diff --git a/app/settings/dev.py b/app/settings/dev.py
index a48ccb1..e60e4df 100644
--- a/app/settings/dev.py
+++ b/app/settings/dev.py
@@ -20,7 +20,7 @@
 # e.g. when you are no longer using the import actions
 WAGTAILREDIRECTS_AUTO_CREATE = False
 
-# Cooment out if you need to use timezone aware datetimes
+# Comment out if you need to use timezone aware datetimes
 USE_TZ = False
 
 # Shell plus config
diff --git a/wordpress.docker/docker-compose.yml b/wordpress.docker/docker-compose.yml
index ca28b1e..5b57008 100644
--- a/wordpress.docker/docker-compose.yml
+++ b/wordpress.docker/docker-compose.yml
@@ -25,6 +25,7 @@ services:
     image: mysql:5.7
     platform: linux/x86_64
     restart: always
+    platform: linux/x86_64
     env_file:
       - .env
     volumes:
@@ -32,7 +33,7 @@ services:
     healthcheck:
       test: [ "CMD", "mysqladmin", "ping", "-h", "localhost" ]
       interval: 5s
-      timeout: 5s
+      timeout: 10s
       retries: 5
 
 volumes:
diff --git a/wp_connector/importer.py b/wp_connector/importer.py
index 98a9e8d..5fd967d 100644
--- a/wp_connector/importer.py
+++ b/wp_connector/importer.py
@@ -83,6 +83,41 @@ class can be used for all models.
         # processing foreign keys here as we have access to all the data now
         self.process_one_to_many(self.one_to_many)
         self.process_many_to_many(self.many_to_many)
+        self.process_clean_fields(self.clean_fields)
+
+    @staticmethod
+    def get_cleaned_data(process_clean_fields, item):
+        cleaned_data = []
+
+        def clean_content(content):
+            # currently just removes whitespace incl. newlines
+            # from the start and end of the content
+            # remove br tags if they are a top level tag using beautifulsoup
+            # remove empty paragraphs
+
+            soup = bs(content, "html.parser")
+            tags = []
+            for tag in soup.find_all("br", recursive=False):
+                tag.decompose()
+
+            for tag in soup.find_all("p", recursive=False):
+                if not tag.text.strip():
+                    tag.decompose()
+
+            for tag in soup.find_all(recursive=True):
+                tags.append(str(tag))
+
+            return "".join(tags)
+
+        for field in process_clean_fields():
+            for key, value in field.items():
+                cleaned_data.append(
+                    {
+                        key: clean_content(jmespath.search(value, item)),
+                    }
+                )
+
+        return cleaned_data
 
     @staticmethod
     def get_many_to_many_data(process_many_to_many_keys, item):
@@ -221,3 +256,12 @@ def process_many_to_many(self, objects):
 
                 for related_object in related_objects:
                     getattr(obj, field).add(related_object)
+
+    @staticmethod
+    def process_clean_fields(cleaned_fields):
+        sys.stdout.write("Processing clean fields...\n")
+        for obj in cleaned_fields:
+            for field in obj.cleaned_data:
+                for key, value in field.items():
+                    setattr(obj, key, value)
+            obj.save()
diff --git a/wp_connector/models/page.py b/wp_connector/models/page.py
index fbf413b..53740f3 100644
--- a/wp_connector/models/page.py
+++ b/wp_connector/models/page.py
@@ -81,7 +81,7 @@ def process_clean_fields():
         """Clean the content."""
         return [
             {
-                "content": "wp_cleaned_content",
+                "wp_cleaned_content": "content.rendered",
             }
         ]
 
diff --git a/wp_connector/models/post.py b/wp_connector/models/post.py
index af30009..378532d 100644
--- a/wp_connector/models/post.py
+++ b/wp_connector/models/post.py
@@ -94,7 +94,7 @@ def process_clean_fields():
         """Clean the content."""
         return [
             {
-                "content": "wp_cleaned_content",
+                "wp_cleaned_content": "content.rendered",
             }
         ]