diff --git a/poetry.lock b/poetry.lock
index 809c5e7..c476a34 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -7361,11 +7361,11 @@ test = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
 testing = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
 
 [extras]
-ingest = ["deutschland", "selenium", "xmltodict"]
+ingest = ["deutschland", "html5lib", "selenium", "xmltodict"]
 transformation = ["spacy", "spacy-sentiws", "torch", "torchaudio", "torchvision", "transformers"]
 web-server = ["dash", "dash-auth", "dash-bootstrap-components", "matplotlib", "networkx", "seaborn"]
 
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.11,<3.13"
-content-hash = "0fb643247c09a91aeef5aae1286426f9296688dadff30f5a4a6085c3abe5399e"
+content-hash = "5ca44ede811dc417faeda6b976c032682be7b4edadc16fc6c81e2ffe3dc4f946"
diff --git a/pyproject.toml b/pyproject.toml
index 77af5eb..a17ac8b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -81,9 +81,10 @@ torchvision = {version = "*", source = "torch-cpu"}
 tqdm = "^4.66.1"
 transformers = {version = "*", extras = ["torch"]}
 xmltodict = "^0.13.0"
+html5lib = "^1.1"
 
 [tool.poetry.extras]
-ingest = ["selenium", "deutschland", "xmltodict"]
+ingest = ["selenium", "deutschland", "xmltodict", "html5lib"]
 transformation = ["torch", "torchaudio", "torchvision", "transformers", "spacy-sentiws", "spacy"]
 web-server = ["dash", "dash-auth", "dash-bootstrap-components", "matplotlib", "seaborn", "networkx"]