oald_parser 0.1
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.
@@ -0,0 +1,37 @@
|
|
1
|
+
require_relative 'oald_parser_exception'
|
2
|
+
require_relative 'page_parser'
|
3
|
+
require_relative 'formatter'
|
4
|
+
require_relative 'page_downloader'
|
5
|
+
|
6
|
+
module OaldParser
|
7
|
+
class Facade
|
8
|
+
def initialize(downloader, parser, formatter)
|
9
|
+
@downloader = downloader
|
10
|
+
@parser = parser
|
11
|
+
@formatter = formatter
|
12
|
+
end
|
13
|
+
|
14
|
+
def self.create_facade
|
15
|
+
downloader = PageDownloader.new('http://www.oup.com/oald-bin/web_getald7index1a.pl')
|
16
|
+
parser = PageParser.new
|
17
|
+
formatter = Formatter.new(lines: 15)
|
18
|
+
Facade.new(downloader, parser, formatter)
|
19
|
+
end
|
20
|
+
|
21
|
+
def describe(args)
|
22
|
+
word = args[:word]
|
23
|
+
raise OaldParserException.new(OaldParserException::INTERNAL) unless word
|
24
|
+
|
25
|
+
page = @downloader.download(word)
|
26
|
+
raise OaldParserException.new(OaldParserException::NET) unless page
|
27
|
+
|
28
|
+
parsed = @parser.parse(page)
|
29
|
+
raise OaldParserException.new(OaldParserException::PARSER) unless parsed
|
30
|
+
|
31
|
+
formatted = @formatter.format(parsed)
|
32
|
+
raise OaldParserException.new(OaldParserException::FORMATTER) unless formatted
|
33
|
+
|
34
|
+
formatted
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
|
3
|
+
module OaldParser
|
4
|
+
class Formatter
|
5
|
+
def initialize(options)
|
6
|
+
@options = options
|
7
|
+
end
|
8
|
+
|
9
|
+
def format(content)
|
10
|
+
lined_content = content.gsub(/<\s*br\s*\/*>/, '\n')
|
11
|
+
text = Nokogiri::HTML(lined_content).text
|
12
|
+
first_lines = first_lines(text, @options[:lines])
|
13
|
+
first_lines.strip
|
14
|
+
rescue
|
15
|
+
nil
|
16
|
+
end
|
17
|
+
|
18
|
+
private
|
19
|
+
def first_lines(text, lines)
|
20
|
+
text.split('\n').first(lines).join('\n')
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
module OaldParser
|
2
|
+
class OaldParserException < Exception
|
3
|
+
NET = :net
|
4
|
+
PARSER = :parser
|
5
|
+
FORMATTER = :formatter
|
6
|
+
INTERNAL = :internal
|
7
|
+
|
8
|
+
attr_reader :code
|
9
|
+
|
10
|
+
def initialize(code, message = nil)
|
11
|
+
@code = code
|
12
|
+
if message
|
13
|
+
super message
|
14
|
+
else
|
15
|
+
super "#{@code} problems"
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
require 'net/http'
|
2
|
+
require 'uri'
|
3
|
+
|
4
|
+
module OaldParser
|
5
|
+
class PageDownloader
|
6
|
+
def initialize(url)
|
7
|
+
@url = url
|
8
|
+
end
|
9
|
+
|
10
|
+
def download(word)
|
11
|
+
url = URI.parse(@url)
|
12
|
+
Net::HTTP.post_form(url, search_word: word)
|
13
|
+
rescue
|
14
|
+
nil
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
module OaldParser
|
2
|
+
class PageParser
|
3
|
+
def parse(page)
|
4
|
+
page = extract_part_without_header(page)
|
5
|
+
return nil unless page
|
6
|
+
page = extract_part_without_footer(page)
|
7
|
+
return nil unless page
|
8
|
+
page.strip
|
9
|
+
end
|
10
|
+
|
11
|
+
private
|
12
|
+
def extract_part_without_header(page)
|
13
|
+
parts = page.split(/<\/select>\s*<\/form>/i)
|
14
|
+
parts.size == 2 ? parts[1] : nil
|
15
|
+
end
|
16
|
+
|
17
|
+
def extract_part_without_footer(page)
|
18
|
+
parts = page.split(/<div\s+class='oald'>/i)
|
19
|
+
parts.size == 2 ? parts[0] : nil
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
metadata
ADDED
@@ -0,0 +1,79 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: oald_parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 0
|
7
|
+
- 1
|
8
|
+
version: "0.1"
|
9
|
+
platform: ruby
|
10
|
+
authors:
|
11
|
+
- Victor Savkin
|
12
|
+
autorequire:
|
13
|
+
bindir: bin
|
14
|
+
cert_chain: []
|
15
|
+
|
16
|
+
date: 2010-04-13 00:00:00 +11:00
|
17
|
+
default_executable:
|
18
|
+
dependencies:
|
19
|
+
- !ruby/object:Gem::Dependency
|
20
|
+
name: rspec
|
21
|
+
prerelease: false
|
22
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
segments:
|
27
|
+
- 0
|
28
|
+
version: "0"
|
29
|
+
type: :development
|
30
|
+
version_requirements: *id001
|
31
|
+
description: Simple parse for online oxford dictionary
|
32
|
+
email:
|
33
|
+
- avix1000@gmail.com
|
34
|
+
executables: []
|
35
|
+
|
36
|
+
extensions: []
|
37
|
+
|
38
|
+
extra_rdoc_files: []
|
39
|
+
|
40
|
+
files:
|
41
|
+
- lib/oald_parser/page_downloader.rb
|
42
|
+
- lib/oald_parser/formatter.rb
|
43
|
+
- lib/oald_parser/oald_parser_exception.rb
|
44
|
+
- lib/oald_parser/page_parser.rb
|
45
|
+
- lib/oald_parser/facade.rb
|
46
|
+
has_rdoc: true
|
47
|
+
homepage:
|
48
|
+
licenses: []
|
49
|
+
|
50
|
+
post_install_message:
|
51
|
+
rdoc_options: []
|
52
|
+
|
53
|
+
require_paths:
|
54
|
+
- lib
|
55
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
56
|
+
requirements:
|
57
|
+
- - ">="
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
segments:
|
60
|
+
- 0
|
61
|
+
version: "0"
|
62
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
63
|
+
requirements:
|
64
|
+
- - ">="
|
65
|
+
- !ruby/object:Gem::Version
|
66
|
+
segments:
|
67
|
+
- 1
|
68
|
+
- 3
|
69
|
+
- 6
|
70
|
+
version: 1.3.6
|
71
|
+
requirements: []
|
72
|
+
|
73
|
+
rubyforge_project:
|
74
|
+
rubygems_version: 1.3.6
|
75
|
+
signing_key:
|
76
|
+
specification_version: 3
|
77
|
+
summary: Simple parse for online oxford dictionary
|
78
|
+
test_files: []
|
79
|
+
|