Created
May 3, 2012 23:52
-
-
Save ozten/2590522 to your computer and use it in GitHub Desktop.
A script to parse useragentstring.com HTML into test JSON
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| var fs = require('fs'); | |
| // Parses HTML from http://www.useragentstring.com/pages/All/ | |
| /* Build a json object like: | |
| { | |
| tests: [ | |
| { | |
| comment: "Internet Explorer" | |
| }, | |
| { | |
| ua: "Mozilla/5.0 (Windows; U; MSIE 9.0; WIndows NT 9.0; en-US))", | |
| os: "Windows NT", | |
| browser: "Internet Explorer", | |
| version: "9" | |
| } | |
| ] | |
| } | |
| */ | |
| var d = { | |
| tests: [] | |
| }, | |
| last_browser = 'Unknown'; | |
| function parse(data) { | |
| for (var i=0; i < data.length; i++) { | |
| switch (data[i]) { | |
| case '<': | |
| // h3 Browser Name | |
| if (i + 2 < data.length && | |
| data[i + 1] === 'h' && | |
| data[i + 2] === '3') { | |
| i = parse_h3(data, i + 3); | |
| // a is user agent string | |
| } else if (i + 1 < data.length && | |
| data[i + 1] === 'a' && | |
| (data[i + 2] === ' ' || data[i + 2] === '>')) { | |
| i = parse_a(data, i + 1); | |
| } | |
| break; | |
| default: | |
| // no op | |
| break; | |
| } | |
| } | |
| }; | |
| function parse_h3 (data, i) { | |
| var new_i = data.length; | |
| var end = data.indexOf('</h3>', i); | |
| if (end === -1) { | |
| console.log("WARN no </h3> found. Stopping."); | |
| } else { | |
| // Sometimes there is an image tag... | |
| if (data[i + 1] === '<' && | |
| data.indexOf('/>', i + 1) !== -1 && | |
| data.indexOf('/>', i + 1) < end) { | |
| i = data.indexOf('/>', i + 1) + 1; | |
| } | |
| var browser = last_browser = data.substring(i + 1, end); | |
| d.tests.push({comment: browser}); | |
| new_i = end; | |
| } | |
| return new_i; | |
| } | |
| function parse_a (data, i) { | |
| var new_i = data.length; | |
| var end = data.indexOf('</a>', i); | |
| if (end === -1 ) { | |
| console.log("WARN no </a> found. Stopping."); | |
| } else { | |
| new_i = end; | |
| var start = data.indexOf('>', i); | |
| if (start !== -1) { | |
| d.tests.push({ | |
| ua: data.substring(start + 1, end), | |
| os: "", | |
| browser: last_browser, | |
| version: "" | |
| }); | |
| } | |
| } | |
| return new_i; | |
| } | |
| fs.readFile('t_user_agents.html', 'utf-8', function (err, data) { | |
| if (err) throw err; | |
| parse(data); | |
| fs.writeFile('f_user_agents.json', JSON.stringify(d, null, 2), 'utf8'); | |
| }); | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment