Extract Wikipedia Lists Into a Javascript Dictionary. I needed this for a text pre-processing project.

wikipedia_list_extractor.js

/*
    Test Case: https://en.wikipedia.org/wiki/List_of_English_abbreviations_made_by_shortening_words
    Creates a js dictionary from a list in wikipedia.
    modules requires! Cheerio & fs
    The result might need a little cleaning

*/

const fs = require("fs");
const cheerio = require("cheerio");

// Step 1: Read the HTML file content
fs.readFile("abbreviations.html", "utf8", (err, html) => {
	if (err) {
		console.error("Error reading file:", err);
		return;
	}

	/* Load the HTML content into Cheerio */
	const $ = cheerio.load(html);

  /* Initialize an empty object to store abbreviations */
	const abbreviations = {};

	/* Step Loop through each abbreviation <dt> and its associated definitions <dd> */
	$("dl").each((i, dl) => {
		let currentAbbreviation = "";

		$(dl)
			.children()
			.each((j, el) => {
				if ($(el).is("dt")) {
					// Get abbreviation key (text content of <dt>)
					currentAbbreviation = $(el).text().trim();
					abbreviations[currentAbbreviation] = [];
				} else if ($(el).is("dd") && currentAbbreviation) {
					// Get the meaning of abbreviation (text content of <dd>)
					const meaning = $(el)
						.text()
						.trim()
						.replace(/\[\d+\]/g, ""); // Remove references like [1] 
					abbreviations[currentAbbreviation].push(meaning);
				}
			});
	});

	/* Convert the meanings array to a string and output the final result */
	for (let abbr in abbreviations) {
		abbreviations[abbr] = abbreviations[abbr].join(" / ");
	}
	
	console.log(JSON.stringify(abbreviations, null, 2));
});