Module 4

requirements.txt

@@ -69,6 +69,7 @@ community==1.0.0b1
 confection==0.1.5
 cons==0.4.7
 contourpy==1.3.3
+courlan==1.3.2
 cramjam==2.11.0
 cryptography==43.0.3
 cuda-python==12.6.2.post1
@@ -90,6 +91,7 @@ dask-cuda==25.6.0
 dask-cudf-cu12==25.6.0
 dataproc-spark-connect==0.8.3
 datasets==4.0.0
+dateparser==1.2.2
 db-dtypes==1.4.3
 dbus-python==1.2.18
 debugpy==1.8.15
@@ -181,7 +183,6 @@ google-cloud-speech==2.33.0
 google-cloud-storage==2.19.0
 google-cloud-trace==1.16.2
 google-cloud-translate==3.21.1
-google-colab @ file:///colabtools/dist/google_colab-1.0.0.tar.gz
 google-crc32c==1.7.1
 google-genai==1.39.1
 google-generativeai==0.8.5
@@ -216,6 +217,7 @@ holidays==0.81
 holoviews==1.21.0
 hpack==4.1.0
 html5lib==1.1
+htmldate==1.9.3
 httpcore==1.0.9
 httpimport==1.4.1
 httplib2==0.31.0
@@ -259,6 +261,7 @@ jax==0.5.3
 jax-cuda12-pjrt==0.5.3
 jax-cuda12-plugin==0.5.3
 jaxlib==0.5.3
+jedi==0.19.2
 jeepney==0.9.0
 jieba==0.42.1
 Jinja2==3.1.6
@@ -280,6 +283,7 @@ jupyter_server_terminals==0.5.3
 jupyterlab_pygments==0.3.0
 jupyterlab_widgets==3.0.15
 jupytext==1.17.3
+jusText==3.0.2
 kaggle==1.7.4.5
 kagglehub==0.3.13
 keras==3.10.0
@@ -311,12 +315,12 @@ librmm-cu12==25.6.0
 librosa==0.11.0
 libucx-cu12==1.18.1
 libucxx-cu12==0.44.0
-lightgbm @ file:///tmp/lightgbm/LightGBM/dist/lightgbm-4.6.0-py3-none-linux_x86_64.whl
 linkify-it-py==2.0.3
 llvmlite==0.43.0
 locket==1.0.0
 logical-unification==0.4.6
 lxml==5.4.0
+lxml_html_clean==0.4.3
 Mako==1.3.10
 marisa-trie==1.3.1
 Markdown==3.9
@@ -418,12 +422,15 @@ parso==0.8.5
 parsy==2.2
 partd==1.4.2
 patsy==1.0.1
+pdfminer.six==20250506
+pdfplumber==0.11.7
 peewee==3.18.2
 peft==0.17.1
 pexpect==4.9.0
 pickleshare==0.7.5
 pillow==11.3.0
 platformdirs==4.4.0
+playwright==1.55.0
 plotly==5.24.1
 plotnine==0.14.5
 pluggy==1.6.0
@@ -464,6 +471,7 @@ pydot==3.0.4
 pydotplus==2.0.2
 PyDrive2==1.21.3
 pydub==0.25.1
+pyee==13.0.0
 pyerfa==2.0.1.5
 pygame==2.6.1
 pygit2==1.18.2
@@ -482,6 +490,7 @@ pyomo==6.9.4
 PyOpenGL==3.1.10
 pyOpenSSL==24.2.1
 pyparsing==3.2.5
+pypdfium2==4.30.0
 pyperclip==1.11.0
 pyproj==3.7.2
 pyproject_hooks==1.2.0
@@ -608,6 +617,7 @@ tifffile==2025.9.30
 tiktoken==0.11.0
 timm==1.0.20
 tinycss2==1.4.0
+tld==0.13.1
 tokenizers==0.22.1
 toml==0.10.2
 tomlkit==0.13.3
@@ -621,6 +631,7 @@ torchtune==0.6.1
 torchvision==0.23.0+cu126
 tornado==6.4.2
 tqdm==4.67.1
+trafilatura==2.0.0
 traitlets==5.7.1
 traittypes==0.2.1
 transformers==4.56.2