mirror of
https://github.com/ada-dmitry/CourseWork_IRFM.git
synced 2026-09-24 01:10:18 +00:00
Dmitry
502f48a279
- Implemented a new crawler module to extract text and links from legal documents. - Added a loader module to handle HTML downloads with error handling and retries. - Created a main script to initiate the crawling process on a specified URL. - Defined functions for normalizing URLs, extracting links, checking terminal pages, and extracting text content. - Updated project metadata with dependencies and versioning in pyproject.toml and uv.lock.
10 lines
181 B
TOML
10 lines
181 B
TOML
[project]
|
|
name = "coursework-irfm"
|
|
version = "0.1.0"
|
|
description = "Add your description here"
|
|
readme = "README.md"
|
|
requires-python = ">=3.13"
|
|
dependencies = [
|
|
"lxml>=6.0.4",
|
|
]
|