Code Modified

app.py

@@ -1,18 +1,28 @@
 import gradio as gr
-import pdfminer
-from pdfminer.high_level import extract_text
+import PyPDF2
+import re
 
 def read_pdf(file):
-    text = extract_text(file.name)
-    return text
+    with open(file.name, 'rb') as f:
+        reader = PyPDF2.PdfReader(f)
+        paragraphs = []
+        for page in reader.pages:
+            extracted_text = page.extract_text()
+            formatted_text = re.sub(r'\n+', '\n', extracted_text)  # Replace multiple consecutive line breaks with a single line break
+            paragraphs.append(formatted_text.strip())
+            
+    formatted_text = "\n\n".join(paragraphs)  # Join paragraphs with double line breaks
+    
+    return formatted_text
 
 iface = gr.Interface(
     read_pdf,
     gr.inputs.File(label="Upload a PDF file"),
-    gr.outputs.Textbox(label="Extracted text"),
+    gr.outputs.Textbox(label="Extracted Text", lines=10, type="auto", spellcheck=True, readonly=True),
     title="PDF Text Extractor",
-    description="A smooth app that gets text from PDF files using pdfminer. 🧠",
-    theme="ParityError/Anime"
-
+    description="A smooth app that gets text from PDF files using pdfminer 🧠",
+    theme="ParityError/Anime",
+    layout="vertical",
+    width="600px"
 )
 iface.launch()