ada/CourseWork_IRFM
1
0
Fork 0
mirror of https://github.com/ada-dmitry/CourseWork_IRFM.git synced 2026-09-24 01:10:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add loader and processor modules with documentation and output files

Browse Source 
- Implemented loader in `modules/loader.py` to download HTML pages using curl and urllib.
- Created processor in `modules/processor.py` for processing the text of the Russian Criminal Code (УК РФ).
- Added README files for both loader and processor explaining their functionality and usage.
- Generated output files including original text, prepared text, and subject index in CSV and JSON formats.
This commit is contained in:
Dmitry
2026-04-16 21:38:00 +03:00
parent 502f48a279
commit 0b41577a42
15 changed files with 8770 additions and 103 deletions
Download Patch File Download Diff File Expand all files Collapse all files
uv.lock
Generated
+46 -1
View File
@@ -8,10 +8,23 @@ version = "0.1.0"
source = { virtual = "." }
dependencies = [
{ name = "lxml" },
{ name = "pymorphy3" },
]
[package.metadata]
requires-dist = [{ name = "lxml", specifier = ">=6.0.4" }]
requires-dist = [
{ name = "lxml", specifier = ">=6.0.4" },
{ name = "pymorphy3", specifier = ">=2.0.6" },
]
[[package]]
name = "dawg2-python"
version = "0.9.0"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/2d/03/85171ce1e59088237aebf21943d1136463f6422820f096ac8cf9322aa851/dawg2_python-0.9.0.tar.gz", hash = "sha256:adea0312acd1a958659e8448ce6899046c0858d0b6c8949a51eebdeb5a113e4a", size = 10278, upload-time = "2025-02-17T13:22:24.261Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/84/3b/7fb4c1a8df59cb80f5f7ecb9646280e000f9ba2ccff8710205dc9aa4604f/dawg2_python-0.9.0-py3-none-any.whl", hash = "sha256:4fab6fc097bd176cd783cd8421b757348ea5a460789e53b0f6bb64831380bab5", size = 9331, upload-time = "2025-02-17T13:22:22.858Z" },
]
[[package]]
name = "lxml"
@@ -74,3 +87,35 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/3d/5e/2231f34cc54b8422b793593138d86d3fa4588fb2297d4ea0472390f25627/lxml-6.0.4-cp314-cp314t-win_amd64.whl", hash = "sha256:25bad2d8438f4ef5a7ad4a8d8bcaadde20c0daced8bdb56d46236b0a7d1cbdd0", size = 4391037, upload-time = "2026-04-12T16:26:54.398Z" },
{ url = "https://files.pythonhosted.org/packages/39/53/8ba3cd5984f8363635450c93f63e541a0721b362bb32ae0d8237d9674aee/lxml-6.0.4-cp314-cp314t-win_arm64.whl", hash = "sha256:1dcd9e6cb9b7df808ea33daebd1801f37a8f50e8c075013ed2a2343246727838", size = 3816184, upload-time = "2026-04-12T16:26:57.011Z" },
]
[[package]]
name = "pymorphy3"
version = "2.0.6"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "dawg2-python" },
{ name = "pymorphy3-dicts-ru" },
{ name = "setuptools" },
]
sdist = { url = "https://files.pythonhosted.org/packages/17/63/3a1eabd3a7e6e060b69a87fe9c28fe89f75f4d49e55f0caf2e29c943c003/pymorphy3-2.0.6.tar.gz", hash = "sha256:1603df3bc9e116967c990607f5b97d42fb1c572d6839b851af3501e51d7f5493", size = 97681, upload-time = "2025-10-09T16:06:18.718Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/18/4b/59bac03278033e293d1405ed42fb6c6252c25f40c50f509c615caeaa3b71/pymorphy3-2.0.6-py3-none-any.whl", hash = "sha256:0254317c02ce3ea17e080b7fc9d675e44662b3a5296bae68605b7a41d25b36c3", size = 53900, upload-time = "2025-10-09T16:06:17.721Z" },
]
[[package]]
name = "pymorphy3-dicts-ru"
version = "2.4.417150.4580142"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/ba/13/02ffe6893a777add5c8a43f212f31a3f6a03e7d44a484cf7b5ac5381fddb/pymorphy3-dicts-ru-2.4.417150.4580142.tar.gz", hash = "sha256:39ab379d4ca905bafed50f5afc3a3de6f9643605776fbcabc4d3088d4ed382b0", size = 8381569, upload-time = "2022-01-08T22:17:37.581Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/b0/67/469e9e52d046863f5959928794d3067d455a77f580bf4a662630a43eb426/pymorphy3_dicts_ru-2.4.417150.4580142-py2.py3-none-any.whl", hash = "sha256:718bac64c73c10c16073a199402657283d9b64c04188b694f6d3e9b0d85440f4", size = 8442043, upload-time = "2022-01-08T22:17:34.282Z" },
]
[[package]]
name = "setuptools"
version = "82.0.1"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/4f/db/cfac1baf10650ab4d1c111714410d2fbb77ac5a616db26775db562c8fab2/setuptools-82.0.1.tar.gz", hash = "sha256:7d872682c5d01cfde07da7bccc7b65469d3dca203318515ada1de5eda35efbf9", size = 1152316, upload-time = "2026-03-09T12:47:17.221Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/9d/76/f789f7a86709c6b087c5a2f52f911838cad707cc613162401badc665acfe/setuptools-82.0.1-py3-none-any.whl", hash = "sha256:a59e362652f08dcd477c78bb6e7bd9d80a7995bc73ce773050228a348ce2e5bb", size = 1006223, upload-time = "2026-03-09T12:47:15.026Z" },
]