Created
June 29, 2018 06:00
-
-
Save kitz99/06cd208749896f368a7dbaceb3c6e781 to your computer and use it in GitHub Desktop.
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 'nokogiri' | |
require 'open-uri' | |
require 'json' | |
URL = "https://kernel-panic.me/scraping.html" | |
def main() | |
document = Nokogiri::HTML(open(URL)) | |
results = [] | |
products = document.xpath("//ul[@class='products']/li") | |
products.each do |p| | |
json_product = {} | |
json_product[:title] = p.xpath("div/div[@class='product-header']").text.strip | |
json_product[:description] = p.xpath("div/div[@class='product-body']/p[contains(@class, 'description')]").text.strip | |
json_product[:price] = p.xpath("div/div[@class='product-footer']/p[contains(@class, 'price')]").text.strip | |
results << json_product | |
end | |
puts results.to_json | |
end | |
main() | |
# output: | |
[ | |
{ | |
"description": "Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed ut quam lectus. Sed ultrices, est nec varius vestibulum, orci\n mi placerat nisi, et accumsan dui nibh tincidunt ex.", | |
"price": "50.50 EUR", | |
"title": "Product title 1" | |
}, | |
{ | |
"description": "Proin efficitur libero mi, ut facilisis orci faucibus vel. Mauris sit amet velit semper, laoreet neque a, laoreet nibh.", | |
"price": "38.50 EUR", | |
"title": "Product title 2" | |
}, | |
{ | |
"description": "Proin efficitur libero mi, ut facilisis orci faucibus vel. Mauris sit amet velit semper, laoreet neque a, laoreet\n nibh.", | |
"price": "66.25 EUR", | |
"title": "Product title 3" | |
}, | |
{ | |
"description": "Proin efficitur libero mi, ut facilisis orci faucibus vel. Mauris sit amet velit semper, laoreet neque a, laoreet\n nibh.", | |
"price": "18.25 EUR", | |
"title": "Product title 3" | |
}, | |
{ | |
"description": "Proin efficitur libero mi, ut facilisis orci faucibus vel. Mauris sit amet velit semper, laoreet neque a, laoreet\n nibh.", | |
"price": "21.66 EUR", | |
"title": "Product title 3" | |
}, | |
{ | |
"description": "Proin efficitur libero mi, ut facilisis orci faucibus vel. Mauris sit amet velit semper, laoreet neque a, laoreet\n nibh.", | |
"price": "19.75 EUR", | |
"title": "Product title 3" | |
}, | |
{ | |
"description": "Proin efficitur libero mi, ut facilisis orci faucibus vel. Mauris sit amet velit semper, laoreet neque a, laoreet\n nibh.", | |
"price": "11.5 EUR", | |
"title": "Product title 3" | |
} | |
] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment