Use boilerpipe-based dom-distiller-js

components/dom_distiller/core/javascript/domdistiller.js

+// Copyright 2014 The Chromium Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
+
+<include src="../../../../third_party/dom_distiller_js/js/domdistiller.js"/>

[nyquist, 2014/02/26 00:30:15]

To be honest, I didn't know
RenderViewHost::ExecuteJavascriptInWebFrameCallbackResult supported HTML as
well...

[nyquist, 2014/02/26 00:53:16]

In fact, since this is GRIT, could we maybe add a short comment in these two
files for new readers? Since the file extension is .js it's a little bit
confusing.

[cjhopman, 2014/02/27 02:43:09]

Done.

+<include src="../../../../third_party/readability/js/readability.js"/>
+
+// Extracts long-form content from a page and returns and array where the first
+// element is the article title, the second element is HTML containing the
+// long-form content, and remaining elements are URLs for images referenced by
+// that HTML. Each <img> tag in the HTML has an id field set to k - 2, which
+// corresponds to a URL listed at index k in the array returned.
+(function() {
+  readability.init();

[Yaron, 2014/02/26 02:50:50]

Add TODO: remove dependency on readability.

[cjhopman, 2014/02/27 02:43:09]

Done.

+  var result = new Array(4);
+  result[0] = readability.getArticleTitle();
+  result[1] = com.dom_distiller.ContentExtractor.extractContent()
+  result[2] = readability.getNextPageLink();
+  // TODO(shashishekhar): Add actual previous page link here.
+  result[3] = '';
+  return result.concat(readability.getImages());
+})()