dnscms: remove some wordpress import functionality, keep fields around but defer

dnscms/news/models.py

@@ -4,12 +4,16 @@ from grapple.helpers import register_singular_query_field
 from grapple.models import GraphQLImage, GraphQLRichText, GraphQLStreamfield, GraphQLString
 from wagtail.admin.panels import FieldPanel
 from wagtail.fields import RichTextField
-from wagtail.models import Page
+from wagtail.models import Page, PageManager
 from wagtail.search import index
 from wagtail_headless_preview.models import HeadlessMixin
 
 from dnscms.fields import CommonStreamField
-from dnscms.wordpress.models import WPImportedPageMixin
+from dnscms.wordpress.models import DeferWPFieldsManagerMixin, WPImportedPageMixin
+
+
+class NewsPageManager(DeferWPFieldsManagerMixin, PageManager):
+    pass
 
 
 @register_singular_query_field("newsIndex")
@@ -39,6 +43,8 @@ class NewsPage(HeadlessMixin, WPImportedPageMixin, Page):
     parent_page_types = ["news.NewsIndex"]
     show_in_menus = False
 
+    objects = NewsPageManager()
+
     excerpt = models.TextField(max_length=512, blank=False)
     lead = RichTextField(features=["italic", "link"], blank=True)
     body = CommonStreamField
@@ -90,52 +96,3 @@ class NewsPage(HeadlessMixin, WPImportedPageMixin, Page):
     class Meta:
         verbose_name = _("news article")
         verbose_name_plural = _("news articles")
-
-    def import_wordpress_data(self, data):
-        import html
-
-        from bs4 import BeautifulSoup
-
-        def generate_excerpt(html_content):
-            soup = BeautifulSoup(html_content, features="lxml")
-            VALID_TAGS = ["div", "p"]
-
-            for tag in soup.findAll("p"):
-                if tag.name not in VALID_TAGS:
-                    tag.remove()
-
-            text = soup.get_text().strip()
-            words = text.split(" ")
-            if len(words) < 26:
-                return text
-            return " ".join(words[:25]) + " [...]"
-
-        # Wagtail page model fields
-        self.title = html.unescape(data["title"])
-        self.slug = data["slug"]
-        self.first_published_at = data["first_published_at"]
-        self.last_published_at = data["last_published_at"]
-        self.latest_revision_created_at = data["latest_revision_created_at"]
-        self.search_description = data["search_description"]
-
-        # debug fields
-        self.wp_post_id = data["wp_post_id"]
-        self.wp_post_type = data["wp_post_type"]
-        self.wp_link = data["wp_link"]
-        self.wp_raw_content = data["wp_raw_content"]
-        self.wp_block_json = data["wp_block_json"]
-        self.wp_processed_content = data["wp_processed_content"]
-        self.wp_normalized_styles = data["wp_normalized_styles"]
-        self.wp_post_meta = data["wp_post_meta"]
-
-        # own model fields
-        self.body = data["body"] or ""
-
-        meta = data["wp_post_meta"]
-
-        written_excerpt = meta.get("excerpt_encoded")
-        generated_excerpt = ""
-        if not written_excerpt:
-            generated_excerpt = generate_excerpt(self.wp_processed_content)
-
-        self.excerpt = written_excerpt or generated_excerpt or "[...]"