Struct HybridExtractor 

pub struct HybridExtractor { /* private fields */ }

End-to-end hybrid extractor: the classifier (supervised) picks the content node, then the RL-tuned ExtractionParams drive block-level extraction within it. When no trained classifier is supplied it falls back to the Readability-style NodeFeatures::heuristic_content_score, so it is useful even before any training has happened.

Implementations

impl HybridExtractor

pub fn heuristic(stopwords: HashSet<String>) -> Self

Heuristic-only extractor (no learned model).

pub fn with_classifier( classifier: NodeClassifier, stopwords: HashSet<String>, ) -> Self

Extractor backed by a trained node classifier.

pub fn extract( &self, html: &str, num_candidates: usize, params: &ExtractionParams, ) -> Result<Option<HybridExtraction>>

Extract article content from a page. Returns None when the document exposes no candidate nodes.