http://railscasts.com/episodes/191-mechanize?view=asciicast http://www.railsenespanol.co/capitulos/capitulo1 http://www.railsenespanol.co/capitulos/capitulo2
Last active
November 29, 2015 02:54
-
-
Save mariochavez/d9a485e8f1502583c647 to your computer and use it in GitHub Desktop.
Ejemplo de uso de Mechanize para scrappear páginas de ASP.NET
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
require 'mechanize' | |
require 'json' | |
HIDALGO_ID = 13 | |
agent = Mechanize.new | |
agent.get('http://tablerocronicas.info/DirApp/tableros/OSicDetIntro.aspx') | |
selector = agent.page.at('#Contenedor_Master_cboEntidad') | |
state_selector = selector.attributes['name'].value | |
form = agent.page.forms[0] | |
form[state_selector] = HIDALGO_ID | |
page = form.submit | |
data = { | |
updated_at: Time.parse(page.at('#Contenedor_Master_lblFecSIC').inner_text), | |
sample: { | |
consultas: page.at('#Contenedor_Master_lblPacAten').inner_text.to_i, | |
centro: page.at('#Contenedor_Master_lblUnidadesSalud').inner_text.to_i | |
}, | |
sex_distribution: { | |
female: page.at('#Contenedor_Master_lblporcM').inner_text.to_f, | |
male: page.at('#Contenedor_Master_lblporcH').inner_text.to_f | |
}, | |
totals: { | |
diabetes: page.at('#Contenedor_Master_lblDM2Total').inner_text.sub(',', '').to_i, | |
hipertension: page.at('#Contenedor_Master_lblHTATotal').inner_text.sub(',', '').to_i, | |
obesidad: page.at('#Contenedor_Master_lblObeTotal').inner_text.sub(',', '').to_i, | |
displidemia: page.at('#Contenedor_Master_lblDlpTotal').inner_text.sub(',', '').to_i | |
}, | |
source: 'http://tablerocronicas.info/DirApp/tableros/OSicDetIntro.aspx' | |
} | |
puts JSON.generate(data) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment