@fast-scrape/wasm 0.1.6 → 0.2.1

package/README.md

@@ -5,7 +5,7 @@
 [![TypeScript](https://img.shields.io/badge/TypeScript-Ready-blue)](https://www.typescriptlang.org/)
 [![License](https://img.shields.io/npm/l/@fast-scrape/wasm)](../../LICENSE-MIT)
 
-**10-50x faster** HTML parsing in the browser. Native-speed parsing via WebAssembly.
+**Native-comparable** HTML parsing in the browser via WebAssembly. Achieves **1.5-2x faster** performance than DOMParser on large documents.
 
 ## Installation
 
@@ -115,15 +115,39 @@ function extractLinks(soup: Soup): string[] {
 
 </details>
 
+## Performance
+
+Native-speed parsing in browsers with SIMD acceleration:
+
+<details open>
+<summary><strong>Browser performance vs native DOMParser</strong></summary>
+
+| Operation | @fast-scrape/wasm | Native DOMParser | Notes |
+|-----------|------------------|------------------|-------|
+| Parse 100KB HTML | **2.1 ms** | 3.2 ms | 1.5x faster |
+| find(".class") | **0.3 µs** | N/A | CSS selector optimization |
+| find("#id") | **0.2 µs** | N/A | ID selector optimization |
+| Memory (100KB doc) | **8.4 MB** | 12.2 MB | 30% more efficient |
+
+**Key advantages:**
+- Compiled Rust guarantees memory safety
+- CSS selectors run in nanoseconds
+- Automatic SIMD acceleration on modern browsers
+- 50-70% memory reduction via zero-copy serialization
+
+</details>
+
 ## Bundle size
 
+Optimized package under 500 KB:
+
 | Build | Size |
 |-------|------|
-| Minified + gzip | ~150 KB |
+| Minified + gzip | **285 KB** |
 | Minified | ~400 KB |
 
 > [!TIP]
-> SIMD enabled automatically on Chrome 91+, Firefox 89+, Safari 16.4+.
+> SIMD enabled automatically on Chrome 91+, Firefox 89+, Safari 16.4+. Zero-copy serialization provides 50-70% memory savings in HTML extraction.
 
 ## Browser support
 
@@ -134,6 +158,15 @@ function extractLinks(soup: Soup): string[] {
 | Safari | 13+ | 16.4+ |
 | Edge | 80+ | 91+ |
 
+## Built on Servo and Cloudflare
+
+**Parsing & Selection (Servo browser engine):**
+- [html5ever](https://crates.io/crates/html5ever) — Spec-compliant HTML5 parser
+- [selectors](https://crates.io/crates/selectors) — CSS selector matching engine
+
+**Streaming Parser (Cloudflare):**
+- [lol_html](https://github.com/cloudflare/lol_html) — High-performance streaming HTML parser with constant-memory event-driven API
+
 ## Related packages
 
 | Platform | Package |

package/package.json

@@ -2,10 +2,10 @@
   "name": "@fast-scrape/wasm",
   "type": "module",
   "collaborators": [
-    "scrape-rs contributors"
+    "Andrei G. <k05h31@gmail.com>"
   ],
   "description": "WebAssembly bindings for scrape-rs HTML parsing library",
-  "version": "0.1.6",
+  "version": "0.2.1",
   "license": "MIT OR Apache-2.0",
   "repository": {
     "type": "git",

package/scrape_wasm.d.ts

@@ -1,6 +1,43 @@
 /* tslint:disable */
 /* eslint-disable */
 
+/**
+ * A pre-compiled CSS selector for efficient repeated matching.
+ *
+ * Compiled selectors avoid the overhead of parsing the selector string on each query.
+ *
+ * @example
+ * ```javascript
+ * import init, { CompiledSelector, Soup } from '@scrape-rs/wasm';
+ *
+ * await init();
+ *
+ * const selector = CompiledSelector.compile("div.item");
+ * const soup = new Soup("<div class='item'>A</div><div class='item'>B</div>");
+ * const items = soup.selectCompiled(selector);
+ * console.log(items.length); // 2
+ * ```
+ */
+export class CompiledSelector {
+    private constructor();
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Compile a CSS selector string.
+     *
+     * @param selector - The CSS selector to compile
+     * @returns A compiled selector
+     * @throws Error if the selector syntax is invalid
+     */
+    static compile(selector: string): CompiledSelector;
+    /**
+     * Get the original selector string.
+     *
+     * @returns The selector string that was compiled
+     */
+    readonly source: string;
+}
+
 /**
  * A parsed HTML document.
  *
@@ -37,6 +74,13 @@ export class Soup {
      * @throws Error if the selector syntax is invalid
      */
     findAll(selector: string): Tag[];
+    /**
+     * Find the first element matching a compiled selector.
+     *
+     * @param selector - A compiled CSS selector
+     * @returns The first matching Tag, or undefined if not found
+     */
+    findCompiled(selector: CompiledSelector): Tag | undefined;
     /**
      * Parses an HTML string into a Soup document.
      *
@@ -44,6 +88,26 @@ export class Soup {
      * @param config - Optional configuration options
      */
     constructor(html: string, config?: SoupConfig | null);
+    /**
+     * Parse an HTML fragment without html/body wrapper.
+     *
+     * @param html - HTML fragment string to parse
+     * @param context - Optional context element name (default: "body")
+     * @param config - Optional parsing configuration
+     * @returns A new Soup instance containing the fragment
+     *
+     * @example
+     * ```javascript
+     * // Parse without wrapper
+     * const soup = Soup.parseFragment("<div>A</div><div>B</div>");
+     * const divs = soup.findAll("div");
+     * console.log(divs.length); // 2
+     *
+     * // Parse with td context
+     * const tdSoup = Soup.parseFragment("<td>Cell</td>", "tr");
+     * ```
+     */
+    static parseFragment(html: string, context?: string | null, config?: SoupConfig | null): Soup;
     /**
      * Finds all elements matching a CSS selector (alias for findAll).
      *
@@ -51,6 +115,44 @@ export class Soup {
      * @returns Array of matching Tag instances
      */
     select(selector: string): Tag[];
+    /**
+     * Extract attribute values from all elements matching a selector.
+     *
+     * @param selector - CSS selector string
+     * @param attr - Attribute name to extract
+     * @returns Array of attribute values (undefined if attribute is missing)
+     * @throws Error if the selector syntax is invalid
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<a href='/a'>A</a><a href='/b'>B</a><a>C</a>");
+     * const hrefs = soup.selectAttr("a", "href");
+     * // hrefs: ["/a", "/b", undefined]
+     * ```
+     */
+    selectAttr(selector: string, attr: string): any[];
+    /**
+     * Find all elements matching a compiled selector.
+     *
+     * @param selector - A compiled CSS selector
+     * @returns Array of matching Tag instances
+     */
+    selectCompiled(selector: CompiledSelector): Tag[];
+    /**
+     * Extract text content from all elements matching a selector.
+     *
+     * @param selector - CSS selector string
+     * @returns Array of text content strings
+     * @throws Error if the selector syntax is invalid
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div>A</div><div>B</div>");
+     * const texts = soup.selectText("div");
+     * // texts: ["A", "B"]
+     * ```
+     */
+    selectText(selector: string): string[];
     /**
      * Get the HTML representation of the document.
      *
@@ -150,6 +252,44 @@ export class Tag {
      * @returns The attribute value, or undefined if not present
      */
     attr(name: string): string | undefined;
+    /**
+     * Get all direct child elements with a specific class.
+     *
+     * @param className - The class name to filter by
+     * @returns Array of matching child Tag instances
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div><p class='item'>A</p><span>B</span><p class='item'>C</p></div>");
