Created
June 15, 2014 18:06
-
-
Save unRob/14b3b69042336cb0222a to your computer and use it in GitHub Desktop.
Cool no sabe hacer crawlers de la RAE
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
zoquete | |
sagaz | |
inconsistente |
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
#!/usr/bin/env ruby | |
# encoding: utf-8 | |
# usage: ./lemas_rae path/to/word.list | |
require 'typhoeus' | |
require 'nokogiri' | |
file = ARGV[0] | |
begin | |
lista = File.read(file).split("\n") | |
rescue Exception => e | |
$stderr << "necesito un archivo con palabras para procesar\r\n" | |
$stderr << e | |
exit 1; | |
end | |
def url_para_lema (l) "http://buscon.rae.es/drae/srv/search?type=3&val=#{l}&val_aux=&origen=REDRAE" end | |
def parse_lema body | |
dom = Nokogiri::HTML(body) | |
defs = [] | |
dom.css('.b').each do |d| | |
defs << d.text.strip | |
end | |
defs.join('|') | |
end | |
$hydra = Typhoeus::Hydra.new(max_concurrency: 100) | |
$h = {'Content-Type'=>'application/x-www-form-urlencoded'} | |
$body = { | |
'TS014dfc77_id' => 3, | |
'TS014dfc77_cr' => 'cf5aba3b3fbec6a7c3dac7226fb1159e:zvwz:cTr5TNpP:1926928421', | |
'TS014dfc77_76' => 0, | |
'TS014dfc77_md' => 1, | |
'TS014dfc77_rf' => 0, | |
'TS014dfc77_ct' => 0, | |
'TS014dfc77_pd' => 0 | |
}.map {|k,v| | |
"#{k}=#{v}" | |
}.join('&') | |
lista.each do |lema| | |
url = url_para_lema(lema) | |
req = Typhoeus::Request.new( url, method: 'post', body: $body, timeout: 60, headers: $h) | |
req.on_complete do |res| | |
if res.success? | |
$stdout << "#{lema}: "+parse_lema(res.body) | |
$stdout << "\r\n" | |
else | |
$stderr << "ERROR: #{res.code}\n" | |
end | |
end | |
$hydra.queue req | |
end | |
$hydra.run |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment