diff --git a/pkgs/development/python-modules/extruct/default.nix b/pkgs/development/python-modules/extruct/default.nix
new file mode 100644
index 000000000000..39591ac55fa2
--- /dev/null
+++ b/pkgs/development/python-modules/extruct/default.nix
@@ -0,0 +1,61 @@
+{ lib
+, buildPythonPackage
+, fetchFromGitHub
+, pythonRelaxDepsHook
+, html-text
+, jstyleson
+, lxml
+, mf2py
+, pyrdfa3
+, rdflib
+, six
+, w3lib
+, pytestCheckHook
+, mock
+}:
+
+buildPythonPackage rec {
+  pname = "extruct";
+  version = "0.13.0";
+
+  src = fetchFromGitHub {
+    owner = "scrapinghub";
+    repo = "extruct";
+    rev = "v${version}";
+    sha256 = "sha256-hf6b/tZLggHzgFmZ6aldZIBd17Ni7vCTIIzhNlyjvxw=";
+  };
+
+  nativeBuildInputs = [
+    pythonRelaxDepsHook
+  ];
+
+  # rdflib-jsonld functionality is part of rdblib from version 6 onwards
+  pythonRemoveDeps = [
+    "rdflib-jsonld"
+  ];
+
+  propagatedBuildInputs = [
+    html-text
+    jstyleson
+    lxml
+    mf2py
+    pyrdfa3
+    rdflib
+    six
+    w3lib
+  ];
+
+  checkInputs = [
+    mock
+    pytestCheckHook
+  ];
+
+  pythonImportsCheck = [ "extruct" ];
+
+  meta = with lib; {
+    description = "Extract embedded metadata from HTML markup";
+    homepage = "https://github.com/scrapinghub/extruct";
+    license = licenses.bsd3;
+    maintainers = with maintainers; [ ambroisie ];
+  };
+}
diff --git a/pkgs/top-level/python-packages.nix b/pkgs/top-level/python-packages.nix
index 80911fa28a81..33ea0833e9c1 100644
--- a/pkgs/top-level/python-packages.nix
+++ b/pkgs/top-level/python-packages.nix
@@ -3138,6 +3138,8 @@ in {
 
   extras = callPackage ../development/python-modules/extras { };
 
+  extruct = callPackage ../development/python-modules/extruct { };
+
   eyeD3 = callPackage ../development/python-modules/eyed3 { };
 
   ezdxf = callPackage ../development/python-modules/ezdxf { };