Files
crawl4ai/crawl4ai/deep_crawling/__init__.py
Aravind a9e24307cc Release prep (#749)
* fix: Update export of URLPatternFilter

* chore: Add dependancy for cchardet in requirements

* docs: Update example for deep crawl in release note for v0.5

* Docs: update the example for memory dispatcher

* docs: updated example for crawl strategies

* Refactor: Removed wrapping in if __name__==main block since this is a markdown file.

* chore: removed cchardet from dependancy list, since unclecode is planning to remove it

* docs: updated the example for proxy rotation to a working example

* feat: Introduced ProxyConfig param

* Add tutorial for deep crawl & update contributor list for bug fixes in feb alpha-1

* chore: update and test new dependancies

* feat:Make PyPDF2 a conditional dependancy

* updated tutorial and release note for v0.5

* docs: update docs for deep crawl, and fix a typo in docker-deployment markdown filename

* refactor: 1. Deprecate markdown_v2 2. Make markdown backward compatible to behave as a string when needed. 3. Fix LlmConfig usage in cli 4. Deprecate markdown_v2 in cli 5. Update AsyncWebCrawler for changes in CrawlResult

* fix: Bug in serialisation of markdown in acache_url

* Refactor: Added deprecation errors for fit_html and fit_markdown directly on markdown. Now access them via markdown

* fix: remove deprecated markdown_v2 from docker

* Refactor: remove deprecated fit_markdown and fit_html from result

* refactor: fix cache retrieval for markdown as a string

* chore: update all docs, examples and tests with deprecation announcements for markdown_v2, fit_html, fit_markdown
2025-02-28 19:53:35 +08:00

48 lines
1.1 KiB
Python

# deep_crawling/__init__.py
from .base_strategy import DeepCrawlDecorator, DeepCrawlStrategy
from .bfs_strategy import BFSDeepCrawlStrategy
from .bff_strategy import BestFirstCrawlingStrategy
from .dfs_strategy import DFSDeepCrawlStrategy
from .filters import (
FilterChain,
ContentTypeFilter,
DomainFilter,
URLFilter,
URLPatternFilter,
FilterStats,
ContentRelevanceFilter,
SEOFilter
)
from .scorers import (
KeywordRelevanceScorer,
URLScorer,
CompositeScorer,
DomainAuthorityScorer,
FreshnessScorer,
PathDepthScorer,
ContentTypeScorer
)
__all__ = [
"DeepCrawlDecorator",
"DeepCrawlStrategy",
"BFSDeepCrawlStrategy",
"BestFirstCrawlingStrategy",
"DFSDeepCrawlStrategy",
"FilterChain",
"ContentTypeFilter",
"DomainFilter",
"URLFilter",
"URLPatternFilter",
"FilterStats",
"ContentRelevanceFilter",
"SEOFilter",
"KeywordRelevanceScorer",
"URLScorer",
"CompositeScorer",
"DomainAuthorityScorer",
"FreshnessScorer",
"PathDepthScorer",
"ContentTypeScorer",
]