Retrieving main document image #52

tommedema · 2015-06-29T13:32:04Z

Libraries like boilerpipe allow one to extract an article's main image. Is it possible to achieve this with node-readability?

kashifeqbal · 2016-01-15T14:45:57Z

Node-Unfluff is best to get the Article main Image.

var read = require('node-readability');

var extractor = require('unfluff');

read('http://www.ainonline.com/aviation-news/aerospace/2016-01-14/boeing-and-unions-reconciled-sides-reach-tentative-deal', function (err, article, meta) {
  // Main Article 
  console.log(article.content);
  console.log("--------------------------------------------------");
  // Title 
  console.log(article.title);
  console.log("--------------------------------------------------");

  // HTML Source Code 
  console.log(article.html);
  console.log("--------------------------------------------------");

  // Response Object from Request Lib 
  console.log(meta);
  console.log("--------------------------------------------------");

  // Extract article main image
  var data = extractor(article.html);
  console.log(data.image);
  console.log("--------------------------------------------------");

  // Close article to clean up jsdom and prevent leaks 
  article.close();
});

458muda · 2016-10-06T10:20:54Z

I am using the following code to grab the main image of the article.
helpers.js

Grabbing main image of the article

var grabImage = module.exports.grabImage = function(document) {
    var images = document.getElementsByTagName('IMG');
    var MINIMUM_SURFACE =  100*100;
     if (images.length > 0) { 
    for (var i = 0; i < images.length; ++i) {
      var image = images[i];
       if ( image.getAttribute('data-src') ) {
                    image.getAttribute('src') = image.getAttribute('data-src');
                }
                if ( image.getAttribute('data-lazy-src') ) {
                    image.getAttribute('src') = image.getAttribute('data-lazy-src');
                }
                 if ( !image.getAttribute('src') ) {
                    continue;
                }

                // //Compute surface
                // var w = image.getAttribute('width') || 1;
                // var h = image.getAttribute('height') || 1;
                // image.surface = w * h;



                // //Filter by size
                // if ( image.surface > MINIMUM_SURFACE ) {
                 var mainImageSrc = image.getAttribute('src');

                     //Resolve relative url
                     if (!mainImageSrc.match(/^http/)) {
                                     if (!image.ownerDocument.originalURL) {

                                          } else{
                          mainImageSrc = url.resolve(image.ownerDocument.originalURL, mainImageSrc);
                        }
                      }
                      image.parentNode.removeChild(image);
                    break;
              //  }

       }
      }
      return mainImageSrc; 
};

and readability.js

var mainImgUrl = helpers.grabImage(this._document);
  var img = this._document.createElement("IMG");
   img.setAttribute('src',  mainImageUrl); 
   articleContent.insertBefore(img, articleContent.childNodes[0] );

I am adding this above part of code in this function
Readability.prototype.getContent = function(notDeprecated) {
But, it' not working. The whole content is being grabbed ,but I'm getting this error

> Cleaning Conditionally [object HTMLDivElement] (image width-494:)
Cleaning Conditionally [object HTMLDivElement] (:)
fixed link
C:\Users\SAI\reader-rest\routes\api.js:19
                var content = '<html><head><meta charset="utf-8"><title>'+articl
e.title+'</title></head><body>' +article.content+'</body></html>';

 ^

TypeError: Cannot read property 'title' of undefined
    at C:\Users\SAI\reader-rest\routes\api.js:19:78
    at Object.jsdom.env.done (C:\Users\SAI\reader-rest\node_modules\node-readabi
lity\src\readability.js:292:18)
    at C:\Users\SAI\reader-rest\node_modules\node-readability\node_modules\jsdom
\lib\jsdom.js:259:18
    at nextTickCallbackWith0Args (node.js:420:9)
    at process._tickCallback (node.js:349:13)
typeerror: Cannot read property 'title' of undefined    at C:\Users\SAI\reader-rest\routes\api.js:19:78    at Object.jsdom.env.done (C:\Users\SAI\reader-rest\node_modules\node-readability\src\readability.js:292:18)    at C:\Users\SAI\reader-rest\node_modules\node-readability\node_modules\jsdom\lib\jsdom.js:259:18    at nextTickCallbackWith0Args (node.js:420:9)    at process._tickCallback (node.js:349:13)

Any Help

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Retrieving main document image #52

Retrieving main document image #52

tommedema commented Jun 29, 2015

kashifeqbal commented Jan 15, 2016

458muda commented Oct 6, 2016 •

edited

Loading

Retrieving main document image #52

Retrieving main document image #52

Comments

tommedema commented Jun 29, 2015

kashifeqbal commented Jan 15, 2016

458muda commented Oct 6, 2016 • edited Loading

458muda commented Oct 6, 2016 •

edited

Loading