Update pdftotext.py

pdftotext.py

@@ -141,6 +141,13 @@ def apiFiltering(apitext):
     return filtered_items
 
 
+def clean_text(text):
+    # Replace all newlines and tabs with a space
+    text = re.sub(r'[\n\t]+', ' ', text)
+    # Collapse multiple spaces into one
+    text = re.sub(r'\s+', ' ', text)
+    return text.strip()
+
 def texts_from_pdfAllText(link):
   
       pdf_content = None
@@ -167,8 +174,10 @@ def texts_from_pdfAllText(link):
             text_instances = page.get_text()
             all_text+=text_instances
             
-      print(all_text)
-      return all_text
+      
+      cleaned_text = clean_text(all_text)
+      print(cleaned_text)
+      return cleaned_text
 # import fitz
 
 # import tsadropboxretrieval