Scrapping de https://www.freeletics.com

commandes.md

installation de la gem 'watir'

gem install watir

téléchargement du driver chrome

télécharge le driver chrome (c’est le browser, mais executable en ligne de commande). Pour faire ça, va ici : https://chromedriver.storage.googleapis.com/2.25/chromedriver_mac64.zip

Dézipe et déplace le fichier “chromedriver” dans le répertoire /usr/local/bin avec la commande suivante : mv Downloads/chromedriver /usr/local/bin/

execute le fichier ruby suivant (remplacer les infos du comptes dans le script) :

ruby scrap_faustin.rb

result.txt

{
  "workouts"=>{
    "aphrodite"=>{
        "Série 1"=>["50 Burpees", "50 Squats", "50 Situps"], 
        "Série 2"=>["40 Burpees", "40 Squats", "40 Situps"], 
        "Série 3"=>["30 Burpees", "30 Squats", "30 Situps"], 
        "Série 4"=>["20 Burpees", "20 Squats", "20 Situps"], 
        "Série 5"=>["10 Burpees", "10 Squats", "10 Situps"]
        }, 
    "dione"=>{
        "Série 1"=>["50 Burpees", "50 Squats", "50 Situps"], 
        "Série 2"=>["40 Burpees", "40 Squats", "40 Situps"], 
        "Série 3"=>["30 Burpees", "30 Squats", "30 Situps"], 
        "Série 4"=>["20 Burpees", "20 Squats", "20 Situps"], 
        "Série 5"=>["10 Burpees", "10 Squats", "10 Situps"]
        }
    }, 
  "exercices"=>{
    "burpees"=>{
        "Série 1"=>["10 Burpees"]
        }
     }
}

scrap_faustin.rb

require 'nokogiri'
require 'watir'
# require 'watir-scroll'
require 'pry-byebug'

def explore(browser, name, item, result)

  # init result
  result[name] = {} unless result.has_key?(name)
  result[name][item[:name]] = {}

  # browse series
  browser.goto item[:url]

  doc = Nokogiri::HTML.parse(browser.html)
  doc.search('.workout_detail-table-repetitions').each do |element|
    # round
    round = element.search('.workout_detail-table-round').text
    series = []

    # combien
    element.search('.big_and_bold').each do |how_many|
      series << how_many.text
    end

    index = 0
    # quoi
    element.search('.workout_detail-table-exercise').each do |what|
      series[index] += " #{what.text}"
      index += 1
    end

    result[name][item[:name]][round] = series

  end


end




# login
browser = Watir::Browser.new
browser.goto 'https://www.freeletics.com/fr/login'
browser.text_field(:placeholder => 'Adresse e-mail').set 'vincent.damien@gmail.com'
browser.text_field(:placeholder => 'Mot de passe').set 'presidentielles2017'
submit = browser.button(:text =>"Se connecter").click

sleep(5)

workouts = [
  {
    name: "aphrodite",
    url: "https://www.freeletics.com/fr/bodyweight/workouts/aphrodite"
  },
  {
    name: "dione",
    url: "https://www.freeletics.com/fr/bodyweight/workouts/aphrodite"
  }
]

exercices = [
  {
    name: "burpees",
    url: "https://www.freeletics.com/fr/bodyweight/exercises/burpees"
  }
]

result = {}

workouts.each do |item|
  explore(browser, "workouts", item, result)
end

exercices.each do |item|
  explore(browser, "exercices", item, result)
end

puts result