v1.0.0

.gitignore

@@ -1,3 +1,4 @@
 # https://git-scm.com/docs/gitignore
 # https://help.github.com/articles/ignoring-files
-# Example .gitignore files: https://github.com/github/gitignore
+# Example .gitignore files: https://github.com/github/gitignore
+/node_modules/

README.md

@@ -0,0 +1,66 @@
+# hma-proxy-parse
+
+Good game, HideMyAss, but I win :)
+
+This module extracts (parses) proxy details including the IP address from [http://proxylist.hidemyass.com/](http://proxylist.hidemyass.com/) and anything else using the same system, despite their (rather heavy) CSS-based obfuscation.
+
+Note that this module only does the parsing; you're responsible for fetching the source HTML yourself.
+
+## License
+
+[WTFPL](http://www.wtfpl.net/txt/copying/) or [CC0](https://creativecommons.org/publicdomain/zero/1.0/), whichever you prefer. A donation and/or attribution are appreciated, but not required.
+
+## Donate
+
+My income consists entirely of donations for my projects. If this module is useful to you, consider [making a donation](http://cryto.net/~joepie91/donate.html)!
+
+You can donate using Bitcoin, PayPal, Gratipay, Flattr, cash-in-mail, SEPA transfers, and pretty much anything else.
+
+Bitcoins can also be sent to `1KafMHn6YEDFkUSoHK6pKkqqmfJUF5Wd1C` directly :)
+
+## Contributing
+
+Pull requests welcome. Please make sure your modifications are in line with the overall code style, and ensure that you're editing the `.coffee` files, not the `.js` files.
+
+Build tool of choice is `gulp`; simply run `gulp` while developing, and it will watch for changes.
+
+Be aware that by making a pull request, you agree to release your modifications under the licenses stated above.
+
+## Usage
+
+You can input HTML from any source, but this example uses [`bhttp`](https://www.npmjs.com/package/bhttp) in Promises mode.
+
+```javascript
+var hmaProxyParse = require("hma-proxy-parse");
+var bhttp = require("bhttp");
+var Promise = require("bluebird");
+
+Promise.try(function(){
+	return bhttp.get("http://proxylist.hidemyass.com/");
+}).then(function(response){
+	console.log(hmaProxyParse(response.body.toString()));
+});
+```
+
+## API
+
+### hmaProxyParse(html)
+
+Parses the specified `html`, and returns an array of objects with proxy information. The objects look something like this:
+
+```javascript
+{
+	updateTimestamp: '1422645602',
+	ip: '187.108.223.204',
+	port: '8080',
+	country: 'br',
+	speed: '2441',
+	connectionTime: '235',
+	protocol: 'HTTP',
+	anonymity: 'Low'
+}
+```
+
+It doesn't attempt to parse the actual data provided - all data is directly as specified in the list, and you'll have to figure out what to do with it. I have no idea, for example, what the bounds on `speed` or `connectionTime` are, or what the possible options for `anonymity` are.
+
+If this helped you, don't forget to donate ;)

gulpfile.js

@@ -0,0 +1,28 @@
+var gulp = require('gulp');
+
+/* CoffeeScript compile deps */
+var path = require('path');
+var gutil = require('gulp-util');
+var concat = require('gulp-concat');
+var rename = require('gulp-rename');
+var coffee = require('gulp-coffee');
+var cache = require('gulp-cached');
+var remember = require('gulp-remember');
+var plumber = require('gulp-plumber');
+
+var source = ["lib/**/*.coffee", "index.coffee"]
+
+gulp.task('coffee', function() {
+	return gulp.src(source, {base: "."})
+		.pipe(plumber())
+		.pipe(cache("coffee"))
+		.pipe(coffee({bare: true}).on('error', gutil.log)).on('data', gutil.log)
+		.pipe(remember("coffee"))
+		.pipe(gulp.dest("."));
+});
+
+gulp.task('watch', function () {
+	gulp.watch(source, ['coffee']);
+});
+
+gulp.task('default', ['coffee', 'watch']);

index.coffee

@@ -0,0 +1 @@
+module.exports = require "./lib/hma-proxy-parse"

index.js

@@ -0,0 +1 @@
+module.exports = require("./lib/hma-proxy-parse");

lib/hma-proxy-parse.coffee

@@ -0,0 +1,67 @@
+cheerio = require "cheerio"
+
+module.exports = (html) ->
+	junkRegex = /\.([a-zA-Z0-9_-]+){display:none}/g
+
+	junk = []
+	proxies = []
+
+	match = true # Kickstarting the loop...
+	while match
+		match = junkRegex.exec html
+		if match
+			junk.push match[1]
+
+	$ = cheerio.load html
+
+	rows = $("tbody > tr")
+
+	rows.each ->
+		element = $(this)
+		timestamp = element.children(".timestamp").attr("rel")
+		port = element.children("td:nth-of-type(3)").text().replace("\n", "")
+		country = element.find("td .country").parent().attr("rel")
+		speed = element.find("td .progress-indicator").eq(0).attr("value")
+		connectionTime = element.find("td .progress-indicator").eq(1).attr("value")
+		protocol = element.children("td:nth-of-type(7)").text()
+		anonymity = element.children("td:nth-of-type(8)").text()
+
+		ipSegments = []
+
+		ipBlock = element.find("td:nth-of-type(2) > span")
+
+		ipBlock.contents().each ->
+			ipElement = $(this)
+
+			if this.tagName == null
+				if ipElement.text().trim() not in [".", ""]
+					ipSegments.push ipElement.text().trim().replace(".", "")
+			else if this.tagName in ["div", "span"]
+				isJunk = false
+
+				classNames = ipElement.attr("class")?.split(" ")
+
+				if classNames?
+					for className in classNames
+						if className in junk
+							isJunk = true
+						else
+
+				if ipElement.attr("style")?
+					if ipElement.css("display") == "none"
+						isJunk = true
+
+				if not isJunk and ipElement.text().trim() not in [".", ""]
+					ipSegments.push ipElement.text().trim().replace(".", "")
+
+		proxies.push
+			updateTimestamp: timestamp
+			ip: ipSegments.join(".")
+			port: port
+			country: country
+			speed: speed
+			connectionTime: connectionTime
+			protocol: protocol
+			anonymity: anonymity
+
+	return proxies

