Struct LinkExtractOptions 

pub struct LinkExtractOptions {

    pub same_site_only: bool,
    pub include_text_links: bool,
    pub sources: Vec<LinkSource>,
    pub allowed_link_types: Option<Vec<LinkType>>,
    pub denied_link_types: Vec<LinkType>,
    pub allow_patterns: Vec<String>,
    pub deny_patterns: Vec<String>,
    pub allow_domains: Vec<String>,
    pub deny_domains: Vec<String>,
    pub allow_path_prefixes: Vec<String>,
    pub deny_path_prefixes: Vec<String>,
    pub allowed_tags: Option<Vec<String>>,
    pub allowed_attributes: Option<Vec<String>>,
}

Options that control link extraction from a Response.

The defaults are intentionally conservative for crawler use: same-site filtering is enabled, text links are included, and common HTML elements are scanned for navigable URLs.

Fields

same_site_only: bool

Restrict discovered links to the same registered domain.

include_text_links: bool

Include URLs found in text content.

sources: Vec<LinkSource>

HTML sources used to discover attribute-based links.

allowed_link_types: Option<Vec<LinkType>>

Optional allow-list of link types to include.

denied_link_types: Vec<LinkType>

Optional deny-list of link types to exclude.

allow_patterns: Vec<String>

Optional allow-list of glob-style URL patterns (* and ? supported).

deny_patterns: Vec<String>

Optional deny-list of glob-style URL patterns (* and ? supported).

allow_domains: Vec<String>

Optional allow-list of domains or registered-domain suffixes.

deny_domains: Vec<String>

Optional deny-list of domains or registered-domain suffixes.

allow_path_prefixes: Vec<String>

Optional allow-list of URL path prefixes.

deny_path_prefixes: Vec<String>

Optional deny-list of URL path prefixes.

allowed_tags: Option<Vec<String>>

Optional allow-list of HTML tag names used for attribute extraction.

allowed_attributes: Option<Vec<String>>

Optional allow-list of attribute names used for attribute extraction.

Implementations

impl LinkExtractOptions

pub fn same_site_only(self, same_site_only: bool) -> Self

Sets whether only same-site URLs should be returned.

pub fn include_text_links(self, include_text_links: bool) -> Self

Sets whether URLs found in text content should be returned.

pub fn with_sources(self, sources: impl IntoIterator<Item = LinkSource>) -> Self

Replaces the configured HTML extraction sources.

pub fn add_source(self, source: LinkSource) -> Self

Adds an HTML extraction source.

pub fn with_allowed_link_types( self, allowed_link_types: impl IntoIterator<Item = LinkType>, ) -> Self

Restricts extraction to the provided link types.

pub fn with_denied_link_types( self, denied_link_types: impl IntoIterator<Item = LinkType>, ) -> Self

Adds link types that should be excluded even if discovered.

pub fn allow_pattern(self, pattern: impl Into<String>) -> Self

Adds a glob-style allow pattern that URLs must match.

pub fn with_allow_patterns( self, patterns: impl IntoIterator<Item = impl Into<String>>, ) -> Self

Replaces the glob-style allow patterns.

pub fn deny_pattern(self, pattern: impl Into<String>) -> Self

Adds a glob-style deny pattern that excludes matching URLs.

pub fn with_deny_patterns( self, patterns: impl IntoIterator<Item = impl Into<String>>, ) -> Self

Replaces the glob-style deny patterns.

pub fn allow_domain(self, domain: impl Into<String>) -> Self

Adds a domain or registered-domain suffix to allow.

pub fn with_allow_domains( self, domains: impl IntoIterator<Item = impl Into<String>>, ) -> Self

Replaces the allowed domains.

pub fn deny_domain(self, domain: impl Into<String>) -> Self

Adds a domain or registered-domain suffix to deny.

pub fn with_deny_domains( self, domains: impl IntoIterator<Item = impl Into<String>>, ) -> Self

Replaces the denied domains.

pub fn allow_path_prefix(self, prefix: impl Into<String>) -> Self

Adds a URL path prefix that links must match.

pub fn with_allow_path_prefixes( self, prefixes: impl IntoIterator<Item = impl Into<String>>, ) -> Self

Replaces the allowed URL path prefixes.

pub fn deny_path_prefix(self, prefix: impl Into<String>) -> Self

Adds a URL path prefix that should be excluded.

pub fn with_deny_path_prefixes( self, prefixes: impl IntoIterator<Item = impl Into<String>>, ) -> Self

Replaces the denied URL path prefixes.

pub fn with_allowed_tags( self, tags: impl IntoIterator<Item = impl Into<String>>, ) -> Self

Restricts attribute-based extraction to specific HTML tag names.

pub fn with_allowed_attributes( self, attributes: impl IntoIterator<Item = impl Into<String>>, ) -> Self

Restricts attribute-based extraction to specific attribute names.

Trait Implementations

impl Clone for LinkExtractOptions

fn clone(&self) -> LinkExtractOptions

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LinkExtractOptions

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

Formats the value using the given formatter.

impl Default for LinkExtractOptions

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for LinkExtractOptions

fn eq(&self, other: &LinkExtractOptions) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Eq for LinkExtractOptions

impl StructuralPartialEq for LinkExtractOptions