Class: Crawler

Inherits:
Object
  • Object
show all
Defined in:
lib/rfilma/crawler.rb

Direct Known Subclasses

CrawlerDB

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Crawler

Returns a new instance of Crawler.



7
8
9
10
11
 
# File 'lib/rfilma/crawler.rb', line 7

def initialize
	@a = Mechanize.new{|op|
		op.user_agent_alias = "Windows Mozilla"			
	}
end

Instance Method Details

#buscar_por_titulo(titulo) ⇒ Object 



60
61
62
63
64
65
66
67
68
 
# File 'lib/rfilma/crawler.rb', line 60

def buscar_por_titulo(titulo)
	indices_pelis = []
	p = @a.get("http://www.filmaffinity.com/es/search.php?stext=#{titulo.strip.gsub(" ","+")}&stype=title").body
	doc = Nokogiri::HTML(p)
	doc.xpath('//div[@class="movie-card movie-card-1"]').each{|mc|
		indices_pelis << mc["data-movie-id"].to_i
	}
	indices_pelis.map{|i| obtener_pelicula(i)}
end

#obtener_pelicula(id) ⇒ Object 



14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
 
# File 'lib/rfilma/crawler.rb', line 14

def obtener_pelicula(id)
	data = {}
	page = @a.get("http://www.filmaffinity.com/es/film#{id}.html").body
	doc = Nokogiri::HTML(page)
	data["id"] = id
	data["titulo"] = doc.xpath("//h1[@id='main-title']/a/span").text
	data["puntuacion"] = doc.xpath('//div[@id="movie-rat-avg"]').text.strip.gsub(",",".").to_f
	begin
		data["portada"] = doc.xpath('//div[@id="movie-main-image-container"]/a')[0]["href"]
	rescue
		data["portada"] = doc.xpath('//div[@id="movie-main-image-container"]/img')[0]["src"]
	end
	doc.xpath('//dl[@class="movie-info"]/dt').each{|m|
		dt = m.inner_html
		case 
		when dt.include?("Título original")
			data["titulo_original"] = m.next_element.text
		when dt.include?("Año")	
			data["año"] = m.next_element.text.to_i		
		when dt.include?("Duración")
			data["duracion"] = m.next_element.text.match('(\d*)')[1].to_i
		when dt.include?("País")
			data["pais"] = m.next_element.at('img')['title']
		when dt.include?("Director")		
			data["director"] = m.next_element.search('a').map{|e| e.inner_html.strip}
		when dt.include?("Guión")
			data["guion"] = m.next_element.text.split(",").map{|e|e.strip}
		when dt.include?("Música")
			data["musica"] = m.next_element.text.split(",").map{|e|e.strip}
		when dt.include?("Fotografía")
			data["fotografia"] = m.next_element.text.split(",").map{|e|e.strip}
		when dt.include?("Reparto")
			data["reparto"] = m.next_element.text.split(",").map{|e|e.strip}
		when dt.include?("Productora")
			data["productora"] = m.next_element.text
		when dt.include?("Género")		
			data["genero"] = m.next_element.search('a').map{|e| e.inner_html}
		when dt.include?("Web")	
			data["web"] = m.next_element.text
		when dt.include?("Sinopsis")	
			data["sinopsis"] = m.next_element.text			
		end
	}
	data
end