Struct ParserConfig 

pub struct ParserConfig {
    pub base_url: Option<Url>,
    pub max_text_length: usize,
    pub extract_images: bool,
    pub extract_links: bool,
    pub extract_tables: bool,
    pub extract_code_blocks: bool,
    pub extract_structured_data: bool,
    pub compute_readability: bool,
    pub min_paragraph_length: usize,
    pub content_selectors: Vec<String>,
    pub remove_selectors: Vec<String>,
    pub preserve_whitespace: bool,
}

Configuration for the HTML parser

Fields

base_url: Option<Url>

Base URL for resolving relative URLs

max_text_length: usize

Maximum text length to extract

extract_images: bool

Whether to extract images

extract_links: bool

Whether to extract links

extract_tables: bool

Whether to extract tables

extract_code_blocks: bool

Whether to extract code blocks

extract_structured_data: bool

Whether to extract structured data

compute_readability: bool

Whether to compute readability scores

min_paragraph_length: usize

Minimum paragraph length to include

content_selectors: Vec<String>

Content selectors (CSS selectors for main content)

remove_selectors: Vec<String>

Selectors for elements to remove (ads, nav, footer, etc.)

preserve_whitespace: bool

Whether to preserve whitespace

Implementations

impl ParserConfig

pub fn with_base_url(url: impl AsRef<str>) -> Result<Self, ParseError>

Create a new config with base URL

pub fn minimal() -> Self

Create minimal config (faster, less extraction)

pub fn full() -> Self

Create config for full extraction

pub fn base_url(self, url: Url) -> Self

Set base URL

pub fn add_content_selector(self, selector: impl Into<String>) -> Self

Add content selector

pub fn add_remove_selector(self, selector: impl Into<String>) -> Self

Add remove selector

Trait Implementations

impl Clone for ParserConfig

fn clone(&self) -> ParserConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ParserConfig

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

Formats the value using the given formatter.

impl Default for ParserConfig

fn default() -> Self

Returns the “default value” for a type.