From a87ca1de1d8b31c4fbf9fddead27cdc58b09565a Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Tue, 3 Nov 2020 23:37:50 -0800
Subject: initial implementation of HTML ingest in existing worker

---
 python/sandcrawler/html_metadata.py | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'python/sandcrawler/html_metadata.py')

diff --git a/python/sandcrawler/html_metadata.py b/python/sandcrawler/html_metadata.py
index 3ebba57..8928978 100644
--- a/python/sandcrawler/html_metadata.py
+++ b/python/sandcrawler/html_metadata.py
@@ -248,6 +248,11 @@ class BiblioMetadata(pydantic.BaseModel):
     html_fulltext_url: Optional[str]
     xml_fulltext_url: Optional[str]
 
+    class Config:
+        json_encoders = {
+            datetime.date: lambda dt: dt.isoformat()
+        }
+
 
 def html_extract_fulltext_url(doc_url: str, doc: HTMLParser, patterns: List[dict]) -> Optional[Tuple[str, str]]:
     """
-- 
cgit v1.2.3