Created
February 19, 2016 17:32
-
-
Save Cshion/88bfb257f1b851862dff to your computer and use it in GitHub Desktop.
Basic DRAE scrapper , need refactor to manage redirections.
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 request = require( "request" ); | |
var cheerio = require( "cheerio" ); | |
var async = require( "async" ); | |
var getHtml = function( word , callback ) { | |
var BASE_URL = "http://dle.rae.es/srv/search"; | |
request( { | |
uri : BASE_URL , | |
qs : { | |
w : word , | |
m : 30 | |
} | |
} , function( err , response , html ) { | |
if( err ) { | |
return callback( err ); | |
} else { | |
return callback( null , html ); | |
} | |
} ) | |
}; | |
var crawlHtml = async.asyncify( function( html ) { | |
var $ = cheerio.load( html ); | |
var resultados = $( "p" ); | |
var results = []; | |
var pattern = /^j.*/; | |
resultados.each( function( i , e ) { | |
var element = $( this ); | |
var c = element.attr( "class" ) | |
if( pattern.test( c ) ) { | |
var s = ""; | |
element.children().each( function( ix , ex ) { | |
s += " " + $( this ).text(); | |
} ); | |
results.push( s ); | |
} | |
} ); | |
return results; | |
} ); | |
function getWordReference( word , callback ) { | |
async.waterfall( [ | |
async.constant( word ) , | |
getHtml , | |
crawlHtml | |
] , function( err , result ) { | |
if( err ) { | |
return callback( err ); | |
} | |
return callback( null , result ); | |
} ) | |
} | |
getWordReference( "cama" , function( err , result ) { | |
if( err ) { | |
console.log( err ); | |
} else { | |
console.log( result ); | |
} | |
} ) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment