google_play_scraper 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/Rakefile +9 -0
- data/lib/google_play_scraper.rb +9 -0
- data/lib/google_play_scraper/app.rb +3 -0
- data/lib/google_play_scraper/parser.rb +67 -0
- data/lib/google_play_scraper/search.rb +43 -0
- data/lib/google_play_scraper/search_options.rb +9 -0
- data/lib/google_play_scraper/url.rb +3 -0
- data/lib/google_play_scraper/version.rb +3 -0
- data/spec/google_play_scraper/search_spec.rb +29 -0
- data/spec/spec_helper.rb +7 -0
- metadata +106 -0
data/Rakefile
ADDED
@@ -0,0 +1,67 @@
|
|
1
|
+
require 'nokogiri'
|
2
|
+
|
3
|
+
class GooglePlayScraper::Parser
|
4
|
+
|
5
|
+
LOGO_CSS_SELECTOR = '.card-content .cover .cover-image-container .cover-outer-align .cover-inner-align img'
|
6
|
+
|
7
|
+
attr_reader :raw_html
|
8
|
+
|
9
|
+
def initialize(raw_html)
|
10
|
+
@raw_html = raw_html
|
11
|
+
end
|
12
|
+
|
13
|
+
def results
|
14
|
+
doc = Nokogiri::HTML(raw_html)
|
15
|
+
|
16
|
+
results = []
|
17
|
+
|
18
|
+
doc.css('.card').each do |app_container|
|
19
|
+
results << create_app(app_container)
|
20
|
+
end
|
21
|
+
|
22
|
+
results
|
23
|
+
end
|
24
|
+
|
25
|
+
def create_app(app_container)
|
26
|
+
app = GooglePlayScraper::App.new
|
27
|
+
app.logo_url = extract_logo_url(app_container)
|
28
|
+
app.logo_url_small = extract_logo_url_small(app_container)
|
29
|
+
app.url = extract_app_url(app_container)
|
30
|
+
app.id = extract_app_id(app_container)
|
31
|
+
app.name = extract_app_name(app_container)
|
32
|
+
app.developer = extract_developer(app_container)
|
33
|
+
|
34
|
+
app
|
35
|
+
end
|
36
|
+
|
37
|
+
def extract_developer(app_container)
|
38
|
+
span_tag = app_container.css('.card-content .details .subtitle-container .subtitle').first
|
39
|
+
span_tag.content
|
40
|
+
end
|
41
|
+
|
42
|
+
def extract_app_name(app_container)
|
43
|
+
a_tag = app_container.css('.card-content .details a.title').first
|
44
|
+
a_tag['title']
|
45
|
+
end
|
46
|
+
|
47
|
+
def extract_app_id(app_container)
|
48
|
+
a_tag = app_container.css('.card-content a.card-click-target').first
|
49
|
+
uri = Addressable::URI.parse(a_tag['href'])
|
50
|
+
uri.query_values['id']
|
51
|
+
end
|
52
|
+
|
53
|
+
def extract_app_url(app_container)
|
54
|
+
a_tag = app_container.css('.card-content a.card-click-target').first
|
55
|
+
GooglePlayScraper::GOOGLE_PLAY_BASE_URL + a_tag['href']
|
56
|
+
end
|
57
|
+
|
58
|
+
def extract_logo_url(app_container)
|
59
|
+
img_tag = app_container.css(LOGO_CSS_SELECTOR).first
|
60
|
+
img_tag['data-cover-large']
|
61
|
+
end
|
62
|
+
|
63
|
+
def extract_logo_url_small(app_container)
|
64
|
+
img_tag = app_container.css(LOGO_CSS_SELECTOR).first
|
65
|
+
img_tag['data-cover-small']
|
66
|
+
end
|
67
|
+
end
|
@@ -0,0 +1,43 @@
|
|
1
|
+
require 'addressable/uri'
|
2
|
+
require 'net/http'
|
3
|
+
|
4
|
+
class GooglePlayScraper::Search
|
5
|
+
|
6
|
+
include GooglePlayScraper::SearchOptions
|
7
|
+
|
8
|
+
attr_reader :query, :options
|
9
|
+
|
10
|
+
GOOGLE_PLAY_SEARCH_URL = GooglePlayScraper::GOOGLE_PLAY_BASE_URL + "/store/search"
|
11
|
+
|
12
|
+
DEFAULT_OPTIONS = {
|
13
|
+
CATEGORY => 'apps',
|
14
|
+
LANGUAGE => 'en',
|
15
|
+
APPLY_SORTING => 1, # 0 means no sorting
|
16
|
+
SAFE_SEARCH => 0, # apply safesearch to results
|
17
|
+
NUMBER_OF_RESULTS => 10 # number of results to display
|
18
|
+
}
|
19
|
+
|
20
|
+
def initialize(query, options = {})
|
21
|
+
@options = DEFAULT_OPTIONS.merge(options)
|
22
|
+
@options['q'] = query
|
23
|
+
end
|
24
|
+
|
25
|
+
def run
|
26
|
+
uri = build_uri
|
27
|
+
http = Net::HTTP.new(uri.host, 443)
|
28
|
+
http.use_ssl = true
|
29
|
+
http.verify_mode = OpenSSL::SSL::VERIFY_NONE
|
30
|
+
|
31
|
+
request = Net::HTTP::Get.new(uri.request_uri)
|
32
|
+