+     * const div = soup.find("div");
+     * const items = div.childrenByClass("item");
+     * // items.length: 2
+     * ```
+     */
+    childrenByClass(class_name: string): Tag[];
+    /**
+     * Get all direct child elements with a specific tag name.
+     *
+     * @param name - The tag name to filter by
+     * @returns Array of matching child Tag instances
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div><p>A</p><span>B</span><p>C</p></div>");
+     * const div = soup.find("div");
+     * const paras = div.childrenByName("p");
+     * // paras.length: 2
+     * ```
+     */
+    childrenByName(name: string): Tag[];
+    /**
+     * Find the nearest ancestor matching a CSS selector.
+     *
+     * @param selector - CSS selector string
+     * @returns The nearest matching ancestor Tag, or undefined if not found
+     * @throws Error if the selector syntax is invalid
+     */
+    closest(selector: string): Tag | undefined;
     /**
      * Find the first descendant matching a CSS selector.
      *
@@ -166,6 +306,13 @@ export class Tag {
      * @throws Error if the selector syntax is invalid
      */
     findAll(selector: string): Tag[];
+    /**
+     * Find the first descendant matching a compiled selector.
+     *
+     * @param selector - A compiled CSS selector
+     * @returns The first matching Tag, or undefined if not found
+     */
+    findCompiled(selector: CompiledSelector): Tag | undefined;
     /**
      * Get an attribute value by name.
      *
@@ -194,6 +341,50 @@ export class Tag {
      * @returns Array of matching Tag instances
      */
     select(selector: string): Tag[];
+    /**
+     * Extract attribute values from all descendants matching a selector.
+     *
+     * @param selector - CSS selector string
+     * @param attr - Attribute name to extract
+     * @returns Array of attribute values (undefined if attribute is missing)
+     * @throws Error if the selector syntax is invalid
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div><a href='/a'>A</a><a href='/b'>B</a></div>");
+     * const div = soup.find("div");
+     * const hrefs = div.selectAttr("a", "href");
+     * // hrefs: ["/a", "/b"]
+     * ```
+     */
+    selectAttr(selector: string, attr: string): any[];
+    /**
+     * Find all descendants matching a compiled selector.
+     *
+     * @param selector - A compiled CSS selector
+     * @returns Array of matching Tag instances
+     */
+    selectCompiled(selector: CompiledSelector): Tag[];
+    /**
+     * Extract text content from all descendants matching a selector.
+     *
+     * @param selector - CSS selector string
+     * @returns Array of text content strings
+     * @throws Error if the selector syntax is invalid
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div><p>A</p><p>B</p></div>");
+     * const div = soup.find("div");
+     * const texts = div.selectText("p");
+     * // texts: ["A", "B"]
+     * ```
+     */
+    selectText(selector: string): string[];
+    /**
+     * Get all ancestor elements (alias for parents).
+     */
+    readonly ancestors: Tag[];
     /**
      * Get all attributes as an object.
      */
@@ -226,6 +417,10 @@ export class Tag {
      * Get the next sibling element.
      */
     readonly nextSibling: Tag | undefined;
+    /**
+     * Get all following sibling elements.
+     */
+    readonly nextSiblings: Tag[];
     /**
      * Get the outer HTML (including this element's tags).
      */
@@ -234,14 +429,40 @@ export class Tag {
      * Get the parent element.
      */
     readonly parent: Tag | undefined;
+    /**
+     * Get all ancestor elements (from parent toward root).
+     */
+    readonly parents: Tag[];
     /**
      * Get the previous sibling element.
      */
     readonly prevSibling: Tag | undefined;
+    /**
+     * Get all preceding sibling elements (in reverse order).
+     */
+    readonly prevSiblings: Tag[];
+    /**
+     * Get all sibling elements (excluding self, in document order).
+     */
+    readonly siblings: Tag[];
     /**
      * Get the text content of this element and all descendants.
      */
     readonly text: string;
+    /**
+     * Get all direct text nodes (excluding descendants).
+     *
+     * @returns Array of text content strings
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div>Text1<span>Inner</span>Text2</div>");
+     * const div = soup.find("div");
+     * const texts = div.textNodes;
+     * // texts: ["Text1", "Text2"]
+     * ```
+     */
+    readonly textNodes: string[];
 }
 
 /**
@@ -292,16 +513,24 @@ export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembl
 
 export interface InitOutput {
     readonly memory: WebAssembly.Memory;
+    readonly __wbg_compiledselector_free: (a: number, b: number) => void;
     readonly __wbg_soup_free: (a: number, b: number) => void;
     readonly __wbg_soupconfig_free: (a: number, b: number) => void;
     readonly __wbg_tag_free: (a: number, b: number) => void;
+    readonly compiledselector_compile: (a: number, b: number, c: number) => void;
+    readonly compiledselector_source: (a: number, b: number) => void;
     readonly hasSimdSupport: () => number;
     readonly parseBatch: (a: number, b: number, c: number) => void;
     readonly soup_find: (a: number, b: number, c: number, d: number) => void;
     readonly soup_findAll: (a: number, b: number, c: number, d: number) => void;
+    readonly soup_findCompiled: (a: number, b: number) => number;
     readonly soup_length: (a: number) => number;
     readonly soup_new: (a: number, b: number, c: number) => number;
+    readonly soup_parseFragment: (a: number, b: number, c: number, d: number, e: number) => number;
     readonly soup_root: (a: number) => number;
+    readonly soup_selectAttr: (a: number, b: number, c: number, d: number, e: number, f: number) => void;
+    readonly soup_selectCompiled: (a: number, b: number, c: number) => void;
+    readonly soup_selectText: (a: number, b: number, c: number, d: number) => void;
     readonly soup_text: (a: number, b: number) => void;
     readonly soup_title: (a: number, b: number) => void;
     readonly soup_toHtml: (a: number, b: number) => void;
@@ -314,28 +543,41 @@ export interface InitOutput {
     readonly soupconfig_set_preserveWhitespace: (a: number, b: number) => void;
     readonly soupconfig_set_strictMode: (a: number, b: number) => void;
     readonly soupconfig_strictMode: (a: number) => number;
+    readonly tag_ancestors: (a: number, b: number) => void;
     readonly tag_attr: (a: number, b: number, c: number, d: number) => void;
     readonly tag_attrs: (a: number) => number;
     readonly tag_children: (a: number, b: number) => void;
+    readonly tag_childrenByClass: (a: number, b: number, c: number, d: number) => void;
+    readonly tag_childrenByName: (a: number, b: number, c: number, d: number) => void;
     readonly tag_classes: (a: number, b: number) => void;
+    readonly tag_closest: (a: number, b: number, c: number, d: number) => void;
     readonly tag_descendants: (a: number, b: number) => void;
     readonly tag_find: (a: number, b: number, c: number, d: number) => void;
     readonly tag_findAll: (a: number, b: number, c: number, d: number) => void;
-    readonly tag_get: (a: number, b: number, c: number, d: number) => void;
+    readonly tag_findCompiled: (a: number, b: number) => number;
     readonly tag_hasAttr: (a: number, b: number, c: number) => number;
     readonly tag_hasClass: (a: number, b: number, c: number) => number;
     readonly tag_innerHTML: (a: number, b: number) => void;
     readonly tag_length: (a: number) => number;
     readonly tag_name: (a: number, b: number) => void;
     readonly tag_nextSibling: (a: number) => number;
+    readonly tag_nextSiblings: (a: number, b: number) => void;
     readonly tag_outerHTML: (a: number, b: number) => void;
     readonly tag_parent: (a: number) => number;
     readonly tag_prevSibling: (a: number) => number;
+    readonly tag_prevSiblings: (a: number, b: number) => void;
+    readonly tag_selectAttr: (a: number, b: number, c: number, d: number, e: number, f: number) => void;
+    readonly tag_selectCompiled: (a: number, b: number, c: number) => void;
+    readonly tag_selectText: (a: number, b: number, c: number, d: number) => void;
+    readonly tag_siblings: (a: number, b: number) => void;
     readonly tag_text: (a: number, b: number) => void;
+    readonly tag_textNodes: (a: number, b: number) => void;
     readonly version: (a: number) => void;
     readonly init: () => void;
     readonly soup_select: (a: number, b: number, c: number, d: number) => void;
     readonly tag_select: (a: number, b: number, c: number, d: number) => void;
+    readonly tag_parents: (a: number, b: number) => void;
+    readonly tag_get: (a: number, b: number, c: number, d: number) => void;
     readonly __wbindgen_export: (a: number, b: number) => number;
     readonly __wbindgen_export2: (a: number, b: number, c: number, d: number) => number;
     readonly __wbindgen_export3: (a: number, b: number, c: number) => void;

package/scrape_wasm.js

@@ -1,5 +1,91 @@
 /* @ts-self-types="./scrape_wasm.d.ts" */
 
+/**
+ * A pre-compiled CSS selector for efficient repeated matching.
+ *
+ * Compiled selectors avoid the overhead of parsing the selector string on each query.
+ *
+ * @example
+ * ```javascript
+ * import init, { CompiledSelector, Soup } from '@scrape-rs/wasm';
+ *
+ * await init();
+ *
+ * const selector = CompiledSelector.compile("div.item");
+ * const soup = new Soup("<div class='item'>A</div><div class='item'>B</div>");
+ * const items = soup.selectCompiled(selector);
+ * console.log(items.length); // 2
+ * ```
+ */
+export class CompiledSelector {
+    static __wrap(ptr) {
+        ptr = ptr >>> 0;
+        const obj = Object.create(CompiledSelector.prototype);
+        obj.__wbg_ptr = ptr;
+        CompiledSelectorFinalization.register(obj, obj.__wbg_ptr, obj);
+        return obj;
+    }
+    __destroy_into_raw() {
+        const ptr = this.__wbg_ptr;
+        this.__wbg_ptr = 0;
+        CompiledSelectorFinalization.unregister(this);
+        return ptr;
+    }
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_compiledselector_free(ptr, 0);
+    }
+    /**
+     * Compile a CSS selector string.
+     *
+     * @param selector - The CSS selector to compile
+     * @returns A compiled selector
+     * @throws Error if the selector syntax is invalid
+     * @param {string} selector
+     * @returns {CompiledSelector}
+     */
+    static compile(selector) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(selector, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.compiledselector_compile(retptr, ptr0, len0);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
+            if (r2) {
+                throw takeObject(r1);
+            }
+            return CompiledSelector.__wrap(r0);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+     * Get the original selector string.
+     *
+     * @returns The selector string that was compiled
+     * @returns {string}
+     */
+    get source() {
+        let deferred1_0;
+        let deferred1_1;
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.compiledselector_source(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            deferred1_0 = r0;
+            deferred1_1 = r1;
+            return getStringFromWasm0(r0, r1);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+            wasm.__wbindgen_export3(deferred1_0, deferred1_1, 1);
+        }
+    }
+}
+if (Symbol.dispose) CompiledSelector.prototype[Symbol.dispose] = CompiledSelector.prototype.free;
+
 /**
  * A parsed HTML document.
  *
@@ -90,6 +176,19 @@ export class Soup {
             wasm.__wbindgen_add_to_stack_pointer(16);
         }
     }
+    /**
+     * Find the first element matching a compiled selector.
+     *
+     * @param selector - A compiled CSS selector
+     * @returns The first matching Tag, or undefined if not found
+     * @param {CompiledSelector} selector
+     * @returns {Tag | undefined}
+     */
+    findCompiled(selector) {
+        _assertClass(selector, CompiledSelector);
+        const ret = wasm.soup_findCompiled(this.__wbg_ptr, selector.__wbg_ptr);
+        return ret === 0 ? undefined : Tag.__wrap(ret);
+    }
     /**
      * Get the number of nodes in the document.
      * @returns {number}
@@ -119,6 +218,42 @@ export class Soup {
         SoupFinalization.register(this, this.__wbg_ptr, this);
         return this;
     }
+    /**
+     * Parse an HTML fragment without html/body wrapper.
+     *
+     * @param html - HTML fragment string to parse
+     * @param context - Optional context element name (default: "body")
+     * @param config - Optional parsing configuration
+     * @returns A new Soup instance containing the fragment
+     *
+     * @example
+     * ```javascript
+     * // Parse without wrapper
+     * const soup = Soup.parseFragment("<div>A</div><div>B</div>");
+     * const divs = soup.findAll("div");
+     * console.log(divs.length); // 2
+     *
+     * // Parse with td context
+     * const tdSoup = Soup.parseFragment("<td>Cell</td>", "tr");
+     * ```
+     * @param {string} html
+     * @param {string | null} [context]
+     * @param {SoupConfig | null} [config]
+     * @returns {Soup}
+     */
+    static parseFragment(html, context, config) {
+        const ptr0 = passStringToWasm0(html, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+        const len0 = WASM_VECTOR_LEN;
+        var ptr1 = isLikeNone(context) ? 0 : passStringToWasm0(context, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+        var len1 = WASM_VECTOR_LEN;
+        let ptr2 = 0;
+        if (!isLikeNone(config)) {
+            _assertClass(config, SoupConfig);
+            ptr2 = config.__destroy_into_raw();
+        }
+        const ret = wasm.soup_parseFragment(ptr0, len0, ptr1, len1, ptr2);
+        return Soup.__wrap(ret);
+    }
     /**
      * Get the root element of the document.
      *
@@ -157,6 +292,104 @@ export class Soup {
             wasm.__wbindgen_add_to_stack_pointer(16);
         }
     }
+    /**
+     * Extract attribute values from all elements matching a selector.
+     *
+     * @param selector - CSS selector string
+     * @param attr - Attribute name to extract
+     * @returns Array of attribute values (undefined if attribute is missing)
+     * @throws Error if the selector syntax is invalid
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<a href='/a'>A</a><a href='/b'>B</a><a>C</a>");
+     * const hrefs = soup.selectAttr("a", "href");
+     * // hrefs: ["/a", "/b", undefined]
+     * ```
+     * @param {string} selector
+     * @param {string} attr
+     * @returns {any[]}
+     */
+    selectAttr(selector, attr) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(selector, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len0 = WASM_VECTOR_LEN;
+            const ptr1 = passStringToWasm0(attr, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len1 = WASM_VECTOR_LEN;
+            wasm.soup_selectAttr(retptr, this.__wbg_ptr, ptr0, len0, ptr1, len1);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
+            var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
+            if (r3) {
+                throw takeObject(r2);
+            }
+            var v3 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v3;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+     * Find all elements matching a compiled selector.
+     *
+     * @param selector - A compiled CSS selector
+     * @returns Array of matching Tag instances
+     * @param {CompiledSelector} selector
+     * @returns {Tag[]}
+     */
+    selectCompiled(selector) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            _assertClass(selector, CompiledSelector);
+            wasm.soup_selectCompiled(retptr, this.__wbg_ptr, selector.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v1 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+     * Extract text content from all elements matching a selector.
+     *
+     * @param selector - CSS selector string
+     * @returns Array of text content strings
+     * @throws Error if the selector syntax is invalid
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div>A</div><div>B</div>");
+     * const texts = soup.selectText("div");
+     * // texts: ["A", "B"]
+     * ```
+     * @param {string} selector
+     * @returns {string[]}
+     */
+    selectText(selector) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(selector, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.soup_selectText(retptr, this.__wbg_ptr, ptr0, len0);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
+            var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
+            if (r3) {
+                throw takeObject(r2);
+            }
+            var v2 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v2;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
     /**
      * Get the text content of the entire document.
      *
@@ -360,6 +593,23 @@ export class Tag {
         const ptr = this.__destroy_into_raw();
         wasm.__wbg_tag_free(ptr, 0);
     }
+    /**
+     * Get all ancestor elements (alias for parents).
+     * @returns {Tag[]}
+     */
+    get ancestors() {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tag_ancestors(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v1 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
     /**
      * Get an attribute value by name (alias for get).
      *
@@ -411,6 +661,68 @@ export class Tag {
             wasm.__wbindgen_add_to_stack_pointer(16);
         }
     }
+    /**
+     * Get all direct child elements with a specific class.
+     *
+     * @param className - The class name to filter by
+     * @returns Array of matching child Tag instances
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div><p class='item'>A</p><span>B</span><p class='item'>C</p></div>");
+     * const div = soup.find("div");
+     * const items = div.childrenByClass("item");
+     * // items.length: 2
+     * ```
+     * @param {string} class_name
+     * @returns {Tag[]}
+     */
+    childrenByClass(class_name) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(class_name, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tag_childrenByClass(retptr, this.__wbg_ptr, ptr0, len0);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v2 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v2;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+     * Get all direct child elements with a specific tag name.
+     *
+     * @param name - The tag name to filter by
+     * @returns Array of matching child Tag instances
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div><p>A</p><span>B</span><p>C</p></div>");
+     * const div = soup.find("div");
+     * const paras = div.childrenByName("p");
+     * // paras.length: 2
+     * ```
+     * @param {string} name
+     * @returns {Tag[]}
+     */
+    childrenByName(name) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(name, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tag_childrenByName(retptr, this.__wbg_ptr, ptr0, len0);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v2 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v2;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
     /**
      * Get all classes as an array.
      * @returns {string[]}
@@ -428,6 +740,32 @@ export class Tag {
             wasm.__wbindgen_add_to_stack_pointer(16);
         }
     }
+    /**
+     * Find the nearest ancestor matching a CSS selector.
+     *
+     * @param selector - CSS selector string
+     * @returns The nearest matching ancestor Tag, or undefined if not found
+     * @throws Error if the selector syntax is invalid
+     * @param {string} selector
+     * @returns {Tag | undefined}
+     */
+    closest(selector) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(selector, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tag_closest(retptr, this.__wbg_ptr, ptr0, len0);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
+            if (r2) {
+                throw takeObject(r1);
+            }
+            return r0 === 0 ? undefined : Tag.__wrap(r0);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
     /**
      * Get all descendant elements.
      * @returns {Tag[]}
@@ -500,6 +838,19 @@ export class Tag {
             wasm.__wbindgen_add_to_stack_pointer(16);
         }
     }
+    /**
+     * Find the first descendant matching a compiled selector.
+     *
+     * @param selector - A compiled CSS selector
+     * @returns The first matching Tag, or undefined if not found
+     * @param {CompiledSelector} selector
+     * @returns {Tag | undefined}
+     */
+    findCompiled(selector) {
+        _assertClass(selector, CompiledSelector);
+        const ret = wasm.tag_findCompiled(this.__wbg_ptr, selector.__wbg_ptr);
+        return ret === 0 ? undefined : Tag.__wrap(ret);
+    }
     /**
      * Get an attribute value by name.
      *
@@ -513,7 +864,7 @@ export class Tag {
             const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
             const ptr0 = passStringToWasm0(name, wasm.__wbindgen_export, wasm.__wbindgen_export2);
             const len0 = WASM_VECTOR_LEN;
-            wasm.tag_get(retptr, this.__wbg_ptr, ptr0, len0);
+            wasm.tag_attr(retptr, this.__wbg_ptr, ptr0, len0);
             var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
             var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
             let v2;
@@ -610,6 +961,23 @@ export class Tag {
         const ret = wasm.tag_nextSibling(this.__wbg_ptr);
         return ret === 0 ? undefined : Tag.__wrap(ret);
     }
+    /**
+     * Get all following sibling elements.
+     * @returns {Tag[]}
+     */
+    get nextSiblings() {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tag_nextSiblings(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v1 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
     /**
      * Get the outer HTML (including this element's tags).
      * @returns {string}
@@ -638,6 +1006,23 @@ export class Tag {
         const ret = wasm.tag_parent(this.__wbg_ptr);
         return ret === 0 ? undefined : Tag.__wrap(ret);
     }
+    /**
+     * Get all ancestor elements (from parent toward root).
+     * @returns {Tag[]}
+     */
+    get parents() {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tag_ancestors(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v1 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
     /**
      * Get the previous sibling element.
      * @returns {Tag | undefined}
@@ -646,6 +1031,23 @@ export class Tag {
         const ret = wasm.tag_prevSibling(this.__wbg_ptr);
         return ret === 0 ? undefined : Tag.__wrap(ret);
     }
+    /**
+     * Get all preceding sibling elements (in reverse order).
+     * @returns {Tag[]}
+     */
+    get prevSiblings() {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tag_prevSiblings(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v1 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
     /**
      * Find all descendants matching a CSS selector (alias for findAll).
      *
@@ -674,6 +1076,123 @@ export class Tag {
             wasm.__wbindgen_add_to_stack_pointer(16);
         }
     }
+    /**
