diff --git a/pkgs/development/python-modules/html-text/default.nix b/pkgs/development/python-modules/html-text/default.nix
new file mode 100644
index 000000000000..997cf053a5f7
--- /dev/null
+++ b/pkgs/development/python-modules/html-text/default.nix
@@ -0,0 +1,37 @@
+{ lib
+, buildPythonPackage
+, fetchFromGitHub
+, lxml
+, six
+, pytestCheckHook
+}:
+
+buildPythonPackage rec {
+  pname = "html-text";
+  version = "0.5.2";
+
+  src = fetchFromGitHub {
+    owner = "TeamHG-Memex";
+    repo = "html-text";
+    rev = version;
+    sha256 = "sha256-jw/hpz0QfcgP5OEJcmre0h1OzOfpPtaROxHm+YUqces=";
+  };
+
+  propagatedBuildInputs = [
+    lxml
+  ];
+
+  checkInputs = [
+    pytestCheckHook
+    six
+  ];
+
+  pythonImportsCheck = [ "html_text" ];
+
+  meta = with lib; {
+    description = "Extract text from HTML";
+    homepage = "https://github.com/TeamHG-Memex/html-text";
+    license = licenses.mit;
+    maintainers = with maintainers; [ ambroisie ];
+  };
+}
diff --git a/pkgs/top-level/python-packages.nix b/pkgs/top-level/python-packages.nix
index 66d1af78f3b6..bc113f821504 100644
--- a/pkgs/top-level/python-packages.nix
+++ b/pkgs/top-level/python-packages.nix
@@ -4301,6 +4301,8 @@ in {
 
   html-sanitizer = callPackage ../development/python-modules/html-sanitizer { };
 
+  html-text = callPackage ../development/python-modules/html-text { };
+
   HTSeq = callPackage ../development/python-modules/HTSeq { };
 
   httmock = callPackage ../development/python-modules/httmock { };