scrape-meta/dist/rules/image.js

A library to easily scrape metadata from an article on the web using Open Graph metadata, regular HTML metadata, and series of fallbacks.

'use strict';

var isUrl = require('is-url');
var utils = require('../utils'

/**
 * Wrap a rule with validation and formatting logic.
 *
 * @param {Function} rule
 * @return {Function} wrapped
 */

);function wrap(rule) {
  return function ($, sourceUrl) {
    var value = rule($);
    if (isUrl(value)) {
      return value;
    } else if (typeof value === 'string' && sourceUrl) {
      return utils.resolveImagePath(sourceUrl, value);
    }
    return;
  };
}

/**
 * Rules.
 */

module.exports = [wrap(function ($) {
  return $('meta[property="og:image:secure_url"]').attr('content');
}), wrap(function ($) {
  return $('meta[property="og:image:url"]').attr('content');
}), wrap(function ($) {
  return $('meta[property="og:image"]').attr('content');
}), wrap(function ($) {
  return $('meta[name="twitter:image"]').attr('content');
}), wrap(function ($) {
  return $('meta[property="twitter:image"]').attr('content');
}), wrap(function ($) {
  return $('meta[name="twitter:image:src"]').attr('content');
}), wrap(function ($) {
  return $('meta[property="twitter:image:src"]').attr('content');
}), wrap(function ($) {
  return $('meta[name="sailthru.image"]').attr('content');
}), wrap(function ($) {
  return $('meta[name="sailthru.image.full"]').attr('content');
}), wrap(function ($) {
  return $('meta[name="sailthru.image.thumb"]').attr('content');
}), wrap(function ($) {
  return $('article img[src]').first().attr('src');
}), wrap(function ($) {
  return $('#content img[src]').first().attr('src');
}), wrap(function ($) {
  return $('[class*="article"] img[src]').first().attr('src');
}), wrap(function ($) {
  return $('img[src]').first().attr('src');
})];