google_scraper_gem 0.1.0
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 +7 -0
- data/.gitignore +17 -0
- data/Gemfile +5 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +6 -0
- data/google_scraper_gem.gemspec +25 -0
- data/lib/google_scraper_gem/version.rb +3 -0
- data/lib/google_scraper_gem.rb +98 -0
- data/spec/google_scraper_gem_spec.rb +18 -0
- metadata +110 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: e2d5d369bdc61676e20de327fa71d15034c813e4
|
4
|
+
data.tar.gz: fa0ea376e7f622027da3a0a5ce574f90d2060ed2
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a34db3cff8fba2a3686bc85a04c25853f314d0c9ad7efa36a7d6c0d00f45aae9b597e66b72fcdbb4497c0f9e5e283e8ab3554b61cdc9f29c95773441166f8e4a
|
7
|
+
data.tar.gz: e5c9596f98e4e3f17303877ce486c0024525e1ad09eec6c5adcf7974dfec35457faefa0da0820a48b3439e580c66343ada3d1ca12d3d4ca13f119c60da61cd34
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Han Chang
|
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
|
+
# GoogleScraperGem
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'google_scraper_gem'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install google_scraper_gem
|
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 'Add 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 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'google_scraper_gem/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "google_scraper_gem"
|
8
|
+
spec.version = GoogleScraperGem::VERSION
|
9
|
+
spec.authors = ["Han Chang"]
|
10
|
+
spec.email = ["szu.han.chang@gmail.com"]
|
11
|
+
spec.description = %q{Scrapes Google Search results}
|
12
|
+
spec.summary = %q{Scrapes Google Search results}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
22
|
+
spec.add_development_dependency "rake"
|
23
|
+
spec.add_runtime_dependency "mechanize"
|
24
|
+
spec.add_runtime_dependency "nokogiri"
|
25
|
+
end
|
@@ -0,0 +1,98 @@
|
|
1
|
+
require 'uri'
|
2
|
+
require 'mechanize'
|
3
|
+
require 'nokogiri'
|
4
|
+
|
5
|
+
class GoogleScraper
|
6
|
+
BASE_URL = "http://www.google"
|
7
|
+
SEARCH = "/search?q="
|
8
|
+
CSS_SELECTOR = "li[@class='g'] > div.rc > h3.r > a"
|
9
|
+
RANK_LIMIT = 100 # Stop looking for the target URL after 100 results
|
10
|
+
|
11
|
+
def initialize()
|
12
|
+
# proxy = {:host => "204.12.216.84", :port => 20602, :username => 'pp-henryjay', :password => 'rein&true'}
|
13
|
+
@mech = Mechanize.new { |agent|
|
14
|
+
# User Agent list - http://github.com/tenderlove/mechanize/blob/master/lib/mechanize.rb
|
15
|
+
agent.user_agent_alias = 'Mac Safari'
|
16
|
+
}
|
17
|
+
|
18
|
+
# @mech.set_proxy proxy[:host], proxy[:port], proxy[:username], proxy[:password]
|
19
|
+
end
|
20
|
+
|
21
|
+
# @return Rank of URL for keyword in google.locale
|
22
|
+
def checkRank(keyword, url, locale: '.com')
|
23
|
+
results = []
|
24
|
+
|
25
|
+
rank_count = 0
|
26
|
+
page_num = 1
|
27
|
+
|
28
|
+
uri = BASE_URL + locale + SEARCH + URI.encode(keyword)
|
29
|
+
|
30
|
+
page = @mech.get(uri)
|
31
|
+
while rank_count < RANK_LIMIT
|
32
|
+
# This parse definition requires the Mac Safari user agent.
|
33
|
+
page.parser.css(CSS_SELECTOR).each do |cite|
|
34
|
+
rank_count += 1
|
35
|
+
|
36
|
+
result = cite.attr('href')
|
37
|
+
puts result
|
38
|
+
|
39
|
+
result.gsub!(%r{^http://}, '')
|
40
|
+
result.gsub!(%r{^https://}, '')
|
41
|
+
|
42
|
+
return rank_count if result.start_with?(url) or result.start_with?("www." + url)
|
43
|
+
end
|
44
|
+
|
45
|
+
# Get next search result page.
|
46
|
+
page_num += 1
|
47
|
+
|
48
|
+
# Add random sleep to prevent blocking of IP.
|
49
|
+
# TODO: Replace this with proxy swap.
|
50
|
+
rand(8)
|
51
|
+
|
52
|
+
# TODO: Click "next" instead?
|
53
|
+
page = page.link_with(:text => page_num.to_s).click
|
54
|
+
end
|
55
|
+
|
56
|
+
return -1
|
57
|
+
end
|
58
|
+
|
59
|
+
# @return Array of domains in the order specified by Google.
|
60
|
+
def getTopResults(keyword, extension: '.com', top: 10)
|
61
|
+
results = []
|
62
|
+
|
63
|
+
rank_count = 0
|
64
|
+
page_num = 1
|
65
|
+
|
66
|
+
uri = BASE_URL + extension + SEARCH + URI.encode(keyword)
|
67
|
+
|
68
|
+
page = @mech.get(uri)
|
69
|
+
while rank_count < top
|
70
|
+
# This parse definition requires the Mac Safari user agent.
|
71
|
+
page.parser.css(CSS_SELECTOR).each do |cite|
|
72
|
+
rank_count += 1
|
73
|
+
|
74
|
+
result = cite.attr('href')
|
75
|
+
puts result
|
76
|
+
results << result if result.start_with? 'http'
|
77
|
+
end
|
78
|
+
|
79
|
+
return results if rank_count >= top
|
80
|
+
|
81
|
+
# Confirm that there are ten results in this cycle.
|
82
|
+
unless rank_count % 10 == 0
|
83
|
+
puts "WARNING: There were #{rank_count.to_s} results instead of 10 near page #{page_num} for '#{keyword}'."
|
84
|
+
end
|
85
|
+
|
86
|
+
# Get next search result page.
|
87
|
+
page_num += 1
|
88
|
+
|
89
|
+
# Add random sleep to prevent blocking of IP.
|
90
|
+
# TODO: Replace this with proxy swap.
|
91
|
+
rand(8)
|
92
|
+
|
93
|
+
page = page.link_with(:text => page_num.to_s).click
|
94
|
+
end
|
95
|
+
|
96
|
+
results
|
97
|
+
end
|
98
|
+
end
|
@@ -0,0 +1,18 @@
|
|
1
|
+
require 'minitest/spec'
|
2
|
+
require 'minitest/autorun'
|
3
|
+
require_relative '../lib/google_scraper_gem'
|
4
|
+
|
5
|
+
@@gs = GoogleScraper.new
|
6
|
+
@@results = @@gs.getTopResults('medical assistant')
|
7
|
+
|
8
|
+
describe GoogleScraper do
|
9
|
+
it "retrieves the top 10 results by default" do
|
10
|
+
@@results.count.must_equal 10
|
11
|
+
end
|
12
|
+
|
13
|
+
it "should not return results that are invalid URLs" do
|
14
|
+
@@results.each do |result|
|
15
|
+
result.wont_include "›"
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
metadata
ADDED
@@ -0,0 +1,110 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: google_scraper_gem
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Han Chang
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-08-05 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.3'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.3'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: mechanize
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: nokogiri
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: Scrapes Google Search results
|
70
|
+
email:
|
71
|
+
- szu.han.chang@gmail.com
|
72
|
+
executables: []
|
73
|
+
extensions: []
|
74
|
+
extra_rdoc_files: []
|
75
|
+
files:
|
76
|
+
- .gitignore
|
77
|
+
- Gemfile
|
78
|
+
- LICENSE.txt
|
79
|
+
- README.md
|
80
|
+
- Rakefile
|
81
|
+
- google_scraper_gem.gemspec
|
82
|
+
- lib/google_scraper_gem.rb
|
83
|
+
- lib/google_scraper_gem/version.rb
|
84
|
+
- spec/google_scraper_gem_spec.rb
|
85
|
+
homepage: ''
|
86
|
+
licenses:
|
87
|
+
- MIT
|
88
|
+
metadata: {}
|
89
|
+
post_install_message:
|
90
|
+
rdoc_options: []
|
91
|
+
require_paths:
|
92
|
+
- lib
|
93
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
94
|
+
requirements:
|
95
|
+
- - '>='
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '0'
|
98
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
99
|
+
requirements:
|
100
|
+
- - '>='
|
101
|
+
- !ruby/object:Gem::Version
|
102
|
+
version: '0'
|
103
|
+
requirements: []
|
104
|
+
rubyforge_project:
|
105
|
+
rubygems_version: 2.0.3
|
106
|
+
signing_key:
|
107
|
+
specification_version: 4
|
108
|
+
summary: Scrapes Google Search results
|
109
|
+
test_files:
|
110
|
+
- spec/google_scraper_gem_spec.rb
|