Scrape FAQs

faq-scrape.js

var $questions = jQuery('.faq-question');
var json = {};
json.categories = [];
json.entries = [];
var categoryIndex = -1;
var sectionId = 21;
var typeId = 28;

function isFirst(string) {
  return (string.search(/^1\./g) !== -1);
}

function convertToSlug(Text) {
  return Text
    .toLowerCase()
    .replace(/ /g,'-')
    .replace(/[^\w-]+/g,'');
}

function buildCategory(category) {
  return {
    "@model": "CategoryModel",
    "attributes": {
      "groupId": 3,
      "parentId": 1,
      "locale": "en_us",
      "slug": category.slug,
      "dateCreated": "2016-01-13 01:25:57",
      "dateUpdated": "2016-01-13 01:25:57",
      "enabled": true
    },
    "content": {
      "title": category.title,
      "fields": []
    }
  }
}

function buildEntry(question, answer, category) {
  return {
    "@model": "EntryModel",
    "attributes": {
      "sectionId": sectionId,
      "typeId": typeId,
      "authorId": 1,
      "locale": "en_us",
      "slug": convertToSlug(question),
      "postDate": "2015-02-27 16:43:52",
      "expiryDate": null,
      "dateCreated": "2015-02-27 16:43:52",
      "dateUpdated": "2015-02-27 16:51:42",
      "enabled": true
    },
    "content": {
      "title": question,
      "fields": {
        "body": answer,
      },
      "related": {
        "category": {
          "@model": "CategoryModel",
          "matchBy": "slug",
          "matchValue": [category],
          "matchCriteria": {
            "groupId": 3
          }
        }
      }
    }
  }
}

var $categories = jQuery('.faq-header');
var categories = [];
$categories.each(function(item) {
  var title = jQuery(this).text();
  json.categories.push(buildCategory({
    title: title,
    slug: convertToSlug(title)
  }));
});

$questions.each(function(item) {
  var category = json.categories[categoryIndex];
  var answerId = jQuery(this).parent().parent().attr('id');
  var $answer = jQuery('[aria-labelledby=' + answerId + ']');
  var answerBody = $answer.html();
  var question = jQuery(this).text();

  if (isFirst(question)) {
    categoryIndex++;
    category = json.categories[categoryIndex];
  }

  json.entries.push(buildEntry( 
    question.replace(/^\d+\.\s*/, ''), 
    answerBody,
    category.attributes.slug
  ));
});

// These numbers should be the same (make sure we got everything)
console.log('questions length: ', $questions.length);
console.log('faq length: ', json.entries.length);


// copy(json.categories); // copy just the categories
// copy(json.entries); // copy just the entries

copy(json); // Copy everything

Just paste this directly into the Chrome console to use.