Skip to main content

extract_single

content_extractor_rl::cli_utils

Function extract_single 

Source 
pub fn extract_single(
    html_file: &Path,
    url: String,
    model_path: Option<&Path>,
    classifier_path: Option<&Path>,
    output: Option<&Path>,
    config: &Config,
) -> Result<ExtractedArticle>
Expand description

Extract article from single HTML file.

Selection priority: RL model_path (if any) → trained classifier_path (if any) → hybrid heuristic.