@ooneex/html 0.0.4

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Ooneex
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -0,0 +1 @@
+# @ooneex/html

package/dist/index.d.ts

@@ -0,0 +1,235 @@
+/**
+* Heading information extracted from HTML
+*/
+interface HtmlHeadingType {
+	/**
+	* Heading level (1-6)
+	*/
+	level: number;
+	/**
+	* Heading text content
+	*/
+	text: string;
+	/**
+	* Heading id attribute
+	*/
+	id: string | null;
+}
+/**
+* Link information extracted from HTML
+*/
+interface HtmlLinkType {
+	/**
+	* Link href URL
+	*/
+	href: string;
+	/**
+	* Link text content
+	*/
+	text: string | null;
+	/**
+	* Link title attribute
+	*/
+	title: string | null;
+	/**
+	* Link target attribute
+	*/
+	target: string | null;
+	/**
+	* Link rel attribute
+	*/
+	rel: string | null;
+}
+/**
+* Image information extracted from HTML
+*/
+interface HtmlImageType {
+	/**
+	* Image source URL
+	*/
+	src: string;
+	/**
+	* Image alt text
+	*/
+	alt: string | null;
+	/**
+	* Image title attribute
+	*/
+	title: string | null;
+	/**
+	* Image width attribute
+	*/
+	width: string | null;
+	/**
+	* Image height attribute
+	*/
+	height: string | null;
+}
+/**
+* Task information extracted from HTML (checkbox list items)
+*/
+interface HtmlTaskType {
+	/**
+	* Task text content
+	*/
+	text: string;
+	/**
+	* Whether the task is checked/completed
+	*/
+	checked: boolean;
+}
+/**
+* Video information extracted from HTML
+*/
+interface HtmlVideoType {
+	/**
+	* Video source URL
+	*/
+	src: string | null;
+	/**
+	* Video poster image URL
+	*/
+	poster: string | null;
+	/**
+	* Video width attribute
+	*/
+	width: string | null;
+	/**
+	* Video height attribute
+	*/
+	height: string | null;
+	/**
+	* Video controls attribute
+	*/
+	controls: boolean;
+	/**
+	* Video autoplay attribute
+	*/
+	autoplay: boolean;
+	/**
+	* Video loop attribute
+	*/
+	loop: boolean;
+	/**
+	* Video muted attribute
+	*/
+	muted: boolean;
+	/**
+	* Video source elements
+	*/
+	sources: {
+		src: string;
+		type: string | null;
+	}[];
+}
+/**
+* Interface for HTML class
+*/
+interface IHtml {
+	/**
+	* Load HTML from a string
+	* @param html - HTML string to parse
+	* @returns this instance for chaining
+	*/
+	load(html: string): this;
+	/**
+	* Load HTML from a URL using Cheerio's fromURL method
+	* @param url - URL to fetch HTML from
+	* @returns Promise resolving to this instance for chaining
+	*/
+	loadUrl(url: string | URL): Promise<this>;
+	/**
+	* Get the text content of the HTML document
+	* @returns Trimmed text content
+	*/
+	getContent(): string;
+	/**
+	* Get the full HTML string of the document
+	* @returns HTML string
+	*/
+	getHtml(): string;
+	/**
+	* Extract all images from the HTML document
+	* @returns Array of image information
+	*/
+	getImages(): HtmlImageType[];
+	/**
+	* Extract all links from the HTML document
+	* @returns Array of link information
+	*/
+	getLinks(): HtmlLinkType[];
+	/**
+	* Extract all headings from the HTML document
+	* @returns Array of heading information
+	*/
+	getHeadings(): HtmlHeadingType[];
+	/**
+	* Extract all videos from the HTML document
+	* @returns Array of video information
+	*/
+	getVideos(): HtmlVideoType[];
+	/**
+	* Extract all tasks (checkbox list items) from the HTML document
+	* @returns Array of task information
+	*/
+	getTasks(): HtmlTaskType[];
+}
+/**
+* HTML document parser and analyzer using Cheerio
+*/
+declare class Html implements IHtml {
+	private $;
+	constructor();
+	/**
+	* Load HTML from a string
+	* @param html - HTML string to parse
+	* @returns this instance for chaining
+	*/
+	load(html: string): this;
+	/**
+	* Load HTML from a URL using Cheerio's fromURL method
+	* @param url - URL to fetch HTML from
+	* @returns Promise resolving to this instance for chaining
+	*/
+	loadUrl(url: string | URL): Promise<this>;
+	/**
+	* Get the text content of the HTML document
+	* @returns Trimmed text content
+	*/
+	getContent(): string;
+	/**
+	* Get the full HTML string of the document
+	* @returns HTML string
+	*/
+	getHtml(): string;
+	/**
+	* Extract all images from the HTML document
+	* @returns Array of image information
+	*/
+	getImages(): HtmlImageType[];
+	/**
+	* Extract all links from the HTML document
+	* @returns Array of link information
+	*/
+	getLinks(): HtmlLinkType[];
+	/**
+	* Extract all headings from the HTML document
+	* @returns Array of heading information
+	*/
+	getHeadings(): HtmlHeadingType[];
+	/**
+	* Extract all videos from the HTML document
+	* @returns Array of video information
+	*/
+	getVideos(): HtmlVideoType[];
+	/**
+	* Extract all tasks (checkbox list items) from the HTML document
+	* @returns Array of task information
+	*/
+	getTasks(): HtmlTaskType[];
+}
+import { Exception } from "@ooneex/exception";
+declare class HtmlException extends Exception {
+	constructor(message: string, data?: Record<string, unknown>);
+}
+export { IHtml, HtmlVideoType, HtmlTaskType, HtmlLinkType, HtmlImageType, HtmlHeadingType, HtmlException, Html };

package/dist/index.js

@@ -0,0 +1,3 @@
+import*as j from"cheerio";import{Exception as G}from"@ooneex/exception";import{HttpStatus as J}from"@ooneex/http-status";class x extends G{constructor(w,C={}){super(w,{status:J.Code.InternalServerError,data:C});this.name="HtmlException"}}class F{$;constructor(){this.$=j.load("")}load(w){return this.$=j.load(w),this}async loadUrl(w){let C=w instanceof URL?w.toString():w;try{return this.$=await j.fromURL(C),this}catch(R){throw new x(`Failed to fetch URL: ${C}`,{status:500,data:{url:C,error:R instanceof Error?R.message:String(R)}})}}getContent(){return this.$.text().trim()}getHtml(){return this.$.html().trim()??""}getImages(){let w=this.$,C=[];return w("img").each((R,I)=>{let p=w(I),H=p.attr("src");if(H)C.push({src:H,alt:p.attr("alt")||null,title:p.attr("title")||null,width:p.attr("width")||null,height:p.attr("height")||null})}),C}getLinks(){let w=this.$,C=[];return w("a").each((R,I)=>{let p=w(I),H=p.attr("href");if(H)C.push({href:H,text:p.text().trim()||null,title:p.attr("title")||null,target:p.attr("target")||null,rel:p.attr("rel")||null})}),C}getHeadings(){let w=this.$,C=[];return w("h1, h2, h3, h4, h5, h6").each((R,I)=>{let p=w(I),H=I.tagName.toLowerCase(),q=Number.parseInt(H.charAt(1),10);C.push({level:q,text:p.text().trim(),id:p.attr("id")||null})}),C}getVideos(){let w=this.$,C=[];return w("video").each((R,I)=>{let p=w(I),H=[];p.find("source").each((q,z)=>{let B=w(z),D=B.attr("src");if(D)H.push({src:D,type:B.attr("type")||null})}),C.push({src:p.attr("src")||null,poster:p.attr("poster")||null,width:p.attr("width")||null,height:p.attr("height")||null,controls:p.attr("controls")!==void 0,autoplay:p.attr("autoplay")!==void 0,loop:p.attr("loop")!==void 0,muted:p.attr("muted")!==void 0,sources:H})}),C}getTasks(){let w=this.$,C=[];return w('input[type="checkbox"]').each((R,I)=>{let p=w(I),H=p.parent(),q=p.attr("checked")!==void 0,z=H.text().trim();C.push({text:z,checked:q})}),C}}export{x as HtmlException,F as Html};
+
+//# debugId=F91403C7DF5ED76864756E2164756E21

package/dist/index.js.map

@@ -0,0 +1,11 @@
+{
+  "version": 3,
+  "sources": ["src/Html.ts", "src/HtmlException.ts"],
+  "sourcesContent": [
+    "import type { CheerioAPI } from \"cheerio\";\nimport * as cheerio from \"cheerio\";\nimport { HtmlException } from \"./HtmlException\";\nimport type { HtmlHeadingType, HtmlImageType, HtmlLinkType, HtmlTaskType, HtmlVideoType, IHtml } from \"./types\";\n\n/**\n * HTML document parser and analyzer using Cheerio\n */\nexport class Html implements IHtml {\n  private $: CheerioAPI;\n\n  constructor() {\n    this.$ = cheerio.load(\"\");\n  }\n\n  /**\n   * Load HTML from a string\n   * @param html - HTML string to parse\n   * @returns this instance for chaining\n   */\n  public load(html: string): this {\n    this.$ = cheerio.load(html);\n    return this;\n  }\n\n  /**\n   * Load HTML from a URL using Cheerio's fromURL method\n   * @param url - URL to fetch HTML from\n   * @returns Promise resolving to this instance for chaining\n   */\n  public async loadUrl(url: string | URL): Promise<this> {\n    const urlString = url instanceof URL ? url.toString() : url;\n\n    try {\n      this.$ = await cheerio.fromURL(urlString);\n      return this;\n    } catch (error) {\n      throw new HtmlException(`Failed to fetch URL: ${urlString}`, {\n        status: 500,\n        data: {\n          url: urlString,\n          error: error instanceof Error ? error.message : String(error),\n        },\n      });\n    }\n  }\n\n  /**\n   * Get the text content of the HTML document\n   * @returns Trimmed text content\n   */\n  public getContent(): string {\n    return this.$.text().trim();\n  }\n\n  /**\n   * Get the full HTML string of the document\n   * @returns HTML string\n   */\n  public getHtml(): string {\n    return this.$.html().trim() ?? \"\";\n  }\n\n  /**\n   * Extract all images from the HTML document\n   * @returns Array of image information\n   */\n  public getImages(): HtmlImageType[] {\n    const $ = this.$;\n    const images: HtmlImageType[] = [];\n\n    $(\"img\").each((_, element) => {\n      const $img = $(element);\n      const src = $img.attr(\"src\");\n\n      if (src) {\n        images.push({\n          src,\n          alt: $img.attr(\"alt\") || null,\n          title: $img.attr(\"title\") || null,\n          width: $img.attr(\"width\") || null,\n          height: $img.attr(\"height\") || null,\n        });\n      }\n    });\n\n    return images;\n  }\n\n  /**\n   * Extract all links from the HTML document\n   * @returns Array of link information\n   */\n  public getLinks(): HtmlLinkType[] {\n    const $ = this.$;\n    const links: HtmlLinkType[] = [];\n\n    $(\"a\").each((_, element) => {\n      const $link = $(element);\n      const href = $link.attr(\"href\");\n\n      if (href) {\n        links.push({\n          href,\n          text: $link.text().trim() || null,\n          title: $link.attr(\"title\") || null,\n          target: $link.attr(\"target\") || null,\n          rel: $link.attr(\"rel\") || null,\n        });\n      }\n    });\n\n    return links;\n  }\n\n  /**\n   * Extract all headings from the HTML document\n   * @returns Array of heading information\n   */\n  public getHeadings(): HtmlHeadingType[] {\n    const $ = this.$;\n    const headings: HtmlHeadingType[] = [];\n\n    $(\"h1, h2, h3, h4, h5, h6\").each((_, element) => {\n      const $heading = $(element);\n      const tagName = element.tagName.toLowerCase();\n      const level = Number.parseInt(tagName.charAt(1), 10);\n\n      headings.push({\n        level,\n        text: $heading.text().trim(),\n        id: $heading.attr(\"id\") || null,\n      });\n    });\n\n    return headings;\n  }\n\n  /**\n   * Extract all videos from the HTML document\n   * @returns Array of video information\n   */\n  public getVideos(): HtmlVideoType[] {\n    const $ = this.$;\n    const videos: HtmlVideoType[] = [];\n\n    $(\"video\").each((_, element) => {\n      const $video = $(element);\n      const sources: { src: string; type: string | null }[] = [];\n\n      $video.find(\"source\").each((_, sourceElement) => {\n        const $source = $(sourceElement);\n        const src = $source.attr(\"src\");\n\n        if (src) {\n          sources.push({\n            src,\n            type: $source.attr(\"type\") || null,\n          });\n        }\n      });\n\n      videos.push({\n        src: $video.attr(\"src\") || null,\n        poster: $video.attr(\"poster\") || null,\n        width: $video.attr(\"width\") || null,\n        height: $video.attr(\"height\") || null,\n        controls: $video.attr(\"controls\") !== undefined,\n        autoplay: $video.attr(\"autoplay\") !== undefined,\n        loop: $video.attr(\"loop\") !== undefined,\n        muted: $video.attr(\"muted\") !== undefined,\n        sources,\n      });\n    });\n\n    return videos;\n  }\n\n  /**\n   * Extract all tasks (checkbox list items) from the HTML document\n   * @returns Array of task information\n   */\n  public getTasks(): HtmlTaskType[] {\n    const $ = this.$;\n    const tasks: HtmlTaskType[] = [];\n\n    $('input[type=\"checkbox\"]').each((_, element) => {\n      const $checkbox = $(element);\n      const $parent = $checkbox.parent();\n      const checked = $checkbox.attr(\"checked\") !== undefined;\n\n      const text = $parent.text().trim();\n\n      tasks.push({\n        text,\n        checked,\n      });\n    });\n\n    return tasks;\n  }\n}\n",
+    "import { Exception } from \"@ooneex/exception\";\nimport { HttpStatus } from \"@ooneex/http-status\";\n\nexport class HtmlException extends Exception {\n  constructor(message: string, data: Record<string, unknown> = {}) {\n    super(message, {\n      status: HttpStatus.Code.InternalServerError,\n      data,\n    });\n    this.name = \"HtmlException\";\n  }\n}\n"
+  ],
+  "mappings": "AACA,0BCDA,oBAAS,0BACT,qBAAS,4BAEF,MAAM,UAAsB,CAAU,CAC3C,WAAW,CAAC,EAAiB,EAAgC,CAAC,EAAG,CAC/D,MAAM,EAAS,CACb,OAAQ,EAAW,KAAK,oBACxB,MACF,CAAC,EACD,KAAK,KAAO,gBAEhB,CDHO,MAAM,CAAsB,CACzB,EAER,WAAW,EAAG,CACZ,KAAK,EAAY,OAAK,EAAE,EAQnB,IAAI,CAAC,EAAoB,CAE9B,OADA,KAAK,EAAY,OAAK,CAAI,EACnB,UAQI,QAAO,CAAC,EAAkC,CACrD,IAAM,EAAY,aAAe,IAAM,EAAI,SAAS,EAAI,EAExD,GAAI,CAEF,OADA,KAAK,EAAI,MAAc,UAAQ,CAAS,EACjC,KACP,MAAO,EAAO,CACd,MAAM,IAAI,EAAc,wBAAwB,IAAa,CAC3D,OAAQ,IACR,KAAM,CACJ,IAAK,EACL,MAAO,aAAiB,MAAQ,EAAM,QAAU,OAAO,CAAK,CAC9D,CACF,CAAC,GAQE,UAAU,EAAW,CAC1B,OAAO,KAAK,EAAE,KAAK,EAAE,KAAK,EAOrB,OAAO,EAAW,CACvB,OAAO,KAAK,EAAE,KAAK,EAAE,KAAK,GAAK,GAO1B,SAAS,EAAoB,CAClC,IAAM,EAAI,KAAK,EACT,EAA0B,CAAC,EAiBjC,OAfA,EAAE,KAAK,EAAE,KAAK,CAAC,EAAG,IAAY,CAC5B,IAAM,EAAO,EAAE,CAAO,EAChB,EAAM,EAAK,KAAK,KAAK,EAE3B,GAAI,EACF,EAAO,KAAK,CACV,MACA,IAAK,EAAK,KAAK,KAAK,GAAK,KACzB,MAAO,EAAK,KAAK,OAAO,GAAK,KAC7B,MAAO,EAAK,KAAK,OAAO,GAAK,KAC7B,OAAQ,EAAK,KAAK,QAAQ,GAAK,IACjC,CAAC,EAEJ,EAEM,EAOF,QAAQ,EAAmB,CAChC,IAAM,EAAI,KAAK,EACT,EAAwB,CAAC,EAiB/B,OAfA,EAAE,GAAG,EAAE,KAAK,CAAC,EAAG,IAAY,CAC1B,IAAM,EAAQ,EAAE,CAAO,EACjB,EAAO,EAAM,KAAK,MAAM,EAE9B,GAAI,EACF,EAAM,KAAK,CACT,OACA,KAAM,EAAM,KAAK,EAAE,KAAK,GAAK,KAC7B,MAAO,EAAM,KAAK,OAAO,GAAK,KAC9B,OAAQ,EAAM,KAAK,QAAQ,GAAK,KAChC,IAAK,EAAM,KAAK,KAAK,GAAK,IAC5B,CAAC,EAEJ,EAEM,EAOF,WAAW,EAAsB,CACtC,IAAM,EAAI,KAAK,EACT,EAA8B,CAAC,EAcrC,OAZA,EAAE,wBAAwB,EAAE,KAAK,CAAC,EAAG,IAAY,CAC/C,IAAM,EAAW,EAAE,CAAO,EACpB,EAAU,EAAQ,QAAQ,YAAY,EACtC,EAAQ,OAAO,SAAS,EAAQ,OAAO,CAAC,EAAG,EAAE,EAEnD,EAAS,KAAK,CACZ,QACA,KAAM,EAAS,KAAK,EAAE,KAAK,EAC3B,GAAI,EAAS,KAAK,IAAI,GAAK,IAC7B,CAAC,EACF,EAEM,EAOF,SAAS,EAAoB,CAClC,IAAM,EAAI,KAAK,EACT,EAA0B,CAAC,EA+BjC,OA7BA,EAAE,OAAO,EAAE,KAAK,CAAC,EAAG,IAAY,CAC9B,IAAM,EAAS,EAAE,CAAO,EAClB,EAAkD,CAAC,EAEzD,EAAO,KAAK,QAAQ,EAAE,KAAK,CAAC,EAAG,IAAkB,CAC/C,IAAM,EAAU,EAAE,CAAa,EACzB,EAAM,EAAQ,KAAK,KAAK,EAE9B,GAAI,EACF,EAAQ,KAAK,CACX,MACA,KAAM,EAAQ,KAAK,MAAM,GAAK,IAChC,CAAC,EAEJ,EAED,EAAO,KAAK,CACV,IAAK,EAAO,KAAK,KAAK,GAAK,KAC3B,OAAQ,EAAO,KAAK,QAAQ,GAAK,KACjC,MAAO,EAAO,KAAK,OAAO,GAAK,KAC/B,OAAQ,EAAO,KAAK,QAAQ,GAAK,KACjC,SAAU,EAAO,KAAK,UAAU,IAAM,OACtC,SAAU,EAAO,KAAK,UAAU,IAAM,OACtC,KAAM,EAAO,KAAK,MAAM,IAAM,OAC9B,MAAO,EAAO,KAAK,OAAO,IAAM,OAChC,SACF,CAAC,EACF,EAEM,EAOF,QAAQ,EAAmB,CAChC,IAAM,EAAI,KAAK,EACT,EAAwB,CAAC,EAe/B,OAbA,EAAE,wBAAwB,EAAE,KAAK,CAAC,EAAG,IAAY,CAC/C,IAAM,EAAY,EAAE,CAAO,EACrB,EAAU,EAAU,OAAO,EAC3B,EAAU,EAAU,KAAK,SAAS,IAAM,OAExC,EAAO,EAAQ,KAAK,EAAE,KAAK,EAEjC,EAAM,KAAK,CACT,OACA,SACF,CAAC,EACF,EAEM,EAEX",
+  "debugId": "F91403C7DF5ED76864756E2164756E21",
+  "names": []
+}

package/package.json

@@ -0,0 +1,46 @@
+{
+  "name": "@ooneex/html",
+  "description": "HTML parsing and DOM manipulation utilities powered by Cheerio",
+  "version": "0.0.4",
+  "type": "module",
+  "files": [
+    "dist",
+    "LICENSE",
+    "README.md",
+    "package.json"
+  ],
+  "module": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "exports": {
+    ".": {
+      "import": {
+        "types": "./dist/index.d.ts",
+        "default": "./dist/index.js"
+      }
+    },
+    "./package.json": "./package.json"
+  },
+  "license": "MIT",
+  "scripts": {
+    "test": "bun test tests",
+    "build": "bunup",
+    "lint": "tsgo --noEmit && bunx biome lint",
+    "publish": "bun publish --access public || true"
+  },
+  "dependencies": {
+    "@ooneex/exception": "0.0.1",
+    "@ooneex/http-status": "0.0.1",
+    "cheerio": "^1.1.2"
+  },
+  "keywords": [
+    "bun",
+    "cheerio",
+    "dom",
+    "html",
+    "markup",
+    "ooneex",
+    "parser",
+    "template",
+    "typescript"
+  ]
+}