Add in original html - play with sanitising paragraphs

sm1-html-2-json5.py

@@ -16,6 +16,18 @@ def validate_html(html):
         etree.fromstring(html, parser)  # Attempt to parse the HTML
     except Exception as e:
         raise ValueError("Invalid HTML document") from e
+        
+def sanitize_text(text):
+    # Replace newlines with spaces
+    sanitized_text = text.replace('\n', ' ').replace('\r', ' ')  # Handle both Unix and Windows line endings
+    # Replace tabs with spaces
+    sanitized_text = sanitized_text.replace('\t', ' ')
+    # Escape quote characters
+    sanitized_text = sanitized_text.replace('"', '\\"').replace("'", "\\'")
+    # Strip leading and trailing whitespace
+    sanitized_text = sanitized_text.strip()
+    return sanitized_text
+
 
 def extract_data(html):
     """Extract paragraphs, inputs, tables, and pre blocks from HTML and organize them in order."""
@@ -54,9 +66,10 @@ def extract_data(html):
         elif element.name == 'p':
             text = element.get_text(strip=True)
             if text:  # Ignore empty paragraphs
+				#Sanitise text freom newlines,tabs and escape quotes.
                 records.append({
                     'Type': 'Paragraph',
-                    'Text': text
+                    'Text': sanitize_text(text)
                 })
 
         elif element.name == 'pre':
@@ -233,7 +246,7 @@ def save_to_json5(data, output_filename, package_name, header, sub_header):
         json_file.truncate()  # Remove any old content beyond the new content length
 
 def main():
-    input_file = '/home/brianr/clients/SM2/SM1-JSONGen/DiskUsage.html'  # Specify the input HTML file path
+    input_file = '/home/brianr/clients/SM2/SM2Gen/venv/html/CreateStarterWebsite.html'  # Specify the input HTML file path
 
     # Read HTML content
     html_content = read_html_file(input_file)