From 07ff730c6288b9f9548a317027cd3d1f0bf9b22f Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Mon, 1 Feb 2021 10:03:15 -0800
Subject: catch HTML parsing error from withing html (via bs4)

---
 fatcat_scholar/schema.py | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/fatcat_scholar/schema.py b/fatcat_scholar/schema.py
index 9b2d2fb..b93962c 100644
--- a/fatcat_scholar/schema.py
+++ b/fatcat_scholar/schema.py
@@ -380,8 +380,15 @@ def clean_str(raw: Optional[str], strip_trailing_period: bool = False) -> Option
 
     text = ftfy.fix_text(raw)
 
-    # remove HTML
-    text = BeautifulSoup(text, "html.parser").get_text()
+    # remove HTML tags
+    try:
+        # TODO: work_h4ufpvlh3rcefacajni7sdndwa as a regression test
+        # TODO: consider w3clib "remove tags" as an alternative
+        clean_text = BeautifulSoup(text, "html.parser").get_text()
+        text = clean_text
+    except UnboundLocalError:
+        # TODO: passing through raw string; what should behavior actually be?
+        pass
 
     # TODO: for performance, compile these as globals?
     # replaces whitespace with single space
-- 
cgit v1.2.3