lib/hma-proxy-parse.js

@@ -0,0 +1,74 @@
+var cheerio,
+  __indexOf = [].indexOf || function(item) { for (var i = 0, l = this.length; i < l; i++) { if (i in this && this[i] === item) return i; } return -1; };
+
+cheerio = require("cheerio");
+
+module.exports = function(html) {
+  var $, junk, junkRegex, match, proxies, rows;
+  junkRegex = /\.([a-zA-Z0-9_-]+){display:none}/g;
+  junk = [];
+  proxies = [];
+  match = true;
+  while (match) {
+    match = junkRegex.exec(html);
+    if (match) {
+      junk.push(match[1]);
+    }
+  }
+  $ = cheerio.load(html);
+  rows = $("tbody > tr");
+  rows.each(function() {
+    var anonymity, connectionTime, country, element, ipBlock, ipSegments, port, protocol, speed, timestamp;
+    element = $(this);
+    timestamp = element.children(".timestamp").attr("rel");
+    port = element.children("td:nth-of-type(3)").text().replace("\n", "");
+    country = element.find("td .country").parent().attr("rel");
+    speed = element.find("td .progress-indicator").eq(0).attr("value");
+    connectionTime = element.find("td .progress-indicator").eq(1).attr("value");
+    protocol = element.children("td:nth-of-type(7)").text();
+    anonymity = element.children("td:nth-of-type(8)").text();
+    ipSegments = [];
+    ipBlock = element.find("td:nth-of-type(2) > span");
+    ipBlock.contents().each(function() {
+      var className, classNames, ipElement, isJunk, _i, _len, _ref, _ref1, _ref2, _ref3;
+      ipElement = $(this);
+      if (this.tagName === null) {
+        if ((_ref = ipElement.text().trim()) !== "." && _ref !== "") {
+          return ipSegments.push(ipElement.text().trim().replace(".", ""));
+        }
+      } else if ((_ref1 = this.tagName) === "div" || _ref1 === "span") {
+        isJunk = false;
+        classNames = (_ref2 = ipElement.attr("class")) != null ? _ref2.split(" ") : void 0;
+        if (classNames != null) {
+          for (_i = 0, _len = classNames.length; _i < _len; _i++) {
+            className = classNames[_i];
+            if (__indexOf.call(junk, className) >= 0) {
+              isJunk = true;
+            } else {
+
+            }
+          }
+        }
+        if (ipElement.attr("style") != null) {
+          if (ipElement.css("display") === "none") {
+            isJunk = true;
+          }
+        }
+        if (!isJunk && ((_ref3 = ipElement.text().trim()) !== "." && _ref3 !== "")) {
+          return ipSegments.push(ipElement.text().trim().replace(".", ""));
+        }
+      }
+    });
+    return proxies.push({
+      updateTimestamp: timestamp,
+      ip: ipSegments.join("."),
+      port: port,
+      country: country,
+      speed: speed,
+      connectionTime: connectionTime,
+      protocol: protocol,
+      anonymity: anonymity
+    });
+  });
+  return proxies;
+};

package.json

@@ -0,0 +1,37 @@
+{
+  "name": "hma-proxy-parse",
+  "version": "1.0.0",
+  "description": "Parses proxies out of HideMyAss' public proxy list.",
+  "main": "index.js",
+  "scripts": {
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git://github.com/joepie91/hma-proxy-parse"
+  },
+  "keywords": [
+    "hidemyass",
+    "proxy",
+    "parser"
+  ],
+  "author": "Sven Slootweg",
+  "license": "WTFPL",
+  "dependencies": {
+    "cheerio": "^0.18.0"
+  },
+  "devDependencies": {
+    "bhttp": "^1.0.2",
+    "bluebird": "^2.9.4",
+    "gulp": "~3.8.0",
+    "gulp-cached": "~0.0.3",
+    "gulp-coffee": "~2.0.1",
+    "gulp-concat": "~2.2.0",
+    "gulp-livereload": "~2.1.0",
+    "gulp-nodemon": "~1.0.4",
+    "gulp-plumber": "~0.6.3",
+    "gulp-remember": "~0.2.0",
+    "gulp-rename": "~1.2.0",
+    "gulp-util": "~2.2.17"
+  }
+}

test.coffee

@@ -0,0 +1,8 @@
+hmaProxyParse = require "./"
+bhttp = require "bhttp"
+Promise = require "bluebird"
+
+Promise.try ->
+	bhttp.get "http://proxylist.hidemyass.com/"
+.then (response) ->
+	console.log hmaProxyParse(response.body.toString())