cleaning product description from html

requirements.txt

@@ -19,4 +19,6 @@ woocommerce==2.1.1
 django-anymail[amazon_ses]==8.2
 boto3==1.17.11
 django-storages==1.11.1
-Faker==6.4.1
+Faker==6.4.1
+beautifulsoup4==4.9.3
+lxml==4.6.2

utils/woocommerce.py

@@ -15,6 +15,8 @@ import requests
 from PIL import Image
 from django.core.files import File
 
+from bs4 import BeautifulSoup
+
 from companies.models import Company
 from products.models import Product
 from products.serializers import ProductSerializer
@@ -52,15 +54,13 @@ def create_imported_product(info, company, history, user):
         'company':company.id,
         'creator': user.id if user is not None else None,
         'history': history.id,
-        'url': info['permalink'],
-        'stock': info['stock_quantity'],
+        'url': info.get('permalink'),
+        'stock': info.get('stock_quantity'),
+        'name': info.get('name'),
+        'description': BeautifulSoup(info.get('description', ''), "lxml").text,
+        'sku': info.get('sku'),
+        'price': info.get('price'),
         }
-    # parse the product info
-    for key in info:
-        if key in PRODUCT_FIELDS:
-            instance_data[key] = info[key]
-    # remove unwanted fields
-    instance_data.pop('id')
 
     # alternative method
     serializer = ProductSerializer(data=instance_data)