There are clear issues remaining with this approach. The wallabag-given 'start' and 'end' fields do _not_ just point to the n-th paragraph all the time (like I thought) but actually represent a beautifulsoup4 like tree descent. So: `p_start_match = re.match(r"/p\[(\d+)\]", annot["ranges"][0]["start"])` will fail on any annotation not just at the n-th paragraph. Instead we should see how we can move this tree into the beautifulsoup4 parser and make use of wallabag already having done the work for us?
20 lines
528 B
TOML
20 lines
528 B
TOML
[project]
|
|
name = "2hoarder"
|
|
version = "0.1.0"
|
|
description = "Add your description here"
|
|
readme = "README.md"
|
|
requires-python = ">=3.13"
|
|
dependencies = [
|
|
"beautifulsoup4>=4.13.3",
|
|
"lxml>=5.3.1",
|
|
"requests>=2.32.3",
|
|
# REQUIRED FOR CURRENT SHAARLI2HOARDER IMPLEMENTATION ONLY
|
|
# "netscape-bookmarks-file-parser",
|
|
# "pyjwt>=2.10.1",
|
|
]
|
|
|
|
[tool.pyright]
|
|
typeCheckingMode = "basic"
|
|
|
|
[tool.uv.sources]
|
|
netscape-bookmarks-file-parser = { git = "https://github.com/FlyingWolFox/Netscape-Bookmarks-File-Parser.git" }
|