Class: BudgetBytesCli::Scraper

Inherits:
Object
  • Object
show all
Defined in:
lib/budget_bytes_cli/scraper.rb

Class Method Summary collapse

Class Method Details

.create_categories ⇒ Object 



12
13
14
15
16
17
18
 
# File 'lib/budget_bytes_cli/scraper.rb', line 12

def self.create_categories
    locate_categories.each do |item|
        url = item.css("a").attribute("href").value
        title = item.css("a").children[0].text
        BudgetBytesCli::Category.new(url, title)
    end
end

.create_page_url(num, url) ⇒ Object 



45
46
47
48
49
50
51
 
# File 'lib/budget_bytes_cli/scraper.rb', line 45

def self.create_page_url(num, url)
    if num == 1
        url
    else
        url + "page/" + num.to_s + "/"
    end
end

.get_recipes(url) ⇒ Object

functions for scraping recipes within a category



21
22
23
24
25
26
27
28
29
30
31
32
 
# File 'lib/budget_bytes_cli/scraper.rb', line 21

def self.get_recipes(url)
    first_page = Nokogiri::HTML(open(url))
    
    page_nums = first_page.css(".page-numbers")
    if page_nums.empty?
        pages_total = 1
    else
        pages_total = page_nums.map{|p| p.text.to_i}.max
    end
    
    (1..pages_total).map {|p|get_recipes_from(create_page_url(p, url))}.flatten
end

.get_recipes_from(page_url) ⇒ Object 



34
35
36
37
38
39
40
41
42
43
 
# File 'lib/budget_bytes_cli/scraper.rb', line 34

def self.get_recipes_from(page_url)
    recipe_page = Nokogiri::HTML(open(page_url))
    recipe_links = recipe_page.css(".archive-post a")
    
    recipe_links.map do |r|
        recipe_title = r.attribute("title").value
        recipe_url = r.attribute("href").value
        BudgetBytesCli::Recipe.new(recipe_url, recipe_title)
    end
end

.locate_categories ⇒ Object 



8
9
10
 
# File 'lib/budget_bytes_cli/scraper.rb', line 8

def self.locate_categories
    open_page.css(".cat-item")
end

.open_page ⇒ Object

functions for getting categories



4
5
6
 
# File 'lib/budget_bytes_cli/scraper.rb', line 4

def self.open_page
    Nokogiri::HTML(open("https://www.budgetbytes.com/recipes/"))
end

.scrape_recipe(url) ⇒ Object

scrape instructions, ingredients from recipe page



54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
 
# File 'lib/budget_bytes_cli/scraper.rb', line 54

def self.scrape_recipe(url)
    page = Nokogiri::HTML(open(url))
    
    ingredient_amounts = page.css('.wprm-recipe-ingredient-amount').map {|i| i.text}
    ingredient_units = page.css('.wprm-recipe-ingredient-unit').map {|i| i.text}
    ingredient_names = page.css('.wprm-recipe-ingredient-name').map {|i| i.text}
    
    ingredient_array = []
    
    #scraping ingredients for new site
    ingredient_amounts.each_with_index do |ele, idx|
        ingredient_array << [ele, ingredient_units[idx], ingredient_names[idx]].join(' ').strip
    end
    
    #scraping for old site before css switched so that the code above scrapes ingredients
    old_ingredients_table = page.css("tr")
    
    #get rid of first, last rows in table (header and total cost)
    old_ingredients_table.shift
    old_ingredients_table.pop 
    
    old_ingredients_table.each do |old_ingredient|
        old_ingredient_text = old_ingredient.text.split("\n")
        
        #get rid of first blank item, last cost item
        old_ingredient_text.shift
        old_ingredient_text.pop
        
        ingredient_array << old_ingredient_text.join(" ")
    end
    
    recipe_steps = []
    
    #scraping instructions for old site before css switched to have recipe instructions in own class
    page.css("p").map {|i| i.text}.each do |p|
        if p.split(" ")[0] == "STEP"
            recipe_steps << p.split(" ").slice(2, p.length - 2).join(" ")
        end
    end
    
    #scraping instructions for new site
    page.css(".wprm-recipe-instruction-text").each {|i| recipe_steps << i.text}

    [ingredient_array.join("\n"), recipe_steps.join("\n")]
end