Extract first p and h1 tag content from markdown

Question

Suppose I have the following markdown content

# What is super?
Super is a keyword used to pass props to the upper classes.

Let's begin
...
..
etc..

For any blog, the title and description are really important.

For title, I would like to get the first # h1 tag and for description, I would like to get the first paragraph p tag.

I can not use browser API because the code is running on NodeJs.

In the case of the above content, the title and description should be

• title - What is super?
• description - Super is a keyword used to pass props to the upper classes.

How can I get the title and description?

Answer 1

Answer

const regex = {
  title: /^#\s+.+/,
  heading: /^#+\s+.+/,
  custom: /\$\$\s*\w+/,
  ol: /\d+\.\s+.*/,
  ul: /\*\s+.*/,
  task: /\*\s+\[.]\s+.*/,
  blockQuote: /\>.*/,
  table: /\|.*/,
  image: /\!\[.+\]\(.+\).*/,
  url: /\[.+\]\(.+\).*/,
  codeBlock: /\`{3}\w+.*/,
};

const isTitle = (str) => regex.title.test(str);
const isHeading = (str) => regex.heading.test(str);
const isCustom = (str) => regex.custom.test(str);
const isOl = (str) => regex.ol.test(str);
const isUl = (str) => regex.ul.test(str);
const isTask = (str) => regex.task.test(str);
const isBlockQuote = (str) => regex.blockQuote.test(str);
const isImage = (str) => regex.image.test(str);
const isUrl = (str) => regex.url.test(str);
const isCodeBlock = (str) => regex.codeBlock.test(str);

export function getMdTitle(md) {
  if (!md) return "";
  let tokens = md.split("\n");
  for (let i = 0; i < tokens.length; i++) {
    if (isTitle(tokens[i])) return tokens[i];
  }
  return "";
}

export function getMdDescription(md) {
  if (!md) return "";
  let tokens = md.split("\n");
  for (let i = 0; i < tokens.length; i++) {
    if (
      isHeading(tokens[i]) ||
      isCustom(tokens[i]) ||
      isOl(tokens[i]) ||
      isUl(tokens[i]) ||
      isTask(tokens[i]) ||
      isBlockQuote(tokens[i]) ||
      isImage(tokens[i]) ||
      isUrl(tokens[i]) ||
      isCodeBlock(tokens[i])
    )
      continue;

    return tokens[i];
  }
  return "";
}