![\"FacebookDataDownload2\"](\"http:\/\/www.nikola-breznjak.com\/blog\/wp-content\/uploads\/2014\/12\/FacebookDataDownload2.jpg\")
<\/a><\/p>\nHere you can just click on the Download a copy of your Facebook data and after they process your request you will get the download link on your email.<\/p>\n
The download package looks\u00a0contains 3 folders (videos, photos, html) and a index.html file. In order to take a look at your posts you have to open up the html folder where you’ll find the file named wall.htm<\/strong>. This is a simple HTML file whose contents\u00a0is put inside the\u00a0<div class=”comment”>\u00a0<\/strong>elements.<\/p>\n In order to parse this with JavaScript (you’ll need to have Node.js installed) you can use the following snippet:<\/p>\n What this does is that it reads the wall.html file and outputs just simple text of the posts in a parsed.txt file.<\/p>\n Few of the challenges here we’re the multiline regex matching which I solved with this link<\/a> on StackOverflow, and another one was getting access to\u00a0matched groups<\/a> of a regex in JavaScript.<\/p>\n","protected":false},"excerpt":{"rendered":" So, first you need to download all the data that Facebook has stored for you (well, and what it’s willing to give you :)). You can do that…<\/p>\n","protected":false},"author":1,"featured_media":948,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-944","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-nodejs"],"_links":{"self":[{"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/posts\/944","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/comments?post=944"}],"version-history":[{"count":2,"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/posts\/944\/revisions"}],"predecessor-version":[{"id":949,"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/posts\/944\/revisions\/949"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/media\/948"}],"wp:attachment":[{"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/media?parent=944"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/categories?post=944"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nikola-breznjak.com\/blog\/wp-json\/wp\/v2\/tags?post=944"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}function getMatches(string, regex, index) {\r\n index || (index = 1); \/\/ default to the first capturing group\r\n var matches = [];\r\n var match;\r\n while (match = regex.exec(string)) {\r\n matches.push(match[index]);\r\n }\r\n return matches;\r\n}\r\n\r\nfs = require('fs');\r\nfs.readFile('wall.htm', 'utf8', function(err, data){\r\n\tif (err){\r\n\t return console.log(err);\r\n\t}\r\n\r\n\tvar regex = \/comment\">([\\s\\S]*?)<\\\/div>\/g\r\n\tvar matches = getMatches(data, regex, 1);\r\n\r\n\tvar output = '';\r\n\tfor(var i=0; i<matches.length; i++){\r\n\t\toutput += matches[i] + '\\n';\r\n\t}\r\n\r\n\tfs.writeFile('parsed.txt', output, 'utf8', function(){\r\n\t\tconsole.log('done!');\r\n\t});\r\n});<\/pre>\n