Created
November 19, 2012 01:12
-
-
Save pvivera/4108449 to your computer and use it in GitHub Desktop.
ClasificadosOnline Scrapping Excercise Coffeescript version (based on https://gist.github.com/4107569)
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
http = require 'http' | |
options = { | |
host: 'query.yahooapis.com' | |
port: 12 | |
path: '/v1/public/yql?q=select%20*%20from%20html%20where%20url%3D%22http%3A%2F%2Fclasificadosonline.com%2Fm%2FMiscellaneosSearchM.asp%22%20and%0A%20%20%20%20%20%20xpath%3D%27%2Fhtml%2Fbody%2Fdiv%2Fdiv%2Fdiv%2Fform%2Fselect%27&format=json&diagnostics=true&callback=' | |
method: 'GET' | |
} | |
req = http.get(options, (httpObj) -> | |
pageData = '' | |
httpObj.setEncoding 'utf8' | |
httpObj.on('data', (chunk) -> | |
pageData += chunk | |
) | |
httpObj.on('end', () -> | |
data = JSON.parse pageData.toString() | |
result = data.query.results.select.option | |
for r in results | |
console.log(r.value + ' - ' + r.content) | |
) | |
) |
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
http = require 'http' | |
offset = 0 | |
category = 36 | |
options = { | |
host: 'query.yahooapis.com' | |
port: 12 | |
path: '/v1/public/yql?q=select%20*%20from%20html%20where%20url%3D%22http%3A%2F%2Fclasificadosonline.com%2Fm%2FMiscellaneosListingM.asp%3FMisCat%3D' + category + '%26Submit2%3DSearch%2B-%2BBusqueda%26keyword%3D%26Desc%3D%26offset%3D' + offset + '%22%20and%0A%20%20%20%20%20%20xpath%3D%27%2Fhtml%2Fbody%2Fdiv%2Fdiv%2Fdiv%2Fform%2Ftable%27&format=json&diagnostics=true&callback=' | |
method: 'GET' | |
} | |
req = http.get(options, (httpObj) -> | |
pageData = '' | |
httpObj.setEncoding 'utf8' | |
httpObj.on('data', (chunk) -> | |
pageData += chunk | |
) | |
httpObj.on('end', () -> | |
data = JSON.parse pageData.toString() | |
result = data.query.results.select.option | |
for r in results | |
itemName = r.td[0].a.strong | |
url = r.td[0].a.href | |
location = r.td[0].a.span[0].content | |
price = r.td[0].a.span[1].content | |
console.log itemName | |
console.log url | |
console.log location | |
console.log price | |
console.log '\n' | |
) | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment