extract-hrefs/dist/index.js

This library is used to extract hrefs from a given HTML string.

"use strict";
var __create = Object.create;
var __defProp = Object.defineProperty;
var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
var __getOwnPropNames = Object.getOwnPropertyNames;
var __getProtoOf = Object.getPrototypeOf;
var __hasOwnProp = Object.prototype.hasOwnProperty;
var __export = (target, all) => {
  for (var name in all)
    __defProp(target, name, { get: all[name], enumerable: true });
};
var __copyProps = (to, from, except, desc) => {
  if (from && typeof from === "object" || typeof from === "function") {
    for (let key of __getOwnPropNames(from))
      if (!__hasOwnProp.call(to, key) && key !== except)
        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
  }
  return to;
};
var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
  // If the importer is in node compatibility mode or this is not an ESM
  // file that has been converted to a CommonJS file using a Babel-
  // compatible transform (i.e. "__esModule" has not been set), then set
  // "default" to the CommonJS "module.exports" for node compatibility.
  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
  mod
));
var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);

// src/index.ts
var index_exports = {};
__export(index_exports, {
  default: () => index_default
});
module.exports = __toCommonJS(index_exports);
var cheerio = __toESM(require("cheerio"));
var import_normalize_url = __toESM(require("normalize-url"));
var normalizeUrls = (links) => {
  return links.map((link) => {
    try {
      return (0, import_normalize_url.default)(link, { stripWWW: false });
    } catch (error) {
      console.error(`Error normalizing URL: ${link}`, error);
      return link;
    }
  });
};
var extractHrefs = (htmlString) => {
  if (!htmlString || typeof htmlString !== "string") {
    throw new Error("HTML string is required");
  }
  const $ = cheerio.load(htmlString);
  const urls = [];
  $("a").each((index, element) => {
    const href = $(element).attr("href");
    if (href) {
      urls.push(href);
    }
  });
  return normalizeUrls(urls);
};
var index_default = extractHrefs;
//# sourceMappingURL=index.js.map