Spanish Anki Deck Scraping Code

scrape.js

// https://www.spanish.academy/blog/1000-most-common-spanish-words-for-beginners/

function scrape() {
  const words = [];
  const parent = document.querySelectorAll(".blog_content")[0];

  let currentSection = [null, null];
  let currentSubsection = [null, null];
  for (const child of parent.children) {
    switch (child.tagName.toLowerCase()) {
      case "h2": {
        const { innerText } = child;
        currentSection = [
          innerText.trim(),
          innerText.toLowerCase().replace(/ /g, "_"),
        ];
        currentSubsection = [null, null];
        break;
      }
      case "h3": {
        const { innerText } = child;
        currentSubsection = [
          innerText.trim(),
          innerText.toLowerCase().replace(/ /g, "_"),
        ];
        break;
      }
      case "ul": {
        if (currentSection[1].includes("ready_to")) {
          continue;
        }

        for (const item of child.children) {
          let [word, definition] = item.innerText
            .replace(/[—–]/g, "#")
            .split("#");

          words.push(
            [
              word.trim(),
              definition.trim(),
              [currentSection[0], currentSubsection[0]]
                .filter(Boolean)
                .join(" - "),
              [currentSection[1], currentSubsection[1]]
                .filter(Boolean)
                .join(" "),
            ].join(";")
          );
        }
        break;
      }
      default:
        break;
    }
  }

  console.log(words.join("\n"));
}

scrape();