Remove lxml installation (#140)

Signed-off-by: Ryan Wolf <[email protected]>

setup.py

@@ -45,7 +45,7 @@
         "awscli>=1.22.55",
         "fasttext==0.9.2",
         "pycld2==0.41",
-        "justext==3.0.0",
+        "justext==3.0.1",
         "resiliparse",
         "ftfy==6.1.1",
         "warcio==1.7.4",
@@ -63,9 +63,6 @@
         "nemo_toolkit[nlp]>=1.23.0",
         "Cython",
         "crossfit @ git+https://github.com/rapidsai/[email protected]",
-        # justext installation breaks without lxml[html_clean]
-        # due to this: https://github.com/miso-belica/jusText/issues/47
-        "lxml[html_clean]",
         # Numpy 2.0 breaks with spacy https://github.com/explosion/spaCy/issues/13528
         # TODO: Remove when issue is fixed
         "numpy<2",