Merge pull request #278 from NASA-IMPACT/fix_check_url

Refactor URL extraction logic in url_validator.py
NASA-IMPACT · Apr 24, 2024 · 246eb9a · 246eb9a
2 parents ef3c2eb + 7bfce69
commit 246eb9a
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/pyQuARC/code/url_validator.py b/pyQuARC/code/url_validator.py
@@ -54,7 +54,7 @@ def status_code_from_request(url):
         validity = True
 
         # extract URLs from text
-        extractor = URLExtract()
+        extractor = URLExtract(cache_dir="/tmp")
         urls = extractor.find_urls(text_with_urls)
         urls.extend(UrlValidator._extract_http_texts(text_with_urls))
 

diff --git a/requirements.txt b/requirements.txt
@@ -8,5 +8,5 @@ requests==2.24.0
 setuptools==60.8.2
 strict-rfc3339==0.7
 tqdm==4.48.2
-urlextract==1.0.0
+urlextract==1.3.0
 xmltodict==0.12.0