Created
December 16, 2015 22:32
-
-
Save tmocellin/89a1d2fcf91e83c1412b to your computer and use it in GitHub Desktop.
Simple test scraping whith nokogiri
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 'open-uri' | |
require 'nokogiri' | |
def getPageResult (html_data) | |
$data_array = [] | |
list_ads = html_data.css('.list-lbc a') | |
list_ads.each { |add| | |
url = add['href'] | |
title = add.css('.detail .title').text.gsub(/\s+/,' ') | |
price = add.css('.detail .price').text.gsub(/\s+/,'').gsub(/\u00a0/,'').gsub(/\u20AC/," euros") | |
data = {price:price , title:title , url:url} | |
$data_array.push(data) | |
} | |
$data_array | |
end | |
$pageResults = [] | |
$pages = [] | |
searchUrl = "http://www.leboncoin.fr/annonces/offres/rhone_alpes/occasions/?o=1&q=guitar" | |
stream = open(searchUrl) | |
html = stream.read | |
html_data = Nokogiri::HTML(html) | |
$pageResults.concat(getPageResult(html_data)) | |
pages_list = html_data.css('#paging a') | |
pages_list.each{ |page_link| | |
if page_link.text != "Page suivante" && page_link.text != ">>" | |
puts "page #{page_link.text}" | |
stream = open(page_link['href']) | |
html = stream.read | |
html_data = Nokogiri::HTML(html) | |
$pageResults.concat(getPageResult(html_data)) | |
pages_list = html_data.css('#paging a') | |
sleep(2.5) | |
end | |
} | |
puts $pageResults |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment