horsefield 0.4.2 → 0.4.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/horsefield/scraper.rb +15 -6
- data/lib/horsefield/version.rb +1 -1
- data/test/horsefield/test_scraper.rb +7 -0
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 0f5b4da37cbaf7e0849d70748e380f7b207c7d1d
|
4
|
+
data.tar.gz: 830aa7acdc756a64cedc424f9dd04d49f5734ccb
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: c38b39c2a26f39994d1b1f09f013c5a4ef5c41b001e71f28cd7003da8d89a2d23a8267a528e4805cd587a9ed1d713245d857b8fcc5f4aea0a9ea9665441c98b1
|
7
|
+
data.tar.gz: e1ce59b3063d0bf4e3db3993d1aec8c11181ce9f544f57584d6355d1e244712e507df12c65bfa52fb9a1d72d210d63764cf2ab61a06efbcaeddfc4af28f21c5c
|
data/lib/horsefield/scraper.rb
CHANGED
@@ -21,20 +21,25 @@ module Horsefield
|
|
21
21
|
end
|
22
22
|
|
23
23
|
def fields
|
24
|
-
@fields ||= self.class.
|
24
|
+
@fields ||= self.class.lookups.reduce({}) { |fields, l| fields.merge(l.call(@doc)) }.
|
25
|
+
instance_eval(&self.class.postprocessor)
|
25
26
|
end
|
26
27
|
|
27
28
|
module ClassMethods
|
28
|
-
def
|
29
|
-
@
|
29
|
+
def lookups
|
30
|
+
@lookups ||= []
|
31
|
+
end
|
32
|
+
|
33
|
+
def postprocessor
|
34
|
+
@postprocessor || Proc.new { self }
|
30
35
|
end
|
31
36
|
|
32
37
|
def one(name, selector, lookup = :optional, &block)
|
33
|
-
self.
|
38
|
+
self.lookups << lambda { |doc| doc.one(name, selector, lookup, &block) }
|
34
39
|
end
|
35
40
|
|
36
41
|
def many(name, selector, lookup = :optional, &block)
|
37
|
-
self.
|
42
|
+
self.lookups << lambda { |doc| doc.many(name, selector, lookup, &block) }
|
38
43
|
end
|
39
44
|
|
40
45
|
def many!(name, selector, &block)
|
@@ -54,7 +59,11 @@ module Horsefield
|
|
54
59
|
end
|
55
60
|
|
56
61
|
def scope(selector, &block)
|
57
|
-
self.
|
62
|
+
self.lookups << lambda { |doc| doc.at(selector).instance_eval(&block) }
|
63
|
+
end
|
64
|
+
|
65
|
+
def postprocess(&block)
|
66
|
+
@postprocessor = block
|
58
67
|
end
|
59
68
|
end
|
60
69
|
end
|
data/lib/horsefield/version.rb
CHANGED
@@ -1,4 +1,5 @@
|
|
1
1
|
require 'test_helper'
|
2
|
+
require 'pry'
|
2
3
|
|
3
4
|
class RecipeScraper
|
4
5
|
include Horsefield::Scraper
|
@@ -12,6 +13,11 @@ class RecipeScraper
|
|
12
13
|
one(:type) { at('span').text }
|
13
14
|
one(:value) { at('span.value').text }
|
14
15
|
end
|
16
|
+
|
17
|
+
postprocess do |doc|
|
18
|
+
doc[:nutritional_value] = doc[:nutritional_value].uniq.compact
|
19
|
+
doc
|
20
|
+
end
|
15
21
|
end
|
16
22
|
|
17
23
|
class RecipeScraperWithOptionalField
|
@@ -41,6 +47,7 @@ class TestScraper < Minitest::Test
|
|
41
47
|
|
42
48
|
def test_that_it_scrapes
|
43
49
|
recipe = RecipeScraper.new(@html).scrape
|
50
|
+
p recipe
|
44
51
|
|
45
52
|
assert_equal 'Traditional Welsh cawl', recipe[:title]
|
46
53
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: horsefield
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.4.
|
4
|
+
version: 0.4.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Erik Strömberg
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-02-
|
11
|
+
date: 2015-02-03 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|