fix goodreads

catalog/book/tests.py

@@ -117,6 +117,14 @@ class GoodreadsTestCase(TestCase):
             site.ready, True, "previous resource should still exist with data"
         )
 
+    @use_local_response
+    def test_scrape2(self):
+        site = SiteManager.get_site_by_url(
+            "https://www.goodreads.com/book/show/13079982-fahrenheit-451"
+        )
+        site.get_resource_ready()
+        self.assertNotIn("<br", site.resource.metadata.get("brief"))
+
     @use_local_response
     def test_asin(self):
         t_url = "https://www.goodreads.com/book/show/45064996-hyperion"

catalog/sites/goodreads.py

@@ -1,5 +1,6 @@
 import json
 import logging
+import re
 from datetime import datetime
 
 from django.utils.timezone import make_aware
@@ -68,6 +69,10 @@ class Goodreads(AbstractSite):
             raise ParseError(self, "Book in __NEXT_DATA__ json")
         data["title"] = b["title"]
         data["brief"] = b["description"]
+        if data["brief"]:
+            data["brief"] = re.sub(
+                r"<[^>]*>", "", data["brief"].replace("<br />", "\n")
+            )
         ids = {}
         t, n = detect_isbn_asin(b["details"].get("asin"))
         if t: