Created
November 4, 2013 11:57
-
-
Save wppurking/7301520 to your computer and use it in GitHub Desktop.
用来抓取 Amazon DE Akkus 下的 Top 100 排名的 ASIN
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 "httparty" | |
require "csv" | |
require "nokogiri" | |
class Asin | |
attr_accessor :rank, :asin | |
def initialize(params) | |
@rank = params[:rank] | |
@asin = params[:asin] | |
end | |
def to_s | |
"#{@asin}, #{@rank}" | |
end | |
end | |
asins = [] | |
threads = [] | |
1.upto(5) do |i| | |
threads << Thread.new do | |
url = "http://www.amazon.de/gp/bestsellers/ce-de/364919031/ref=zg_bs_364919031_pg_2?pg=#{i}" | |
puts url | |
resp = HTTParty.get(url, headers: {'User-Agent' => "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.65 Safari/537.36", "Accept-Encoding" => "gzip"}) | |
doc = Nokogiri::HTML.parse(resp.body) | |
asins += doc.css('#zg_centerListWrapper .zg_itemImmersion').map do |div| | |
asin = Asin.new({rank: div.at_css('.zg_rankNumber').text, asin: div.at_css('.zg_title a')['href'].split('/dp/')[1][0...10]}) | |
end | |
end | |
end | |
threads.each(&:join) | |
CSV.open('./de_rank.csv', 'w+') do |csv| | |
asins.each do |a| | |
csv << [a.asin, a.rank] | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment