Last active
January 21, 2018 22:55
-
-
Save denissellu/1ff33c2ff32f4c6a790d797f41ed8c21 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| # Install Ruby 2.1+ | |
| # gem install nokogiri | |
| require "nokogiri" | |
| require "open-uri" | |
| require "csv" | |
| CSV.open("top-posts.csv", "wb") do |csv| | |
| csv << ["Article Name", "Article Link", "Article Claps", "Trending Date"] | |
| # Date range to scrape the article for | |
| Date.new(2017, 01, 01).upto(Date.new(2018, 01, 21)) do |date| | |
| year = date.year | |
| month = date.strftime("%B").downcase | |
| day = date.strftime("%d").downcase | |
| trending_date = "#{day}-#{month}-#{year}" | |
| url = "https://medium.com/browse/top/#{month}-#{day}-#{year}" | |
| doc = Nokogiri::HTML(open(url)) | |
| puts "Scraping #{day} #{month} #{year}" | |
| puts url | |
| doc.css('div.postArticle').each do |article_title| | |
| # Incase there is no title | |
| if article_title.css('.postArticle-content a > h3').first | |
| article_name = article_title.css('.postArticle-content a > h3').first.content | |
| else | |
| article_name = "" | |
| end | |
| article_link = article_title.css('.postArticle-content a').first['href'] | |
| article_claps = article_title.css('.js-multirecommendCountButton').first.content | |
| csv << [article_name, article_link, article_claps, trending_date] | |
| end | |
| end | |
| end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment