starmen1265
63dd88279c
- Create ArchiveProcessor with STEP_NAME = archive - Implement process() method with idempotent execution - Add _find_existing_archive() for duplicate detection - Add _ask_overwrite() using rich.prompt with fallback - Only copy md files (not json) to archive directory - Export ArchiveProcessor in __init__.py
27 lines
847 B
Python
27 lines
847 B
Python
"""Processors module for KB Pipeline
|
|
|
|
This module contains processors for various content transformation tasks:
|
|
- BaseProcessor: Abstract base class for all processors
|
|
- ParseProcessor: URL parsing for various platforms
|
|
- DownloadProcessor: Metadata and content downloading
|
|
- ASRProcessor: Audio-to-text conversion (subtitle download + Whisper.cpp)
|
|
- AnalyzeProcessor: AI-powered content analysis using DeepAnalyzer
|
|
- ArchiveProcessor: Copy analysis reports to archive directory
|
|
"""
|
|
|
|
from .base import BaseProcessor
|
|
from .parse import ParseProcessor
|
|
from .download import DownloadProcessor
|
|
from .asr import ASRProcessor
|
|
from .analyze import AnalyzeProcessor
|
|
from .archive import ArchiveProcessor
|
|
|
|
__all__ = [
|
|
"BaseProcessor",
|
|
"ParseProcessor",
|
|
"DownloadProcessor",
|
|
"ASRProcessor",
|
|
"AnalyzeProcessor",
|
|
"ArchiveProcessor",
|
|
]
|