Removing lxml and using html5lib to avoid BS4 failing with lxml on HPCs

c3g · Feb 14, 2025 · 162f83d · 162f83d
1 parent e0e5755
commit 162f83d
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 3 deletions.
diff --git a/pt_cli/connect.py b/pt_cli/connect.py
@@ -10,7 +10,6 @@
 
 import requests
 import bs4
-import lxml
 
 logger = logging.getLogger(__name__)
 
@@ -128,7 +127,7 @@ def maybe_json(self, data):
             return loads
         except json.decoder.JSONDecodeError:
             if isinstance(data, str):
-                soup = bs4.BeautifulSoup(data, features="lxml")
+                soup = bs4.BeautifulSoup(data, features="html5lib")
                 if soup.get_text().startswith("----------"):
                     sys.stdout.write(soup.get_text())
                 elif soup.get_text().startswith("Welcome"):

diff --git a/pyproject.toml b/pyproject.toml
@@ -21,7 +21,7 @@ dependencies = [
     "pyyaml>=6.0",
     "requests>=2.28",
     "beautifulsoup4>=4.12",
-    "lxml",
+    "html5lib",
     "shtab",
 ]