google_translate_scraper 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +18 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +29 -0
- data/Rakefile +2 -0
- data/google_translate_scraper.gemspec +18 -0
- data/lib/google_translate_scraper/translator.rb +62 -0
- data/lib/google_translate_scraper/version.rb +3 -0
- data/lib/google_translate_scraper.rb +6 -0
- metadata +87 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Sebastian Glazebrook
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# GoogleTranslateScraper
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'google_translate_scraper'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install google_translate_scraper
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/google_translate_scraper/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Seb Glazebrook"]
|
6
|
+
gem.email = ["me@sebglazebrook.com"]
|
7
|
+
gem.description = %q{" add details description of gem here."}
|
8
|
+
gem.summary = %q{"This gem scrapes Google Translate and their results."}
|
9
|
+
gem.homepage = ""
|
10
|
+
|
11
|
+
gem.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
12
|
+
gem.files = `git ls-files`.split("\n")
|
13
|
+
gem.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
14
|
+
gem.name = "google_translate_scraper"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.version = GoogleTranslateScraper::VERSION
|
17
|
+
gem.add_dependency "nokogiri"
|
18
|
+
end
|
@@ -0,0 +1,62 @@
|
|
1
|
+
module GoogleTranslateScraper
|
2
|
+
require 'net/http'
|
3
|
+
require 'nokogiri'
|
4
|
+
|
5
|
+
class Translator
|
6
|
+
|
7
|
+
@@input_language = nil
|
8
|
+
@@target_language = nil
|
9
|
+
@@text = nil
|
10
|
+
|
11
|
+
def translate(input_language, target_language, text )
|
12
|
+
@@input_language = input_language
|
13
|
+
@@target_language = target_language
|
14
|
+
@@text = text
|
15
|
+
get_translation
|
16
|
+
end
|
17
|
+
|
18
|
+
def get_translation
|
19
|
+
# set POST variables
|
20
|
+
js = "n"
|
21
|
+
prev = "_t"
|
22
|
+
hv = "en" # i think this is the language of the website
|
23
|
+
ie = "UTF-8"
|
24
|
+
layout = "2"
|
25
|
+
eotf = "1"
|
26
|
+
file = ""
|
27
|
+
|
28
|
+
# download the webpage
|
29
|
+
http_response = Net::HTTP.post_form(URI.parse('http://translate.google.com/'), {"sl" => @@input_language, "tl" => @@target_language, "js" => "n", "prev" => "_t", "hv" => "en", "ie" =>
|
30
|
+
"UTF-8" , "layout" => "2", "eotf" => "1", "text" => @@text, "file" => ""})
|
31
|
+
# get the string
|
32
|
+
html_string = http_response.body
|
33
|
+
# convert string to a Nokogiri document file
|
34
|
+
html_doc = Nokogiri::HTML(html_string)
|
35
|
+
# find the translation
|
36
|
+
translation = Array.new
|
37
|
+
translation = get_dictionary_translation(html_doc)
|
38
|
+
# check for non-dictionary translations
|
39
|
+
if translation.empty?
|
40
|
+
translation[0] = get_non_dictionary_translation(html_doc).text
|
41
|
+
end
|
42
|
+
return translation
|
43
|
+
|
44
|
+
end
|
45
|
+
|
46
|
+
# when there are multiple translations
|
47
|
+
def get_dictionary_translation html_doc
|
48
|
+
translations = Array.new
|
49
|
+
translation = html_doc.xpath('//div[@id="gt-res-dict"]/ol/li/div/div')
|
50
|
+
translation.each do |t|
|
51
|
+
translations.push t.text
|
52
|
+
end
|
53
|
+
translations
|
54
|
+
end
|
55
|
+
|
56
|
+
# when there is a phrase with no dictionary translation i.e multiple possible translations
|
57
|
+
def get_non_dictionary_translation html_doc
|
58
|
+
translation = html_doc.xpath('//html/body/div[2]/div[2]/form/div[2]/div[2]/div/div/div[2]/div/div[2]/span/span')
|
59
|
+
end
|
60
|
+
|
61
|
+
end
|
62
|
+
end
|
metadata
ADDED
@@ -0,0 +1,87 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: google_translate_scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 29
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 0
|
9
|
+
- 1
|
10
|
+
version: 0.0.1
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Seb Glazebrook
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2012-03-12 00:00:00 Z
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: nokogiri
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
none: false
|
25
|
+
requirements:
|
26
|
+
- - ">="
|
27
|
+
- !ruby/object:Gem::Version
|
28
|
+
hash: 3
|
29
|
+
segments:
|
30
|
+
- 0
|
31
|
+
version: "0"
|
32
|
+
type: :runtime
|
33
|
+
version_requirements: *id001
|
34
|
+
description: "\" add details description of gem here.\""
|
35
|
+
email:
|
36
|
+
- me@sebglazebrook.com
|
37
|
+
executables: []
|
38
|
+
|
39
|
+
extensions: []
|
40
|
+
|
41
|
+
extra_rdoc_files: []
|
42
|
+
|
43
|
+
files:
|
44
|
+
- .gitignore
|
45
|
+
- Gemfile
|
46
|
+
- LICENSE
|
47
|
+
- README.md
|
48
|
+
- Rakefile
|
49
|
+
- google_translate_scraper.gemspec
|
50
|
+
- lib/google_translate_scraper.rb
|
51
|
+
- lib/google_translate_scraper/translator.rb
|
52
|
+
- lib/google_translate_scraper/version.rb
|
53
|
+
homepage: ""
|
54
|
+
licenses: []
|
55
|
+
|
56
|
+
post_install_message:
|
57
|
+
rdoc_options: []
|
58
|
+
|
59
|
+
require_paths:
|
60
|
+
- lib
|
61
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
62
|
+
none: false
|
63
|
+
requirements:
|
64
|
+
- - ">="
|
65
|
+
- !ruby/object:Gem::Version
|
66
|
+
hash: 3
|
67
|
+
segments:
|
68
|
+
- 0
|
69
|
+
version: "0"
|
70
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
71
|
+
none: false
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
hash: 3
|
76
|
+
segments:
|
77
|
+
- 0
|
78
|
+
version: "0"
|
79
|
+
requirements: []
|
80
|
+
|
81
|
+
rubyforge_project:
|
82
|
+
rubygems_version: 1.8.9
|
83
|
+
signing_key:
|
84
|
+
specification_version: 3
|
85
|
+
summary: "\"This gem scrapes Google Translate and their results.\""
|
86
|
+
test_files: []
|
87
|
+
|