refactor(core): reorganize project structure and remove legacy code
Major reorganization of the project structure: - Moved legacy synchronous crawler code to legacy folder - Removed deprecated CLI and docs manager - Consolidated version manager into utils.py - Added CrawlerHub to __init__.py exports - Fixed type hints in async_webcrawler.py - Fixed minor bugs in chunking and crawler strategies BREAKING CHANGE: Removed synchronous WebCrawler, CLI, and docs management functionality. Users should migrate to AsyncWebCrawler.
This commit is contained in:
@@ -14,6 +14,8 @@ from .extraction_strategy import (
|
||||
JsonCssExtractionStrategy,
|
||||
JsonXPathExtractionStrategy
|
||||
)
|
||||
|
||||
|
||||
from .chunking_strategy import ChunkingStrategy, RegexChunking
|
||||
from .markdown_generation_strategy import DefaultMarkdownGenerator
|
||||
from .content_filter_strategy import PruningContentFilter, BM25ContentFilter, LLMContentFilter, RelevantContentFilter
|
||||
@@ -26,10 +28,12 @@ from .async_dispatcher import (
|
||||
DisplayMode,
|
||||
BaseDispatcher
|
||||
)
|
||||
from .hub import CrawlerHub
|
||||
|
||||
__all__ = [
|
||||
"AsyncWebCrawler",
|
||||
"CrawlResult",
|
||||
"CrawlerHub",
|
||||
"CacheMode",
|
||||
"ContentScrapingStrategy",
|
||||
"WebScrapingStrategy",
|
||||
|
||||
Reference in New Issue
Block a user