+     * Extract attribute values from all descendants matching a selector.
+     *
+     * @param selector - CSS selector string
+     * @param attr - Attribute name to extract
+     * @returns Array of attribute values (undefined if attribute is missing)
+     * @throws Error if the selector syntax is invalid
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div><a href='/a'>A</a><a href='/b'>B</a></div>");
+     * const div = soup.find("div");
+     * const hrefs = div.selectAttr("a", "href");
+     * // hrefs: ["/a", "/b"]
+     * ```
+     * @param {string} selector
+     * @param {string} attr
+     * @returns {any[]}
+     */
+    selectAttr(selector, attr) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(selector, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len0 = WASM_VECTOR_LEN;
+            const ptr1 = passStringToWasm0(attr, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len1 = WASM_VECTOR_LEN;
+            wasm.tag_selectAttr(retptr, this.__wbg_ptr, ptr0, len0, ptr1, len1);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
+            var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
+            if (r3) {
+                throw takeObject(r2);
+            }
+            var v3 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v3;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+     * Find all descendants matching a compiled selector.
+     *
+     * @param selector - A compiled CSS selector
+     * @returns Array of matching Tag instances
+     * @param {CompiledSelector} selector
+     * @returns {Tag[]}
+     */
+    selectCompiled(selector) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            _assertClass(selector, CompiledSelector);
+            wasm.tag_selectCompiled(retptr, this.__wbg_ptr, selector.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v1 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+     * Extract text content from all descendants matching a selector.
+     *
+     * @param selector - CSS selector string
+     * @returns Array of text content strings
+     * @throws Error if the selector syntax is invalid
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div><p>A</p><p>B</p></div>");
+     * const div = soup.find("div");
+     * const texts = div.selectText("p");
+     * // texts: ["A", "B"]
+     * ```
+     * @param {string} selector
+     * @returns {string[]}
+     */
+    selectText(selector) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passStringToWasm0(selector, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len0 = WASM_VECTOR_LEN;
+            wasm.tag_selectText(retptr, this.__wbg_ptr, ptr0, len0);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
+            var r3 = getDataViewMemory0().getInt32(retptr + 4 * 3, true);
+            if (r3) {
+                throw takeObject(r2);
+            }
+            var v2 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v2;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+     * Get all sibling elements (excluding self, in document order).
+     * @returns {Tag[]}
+     */
+    get siblings() {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tag_siblings(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v1 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
     /**
      * Get the text content of this element and all descendants.
      * @returns {string}
@@ -694,6 +1213,33 @@ export class Tag {
             wasm.__wbindgen_export3(deferred1_0, deferred1_1, 1);
         }
     }
+    /**
+     * Get all direct text nodes (excluding descendants).
+     *
+     * @returns Array of text content strings
+     *
+     * @example
+     * ```javascript
+     * const soup = new Soup("<div>Text1<span>Inner</span>Text2</div>");
+     * const div = soup.find("div");
+     * const texts = div.textNodes;
+     * // texts: ["Text1", "Text2"]
+     * ```
+     * @returns {string[]}
+     */
+    get textNodes() {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.tag_textNodes(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var v1 = getArrayJsValueFromWasm0(r0, r1).slice();
+            wasm.__wbindgen_export3(r0, r1 * 4, 4);
+            return v1;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
 }
 if (Symbol.dispose) Tag.prototype[Symbol.dispose] = Tag.prototype.free;
 
@@ -850,6 +1396,9 @@ function __wbg_get_imports() {
     };
 }
 
+const CompiledSelectorFinalization = (typeof FinalizationRegistry === 'undefined')
+    ? { register: () => {}, unregister: () => {} }
+    : new FinalizationRegistry(ptr => wasm.__wbg_compiledselector_free(ptr >>> 0, 1));
 const SoupFinalization = (typeof FinalizationRegistry === 'undefined')
     ? { register: () => {}, unregister: () => {} }
     : new FinalizationRegistry(ptr => wasm.__wbg_soup_free(ptr >>> 0, 1));