Created
May 23, 2013 08:28
-
-
Save fizerkhan/5633503 to your computer and use it in GitHub Desktop.
Extract largest image thumbnail from url using node and cheerio
This file contains 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 cheerio = require('cheerio') | |
, Shred = require('shred') | |
, shred = new Shred() | |
, http = require('http') | |
, URL = require('url'); | |
var server = http.createServer(function(request, response) { | |
var url, urlToDiscover; | |
url = URL.parse(request.url, true); | |
urlToDiscover = url.query['url']; | |
return startDiscovery(urlToDiscover, function(theImageURL) { | |
if (theImageURL != null) { | |
response.writeHead(200, { | |
"Content-Type": 'application/json' | |
}); | |
return response.end(JSON.stringify(theImageURL)); | |
} else { | |
console.log("Did not find image for " + urlToDiscover); | |
response.writeHead(404, "Cant find theImage"); | |
return response.end(); | |
} | |
}); | |
}); | |
server.listen(process.env.PORT || 5000, '0.0.0.0'); | |
var startDiscovery = function(url, cb) { | |
return shred.get({ | |
url: url, | |
on: { | |
redirect: function(response) { | |
return discoverImage(response.request.url, null, cb); | |
}, | |
200: function(response) { | |
return discoverImage(response.request.url, response.content.data, cb); | |
} | |
} | |
}); | |
}; | |
var discoverImage = function(url, data, cb) { | |
var discoveredURL; | |
discoveredURL = discoverImageFromURL(url); | |
if (data) { | |
discoveredURL || (discoveredURL = discoverImageFromData(url, data)); | |
} | |
discoveredURL = cleanURL(url, discoveredURL); | |
return cb(discoveredURL); | |
}; | |
var cleanURL = function(baseURL, discoveredURL) { | |
if (!discoveredURL) { | |
return null; | |
} | |
if (discoveredURL.indexOf("/") === 0) { | |
return "" + baseURL + discoveredURL; | |
} | |
return discoveredURL; | |
}; | |
var discoverImageFromURL = function(url) { | |
console.log(url.indexOf('yfrog')); | |
if (url.indexOf('yfrog') !== -1) { | |
return url + ":medium"; | |
} | |
}; | |
var discoverImageFromData = function(url, data) { | |
var $, currDimension, image, images, maxDimension, maxImage, _i, _len; | |
$ = cheerio.load(data); | |
images = $('img'); | |
maxImage = null; | |
maxDimension = 0; | |
for (_i = 0, _len = images.length; _i < _len; _i++) { | |
image = images[_i]; | |
currDimension = $(image).attr('width') * $(image).attr('height'); | |
if (currDimension > maxDimension) { | |
maxDimension = currDimension; | |
maxImage = image; | |
} | |
} | |
return $(maxImage).attr('src'); | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment