Struct HtmlCleaner 

pub struct HtmlCleaner { /* private fields */ }

HTML cleaning utility.

Provides methods for removing, stripping, and normalizing HTML elements.

Example

use html_cleaning::{HtmlCleaner, CleaningOptions};
use dom_query::Document;

let options = CleaningOptions {
    tags_to_remove: vec!["script".into(), "style".into()],
    prune_empty: true,
    ..Default::default()
};

let cleaner = HtmlCleaner::with_options(options);
let doc = Document::from("<div><script>x</script><p>Hello</p></div>");
cleaner.clean(&doc);
assert!(doc.select("script").is_empty());

Implementations

impl HtmlCleaner

pub fn new() -> Self

Create a cleaner with default options.

pub fn with_options(options: CleaningOptions) -> Self

Create a cleaner with custom options.

pub fn options(&self) -> &CleaningOptions

Get a reference to the current options.

pub fn clean(&self, doc: &Document)

Apply all configured cleaning operations to the document.

Operations are applied in this order:

1. Remove tags (with children)
2. Strip tags (keep children)
3. Remove by CSS selector
4. Remove HTML comments
5. Prune empty elements
6. Normalize whitespace
7. Clean attributes

pub fn remove_comments(&self, doc: &Document)

Remove HTML comment nodes from the document.

Walks the entire DOM tree and removes all comment nodes (<!-- ... -->).

Example

use html_cleaning::HtmlCleaner;
use dom_query::Document;

let cleaner = HtmlCleaner::new();
let doc = Document::from("<div><!-- comment --><p>Content</p></div>");
cleaner.remove_comments(&doc);

pub fn remove_tags(&self, doc: &Document, tags: &[&str])

Remove elements matching tags (including all children).

Example

use html_cleaning::HtmlCleaner;
use dom_query::Document;

let cleaner = HtmlCleaner::new();
let doc = Document::from("<div><script>bad</script><p>good</p></div>");
cleaner.remove_tags(&doc, &["script"]);
assert!(doc.select("script").is_empty());

pub fn strip_tags(&self, doc: &Document, tags: &[&str])

Strip tags but preserve their children.

The tag wrapper is removed but inner content (text and child elements) is moved to the parent.

Example

use html_cleaning::HtmlCleaner;
use dom_query::Document;

let cleaner = HtmlCleaner::new();
let doc = Document::from("<div><span>text</span></div>");
cleaner.strip_tags(&doc, &["span"]);
assert!(doc.select("span").is_empty());

pub fn remove_by_selector(&self, doc: &Document, selector: &str)

Remove elements matching a CSS selector.

Example

use html_cleaning::HtmlCleaner;
use dom_query::Document;

let cleaner = HtmlCleaner::new();
let doc = Document::from(r#"<div class="ad">Ad</div><p>Content</p>"#);
cleaner.remove_by_selector(&doc, ".ad");
assert!(doc.select(".ad").is_empty());

pub fn prune_empty(&self, doc: &Document)

Remove empty elements.

Elements are considered empty if they:

• Have no child elements
• Have no text content (or only whitespace)

Processes in reverse document order (children before parents).

pub fn normalize_text(&self, doc: &Document)

Normalize text nodes (trim, collapse whitespace).

Walks all text nodes and collapses multiple whitespace to single space.

pub fn clean_attributes(&self, doc: &Document)

Remove or filter attributes from all elements.

If strip_attributes is true in options:

• Removes all attributes except those in preserved_attributes

Trait Implementations

impl Clone for HtmlCleaner

fn clone(&self) -> HtmlCleaner

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for HtmlCleaner

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

Formats the value using the given formatter.

impl Default for HtmlCleaner

fn default() -> Self

Returns the “default value” for a type.