40 lines
803 B
Python
40 lines
803 B
Python
"""
|
|
# Summary
|
|
|
|
HTML format implementation for OmniRead.
|
|
|
|
This package provides **HTML-specific implementations** of the core OmniRead
|
|
contracts defined in `omniread.core`.
|
|
|
|
It includes:
|
|
|
|
- HTML parsers that interpret HTML content.
|
|
- HTML scrapers that retrieve HTML documents.
|
|
|
|
Key characteristics:
|
|
|
|
- Implements, but does not redefine, core contracts.
|
|
- May contain HTML-specific behavior and edge-case handling.
|
|
- Produces canonical content models defined in `omniread.core.content`.
|
|
|
|
Consumers should depend on `omniread.core` interfaces wherever possible and
|
|
use this package only when HTML-specific behavior is required.
|
|
|
|
---
|
|
|
|
# Public API
|
|
|
|
- `HTMLScraper`
|
|
- `HTMLParser`
|
|
|
|
---
|
|
"""
|
|
|
|
from .scraper import HTMLScraper
|
|
from .parser import HTMLParser
|
|
|
|
__all__ = [
|
|
"HTMLScraper",
|
|
"HTMLParser",
|
|
]
|