Struct HtmlParserConfig 

pub struct HtmlParserConfig {
    pub preserve_whitespace: bool,
    pub extract_images: bool,
    pub extract_links: bool,
    pub heading_strategy: HeadingStrategy,
    pub max_depth: usize,
    pub max_blocks: usize,
    pub min_text_length: usize,
}

Configuration for HTML parsing

Fields

preserve_whitespace: bool

Whether to preserve whitespace in text nodes

extract_images: bool

Whether to extract images as media blocks

extract_links: bool

Whether to extract links and store href in edges

heading_strategy: HeadingStrategy

Strategy for handling heading levels

max_depth: usize

Maximum nesting depth to process

max_blocks: usize

Maximum number of blocks to create

min_text_length: usize

Minimum text length to create a block (filters noise)

Trait Implementations

impl Clone for HtmlParserConfig

fn clone(&self) -> HtmlParserConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for HtmlParserConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for HtmlParserConfig

fn default() -> Self

Returns the “default value” for a type.