Class: WebsCriteria

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

Overview

WebsCriteria.new.all_scrub_web_criteria

Class Method Summary collapse

Class Method Details

.all_scrub_web_criteria ⇒ Object 



5
6
7
8
9
10
11
12
13
14
 
# File 'lib/webs_criteria.rb', line 5

def self.all_scrub_web_criteria
  {
    neg_urls: seed_neg_urls,
    pos_urls: seed_pos_urls,
    neg_paths: seed_neg_paths,
    pos_paths: seed_pos_paths,
    neg_exts: seed_neg_exts,
    pos_exts: seed_pos_exts
  }
end

.seed_neg_exts ⇒ Object 



32
33
34
 
# File 'lib/webs_criteria.rb', line 32

def self.seed_neg_exts
   %w(au ca edu es gov in ru uk us)
end

.seed_neg_paths ⇒ Object 



24
25
26
 
# File 'lib/webs_criteria.rb', line 24

def self.seed_neg_paths
  %w(: .biz .co .edu .gov .jpg .net // afri anounc book business buy bye call cash cheap click collis cont distrib download drop event face feature feed financ find fleet form gas generat graphic hello home hospi hour hours http info insta inventory item join login mail mailto mobile movie museu music news none offer part phone policy priva pump rate regist review schedul school service shop site test ticket tire tv twitter watch www yelp youth)
end

.seed_neg_urls ⇒ Object 



16
17
18
 
# File 'lib/webs_criteria.rb', line 16

def self.seed_neg_urls
  %w(approv avis budget collis eat enterprise facebook financ food google gourmet hertz hotel hyatt insur invest loan lube mobility motel motorola parts quick rent repair restaur rv ryder service softwar travel twitter webhost yellowpages yelp youtube)
end

.seed_pos_exts ⇒ Object 



36
37
38
 
# File 'lib/webs_criteria.rb', line 36

def self.seed_pos_exts
   %w(com net)
end

.seed_pos_paths ⇒ Object 



28
29
30
 
# File 'lib/webs_criteria.rb', line 28

def self.seed_pos_paths
  %w(team staff management)
end

.seed_pos_urls ⇒ Object 



20
21
22
 
# File 'lib/webs_criteria.rb', line 20

def self.seed_pos_urls
  ["acura", "alfa romeo", "aston martin", "audi", "bmw", "bentley", "bugatti", "buick", "cdjr", "cadillac", "chevrolet", "chrysler", "dodge", "ferrari", "fiat", "ford", "gmc", "group", "group", "honda", "hummer", "hyundai", "infiniti", "isuzu", "jaguar", "jeep", "kia", "lamborghini", "lexus", "lincoln", "lotus", "mini", "maserati", "mazda", "mclaren", "mercedes-benz", "mitsubishi", "nissan", "porsche", "ram", "rolls-royce", "saab", "scion", "smart", "subaru", "suzuki", "toyota", "volkswagen", "volvo"]
end