oald_parser 0.2 → 0.2.1
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.
- data/lib/oald_parser/page_parser.rb +22 -5
- data/lib/oald_parser.rb +1 -1
- metadata +3 -2
@@ -25,8 +25,10 @@ module OaldParser
|
|
25
25
|
class PageParser
|
26
26
|
def parse(page)
|
27
27
|
parsed = Nokogiri::HTML(page)
|
28
|
-
if blocks_on_page?
|
28
|
+
if blocks_on_page? parsed
|
29
29
|
Page.new(parse_block(parsed), [])
|
30
|
+
elsif def_on_page? parsed
|
31
|
+
Page.new([], parse_def(parsed))
|
30
32
|
else
|
31
33
|
Page.new([], parse_items(parsed))
|
32
34
|
end
|
@@ -37,6 +39,10 @@ module OaldParser
|
|
37
39
|
page.css('div.sd-g').first
|
38
40
|
end
|
39
41
|
|
42
|
+
def def_on_page?(page)
|
43
|
+
page.css('div.h-g').first
|
44
|
+
end
|
45
|
+
|
40
46
|
def parse_block(page)
|
41
47
|
block_nodes = page.css('div.sd-g')
|
42
48
|
block_nodes.collect do |block|
|
@@ -50,15 +56,26 @@ module OaldParser
|
|
50
56
|
item_nodes = block.css('span.n-g')
|
51
57
|
item_nodes.collect do |item|
|
52
58
|
item_text = all_except(item, 'x-g')
|
53
|
-
|
54
|
-
examples = example_nodes.collect{|e| e.text.strip}
|
55
|
-
Item.new(item_text, examples)
|
59
|
+
Item.new(item_text, parse_examples(item))
|
56
60
|
end
|
57
61
|
end
|
58
62
|
|
63
|
+
def parse_def(page)
|
64
|
+
item_nodes = page.css('div.h-g')
|
65
|
+
item_nodes.collect do |item|
|
66
|
+
item_text = item.css('div.def_block').first.text.strip
|
67
|
+
Item.new(item_text, parse_examples(item))
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
def parse_examples(item)
|
72
|
+
example_nodes = item.css('span.x-g')
|
73
|
+
example_nodes.collect{|e| e.text.strip}
|
74
|
+
end
|
75
|
+
|
59
76
|
def all_except(item, class_name)
|
60
77
|
elements = item.children.find_all do |c|
|
61
|
-
!(c.name
|
78
|
+
!(['span', 'div'].include?(c.name) && c[:class] == class_name)
|
62
79
|
end
|
63
80
|
elements.collect{|e|e.text}.join('').strip
|
64
81
|
end
|
data/lib/oald_parser.rb
CHANGED
@@ -8,7 +8,7 @@ require_relative 'oald_parser/page_parser'
|
|
8
8
|
#include OaldParser
|
9
9
|
#
|
10
10
|
#downloader = PageDownloader.new("http://www.oxfordadvancedlearnersdictionary.com/dictionary")
|
11
|
-
#page = downloader.download("
|
11
|
+
#page = downloader.download("prevent")
|
12
12
|
#parser = PageParser.new
|
13
13
|
#parsed = parser.parse(page)
|
14
14
|
#formatter = Formatter.new(items: 15)
|
metadata
CHANGED
@@ -5,7 +5,8 @@ version: !ruby/object:Gem::Version
|
|
5
5
|
segments:
|
6
6
|
- 0
|
7
7
|
- 2
|
8
|
-
|
8
|
+
- 1
|
9
|
+
version: 0.2.1
|
9
10
|
platform: ruby
|
10
11
|
authors:
|
11
12
|
- Victor Savkin
|
@@ -13,7 +14,7 @@ autorequire:
|
|
13
14
|
bindir: bin
|
14
15
|
cert_chain: []
|
15
16
|
|
16
|
-
date: 2010-05-
|
17
|
+
date: 2010-05-11 00:00:00 +11:00
|
17
18
|
default_executable:
|
18
19
|
dependencies:
|
19
20
|
- !ruby/object:Gem::Dependency
|