Initial import.

n1k0 · n1k0 · commit 96945bb54d88 · 2015-02-22T18:04:33.000+01:00
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1 @@
+node_modules
diff --git a/README.md b/README.md
@@ -0,0 +1,38 @@
+readable-proxy
+==============
+
+Proxy server to retrieve a readable version of any provided url, powered by Node,
+[PhantomJS](http://phantom.org/) and [Readability.js](https://github.com/mozilla/readability).
+
+Installation
+------------
+
+    $ git clone https://github.com/n1k0/readable-proxy
+    $ cd readable-proxy
+    $ npm install
+
+Run
+---
+
+Starts server on `localhost:3000`:
+
+    $ npm start
+
+Note about CORS: by design, the server will allow any origin to access it, so browsers can consume it from pages hosted on a different domain.
+
+Usage
+-----
+
+    $ curl http://0.0.0.0:3000/get\?url\=https://nicolas.perriault.net/code/2013/get-your-frontend-javascript-code-covered/
+    {
+      "byline":"Nicolas Perriault —",
+      "content":"<div id=\"readability-page-1\" class=\"page\"><section class=\"\">\n<p><strong>So finally you're…",
+      "length":3851,
+      "title":"Get your Frontend JavaScript Code Covered | Code",
+      "uri":"https://nicolas.perriault.net/code/2013/get-your-frontend-javascript-code-covered/"
+    }
+
+License
+-------
+
+MPL 2.0.
diff --git a/index.js b/index.js
@@ -0,0 +1,34 @@
+var scrape = require("./scrape");
+var express = require("express");
+var pkgInfo = require("./package.json");
+
+var app = express();
+
+app.use(function(req, res, next) {
+  res.header("Content-Type", "application/json");
+  res.header("Access-Control-Allow-Origin", "*");
+  res.header("Access-Control-Allow-Headers", "Origin, Requested-With, Content-Type, Accept");
+  next();
+});
+
+app.get("/", function(req, res) {
+  res.json({name: "moz-readable", version: pkgInfo.version});
+});
+
+app.get("/get", function(req, res) {
+  var url = req.query.url;
+  if (!url) {
+    return res.status(400).json({error: "Missing url parameter"});
+  }
+  scrape(url).then(function(result) {
+    res.json(result);
+  }).catch(function(err) {
+    res.status(500).json({error: err.message});
+  });
+});
+
+var server = app.listen(3000, function() {
+  var host = server.address().address;
+  var port = server.address().port;
+  console.log("Server listening at http://%s:%s", host, port);
+});
diff --git a/package.json b/package.json
@@ -0,0 +1,22 @@
+{
+  "name": "readable-proxy",
+  "version": "0.0.1",
+  "description": "Node service attempting to fetch readable contents from any URL.",
+  "main": "index.js",
+  "scripts": {
+    "start": "node index.js",
+    "test": "echo \"Error: no test specified\" && exit 1"
+  },
+  "keywords": [
+    "readable",
+    "readability",
+    "fetch"
+  ],
+  "author": "Nicolas Perriault <nperriault@mozilla.com>",
+  "license": "MPL",
+  "dependencies": {
+    "bluebird": "^2.9.12",
+    "express": "^4.11.2",
+    "phantomjs": "^1.9.15"
+  }
+}
diff --git a/phantom-scrape.js b/phantom-scrape.js
@@ -0,0 +1,24 @@
+var system = require("system");
+var page = require("webpage").create();
+var url = system.args[1];
+
+function json(o) {
+  console.log(JSON.stringify(o, null, 2));
+}
+
+if (!url) {
+  json({error: "Missing url"});
+  phantom.exit();
+}
+
+page.open(url, function(status) {
+  if (status !== "success") {
+    json({error: "Unable to open " + url});
+    return phantom.exit();
+  }
+  page.injectJs("vendor/Readability.js");
+  json(page.evaluate(function(url) {
+    return new Readability(document.location.href, document).parse();
+  }, url));
+  phantom.exit();
+});
diff --git a/scrape.js b/scrape.js
@@ -0,0 +1,21 @@
+var childProcess = require("child_process");
+var phantomjs = require("phantomjs");
+var binPath = phantomjs.path;
+var path = require("path");
+var Promise = require("bluebird");
+
+module.exports = function scrape(url) {
+  return new Promise(function(fulfill, reject) {
+    var childArgs = [path.join(__dirname, "phantom-scrape.js"), url];
+    childProcess.execFile(binPath, childArgs, function(err, stdout, stderr) {
+      if (err) {
+        return reject(err);
+      }
+      try {
+        fulfill(JSON.parse(stdout));
+      } catch (e) {
+        reject(new Error("Unable to parse JSON proxy response."));
+      }
+    });
+  });
+};
diff --git a/vendor/Readability.js b/vendor/Readability.js
