else:
-                anonymized_text = 'PDF file appears to be corrupted.'
+            page2content = process_document(file)
+            anonymized_text = ''
+            for page_id in page2content:
+                pdftext = page2content[page_id]
+                anonymized_text += deidentify_doc(pdftext, maxtokens, temperature, top_probability)
+                anonymized_text += '\n\n\n'
     return anonymized_text
 
 css = ".gradio-container {background: 'logo.png'}"
@@ -215,8 +212,7 @@ output_path_component = gr.File(label="Select Output Path")
 iface = gr.Interface(
     fn=pdf_to_text,
     inputs=['file'],
-    # css = css,
-    outputs=output_text,
+    outputs="text",
     title='DeID: Endoscopy Report De-Identification',
     description="This application assists to remove personal information from the uploaded clinical report",
     theme=gr.themes.Soft(),