v1.4.1: add trafilatura.utils to SENTRY_LOGGERS_TO_IGNORE

Author: philbudne

CHANGELOG.md

@@ -4,14 +4,17 @@ Version History
 Version 1
 ---------
 
+### V1.4.1
+* add trafilatura.utils to SENTRY_LOGGERS_TO_IGNORE
+
 ### V1.4.0
 * add ignore_loggers and sentry_ignore_loggers
 
 ### V1.3.1
 * Fix CI Bug from out-of-date dependency
 
 ### V1.3.0
-* Add option to optionally override canonical_domain 
+* Add option to optionally override canonical_domain
 
 ### V1.2.0
 * metadata now includes Canonical Url when available

mcmetadata/__init__.py

@@ -33,6 +33,7 @@
     # NOTE! in sorted order!
     "htmldate.utils",
     "trafilatura.core",
+    "trafilatura.utils",
 ]
 
 
@@ -102,9 +103,9 @@ def extract(
     is_shortened_url = urls.is_shortened_url(url)
     url_duration = time.monotonic() - t1
     stats_accumulator["url"] += url_duration
-    
-    if 'canonical_domain' in overrides:
-        canonical_domain = overrides['canonical_domain']
+
+    if "canonical_domain" in overrides:
+        canonical_domain = overrides["canonical_domain"]
     else:
         canonical_domain = urls.canonical_domain(final_url)
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "flit_core.buildapi"
 
 [project]
 name = "mediacloud-metadata"
-version = "1.4.0"
+version = "1.4.1"
 authors = [
     {name='Rahul Bhargava', email='[email protected]'}
 ]