Goodreads Scrapper

goodreads_book_scrapper_service.rb

require 'open-uri'
require 'nokogiri'
require 'byebug'

class Book
  #   {
  #      cover: "goodread.com...",
  #      title: "For Whom the Bell Tolls",
  #      author: "Ernest Hemmingway",
  #      rating: 4.56
  #    }
  def initialize(attributes = {})
    @cover = attributes[:cover]
    @title = attributes[:title]
    @author = attributes[:author]
    @rating = attributes[:rating] || 0.0
  end

  def to_s
    "#{@title} by #{@author} | #{@rating} rating"
  end
end

# Scapping with OOP
# GoodreadsBookScrapperService.new("fiction").perfor,
class GoodreadsBookScrapperService
  BASE_URL = "https://www.goodreads.com/"

  attr_reader :books

  def initialize(term)
    @url = BASE_URL + "search?query=#{term}"
    @books = []
  end

  def perform
    build_books
    self # returns the scrapper instance
  end

  private

  def build_books
    @books = rows.map { |book| build_book(book) }
  end

  def build_book(book)
    cover = book.search("td:first a").attr("href").value
      title = book.search("span[itemprop='name']").first.text
      author = book.search("span[itemprop='name']")[1].text
      rating = book.search("span.greyText")[1]&.text&.strip.to_f
      attributes = {
        cover: cover,
        title: title,
        author: author,
        rating: rating
      }
      Book.new(attributes)
  end

  def doc
    @doc ||= open(@url).read
  end

  def page
    @page ||= Nokogiri::HTML.parse(doc)
  end

  def table
    @table ||= page.search("table").first
  end

  def rows
    @rows ||= table.search("tr")
  end
end

scrapper = GoodreadsBookScrapperService.new("fiction").perform
books = scrapper.books

books.each_with_index do |book, index|
  puts "#{index + 1}) #{book.to_s}"
end

puts "Finished!"

scrapper.rb

# Scapping

require 'open-uri'
require 'nokogiri'
require 'byebug'

BASE_URL = "https://www.goodreads.com/"
term = "fiction"
url = BASE_URL + "search?query=#{term}"

doc = open(url).read
page = Nokogiri::HTML.parse(doc)
table = page.search("table").first
rows = table.search("tr")

books = rows.map do |book|
  cover = book.search("td:first a").attr("href").value
  title = book.search("span[itemprop='name']").first.text
  author = book.search("span[itemprop='name']")[1].text
  rating = book.search("span.greyText")[1]&.text&.strip.to_f
  {
    cover: cover,
    title: title,
    author: author,
    rating: rating
  }
end

books.each_with_index do |book, index|
  puts "#{index + 1}) #{book[:title]} by #{book[:author]} | #{book[:rating]} rating"
end


puts "Finished!"