Xcraper

Based on cheerio and native fetch enable to "Xcrape" data from html content

Types

type Schema = {
  type: "text" | "number" | "array" | "object";
  attribute?: string;
  selector?: string;
  child?: { [key: string]: Schema };
  selector?: string;
  children?: Schema;
};

Usage

import { Xcraper } from "./src";

Xcraper.fetch(url, [options]).extract(schema);

url: string;
options: RequestInit;
schema: Schema;

Sample

import { Xcraper } from "./src";

Xcraper.fetch(
  "https://www.foxnews.com/entertainment/tom-cruise-ana-de-armas-fuel-romance-rumors-stepping-out-london-again"
).extract({
  type: "object",
  child: {
    title: {
      type: "text",
      selector: ".headline.speakable",
    },
    description: {
      type: "text",
      selector: ".sub-headline.speakable",
    },
    articleDate: {
      type: "text",
      selector: ".article-date time",
    },
    content: {
      type: "array",
      selector: ".article-content .article-body p",
      children: {
        type: "text",
      },
    },
    images: {
      type: "array",
      selector: ".article-content .article-body img",
      children: {
        type: "text",
        attribute: "src",
      },
    },
  },
});

// OUTPUT
// {
//   title: string;
//   description: string;
//   articleDate: string;
//   content: string[];
//   images: string[];
// }