37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
"""
|
|
Readers module for pyWebLayout.
|
|
|
|
This module provides specialized readers for different document formats
|
|
using a decomposed architecture pattern.
|
|
"""
|
|
|
|
# Base classes for the decomposed architecture
|
|
from .base import BaseReader, MetadataReader, ContentReader, ResourceReader, CompositeReader
|
|
|
|
# HTML readers (decomposed)
|
|
from .html import HTMLReader, read_html, read_html_file, parse_html_string
|
|
from .html_metadata import HTMLMetadataReader
|
|
from .html_content import HTMLContentReader
|
|
from .html_resources import HTMLResourceReader
|
|
|
|
# HTML processing components (supporting modules)
|
|
from .html_style import HTMLStyleManager
|
|
from .html_text import HTMLTextProcessor
|
|
from .html_elements import BlockElementHandler, ListElementHandler, TableElementHandler, InlineElementHandler
|
|
|
|
# EPUB readers
|
|
from .epub_reader import read_epub # Legacy
|
|
from .epub_metadata import EPUBMetadataReader # New decomposed
|
|
|
|
__all__ = [
|
|
# Base classes
|
|
'BaseReader', 'MetadataReader', 'ContentReader', 'ResourceReader', 'CompositeReader',
|
|
|
|
# HTML readers
|
|
'HTMLReader', 'read_html', 'read_html_file', 'parse_html_string',
|
|
'HTMLMetadataReader', 'HTMLContentReader', 'HTMLResourceReader',
|
|
|
|
# EPUB readers
|
|
'read_epub', 'EPUBMetadataReader',
|
|
]
|