@synstack/web/dist/web.index.js

Web scraping utilities

var __defProp = Object.defineProperty;
var __export = (target, all) => {
  for (var name in all)
    __defProp(target, name, { get: all[name], enumerable: true });
};

// src/web.bundle.ts
var web_bundle_exports = {};
__export(web_bundle_exports, {
  fetchArticle: () => fetchArticle,
  fetchJson: () => fetchJson,
  fetchText: () => fetchText
});

// src/web.lib.ts
import { Readability } from "@mozilla/readability";
import { parseHTML } from "linkedom";
var fetchJson = (url, options = {}) => fetch(url).then((response) => response.json()).then((data) => options.schema ? options.schema.parse(data) : data);
var fetchText = (url) => fetch(url).then((response) => response.text());
var fetchArticle = async (url) => {
  const content = await fetchText(url);
  const doc = parseHTML(content, { url });
  const reader = new Readability(doc.window.document);
  const article = reader.parse();
  if (!article?.content) throw new ArticleNotFoundException(url);
  return {
    url,
    content: article.content,
    title: article.title,
    byline: article.byline,
    siteName: article.siteName,
    lang: article.lang,
    publishedTime: article.publishedTime
  };
};
var ArticleNotFoundException = class extends Error {
  constructor(url) {
    super(
      `
No article found at the URL
URL: ${url}
`.trim()
    );
  }
};
export {
  ArticleNotFoundException,
  fetchArticle,
  fetchJson,
  fetchText,
  web_bundle_exports as web
};
//# sourceMappingURL=web.index.js.map