response = http.request(request)
|
33
|
+
|
34
|
+
parser = GooglePlayScraper::Parser.new(response.body)
|
35
|
+
parser.results
|
36
|
+
end
|
37
|
+
|
38
|
+
def build_uri
|
39
|
+
uri = Addressable::URI.parse(GOOGLE_PLAY_SEARCH_URL)
|
40
|
+
uri.query_values = options
|
41
|
+
uri
|
42
|
+
end
|
43
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe GooglePlayScraper::Search do
|
4
|
+
context 'searching' do
|
5
|
+
it 'should be able to search for angry birds' do
|
6
|
+
search = GooglePlayScraper::Search.new('Angry Birds')
|
7
|
+
results = search.run
|
8
|
+
results.size.should == 10
|
9
|
+
results.first.name.should == 'Angry Birds'
|
10
|
+
results.first.developer.should == 'Rovio Mobile Ltd.'
|
11
|
+
results.first.id.should == 'com.rovio.angrybirds'
|
12
|
+
results.first.logo_url.should == 'https://lh6.ggpht.com/M9q_Zs_CRt2rbA41nTMhrPqiBxhUEUN8Z1f_mn9m89_TiHbIbUF8hjnc_zwevvLsRIJy=w340'
|
13
|
+
results.first.logo_url_small.should == 'https://lh6.ggpht.com/M9q_Zs_CRt2rbA41nTMhrPqiBxhUEUN8Z1f_mn9m89_TiHbIbUF8hjnc_zwevvLsRIJy=w170'
|
14
|
+
results.first.url.should == 'https://play.google.com/store/apps/details?id=com.rovio.angrybirds'
|
15
|
+
end
|
16
|
+
|
17
|
+
it 'should be able to search for the sparq.me scanner' do
|
18
|
+
search = GooglePlayScraper::Search.new('SPARQ.ME')
|
19
|
+
results = search.run
|
20
|
+
results.size.should == 1
|
21
|
+
results.first.name.should == 'SPARQ.ME'
|
22
|
+
results.first.developer.should == 'MSKYNET, Inc.'
|
23
|
+
results.first.id.should == 'com.sparqcode.sparqeye.android'
|
24
|
+
results.first.logo_url.should == 'https://lh3.ggpht.com/m8vHSrnD8kqMpYkgyQDxWpren2Pi5Vn-Eemj-xyHwcGUsbsi0rcYy0dR5Qzi5B566ig=w340'
|
25
|
+
results.first.logo_url_small.should == 'https://lh3.ggpht.com/m8vHSrnD8kqMpYkgyQDxWpren2Pi5Vn-Eemj-xyHwcGUsbsi0rcYy0dR5Qzi5B566ig=w170'
|
26
|
+
results.first.url.should == 'https://play.google.com/store/apps/details?id=com.sparqcode.sparqeye.android'
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,106 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: google_play_scraper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Mike Emery
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-07-16 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: nokogiri
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 1.5.0
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 1.5.0
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: addressable
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ~>
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: 2.3.0
|
38
|
+
type: :runtime
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ~>
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: 2.3.0
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: rspec
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ~>
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: 2.14.1
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 2.14.1
|
62
|
+
description: Uses Nokogiri to scrape app search results on the Google Play app search
|
63
|
+
results page. Returns results as Ruby objects
|
64
|
+
email:
|
65
|
+
- mike@sparq.it
|
66
|
+
executables: []
|
67
|
+
extensions: []
|
68
|
+
extra_rdoc_files: []
|
69
|
+
files:
|
70
|
+
- lib/google_play_scraper/app.rb
|
71
|
+
- lib/google_play_scraper/parser.rb
|
72
|
+
- lib/google_play_scraper/search.rb
|
73
|
+
- lib/google_play_scraper/search_options.rb
|
74
|
+
- lib/google_play_scraper/url.rb
|
75
|
+
- lib/google_play_scraper/version.rb
|
76
|
+
- lib/google_play_scraper.rb
|
77
|
+
- Rakefile
|
78
|
+
- spec/google_play_scraper/search_spec.rb
|
79
|
+
- spec/spec_helper.rb
|
80
|
+
homepage: ''
|
81
|
+
licenses: []
|
82
|
+
post_install_message:
|
83
|
+
rdoc_options: []
|
84
|
+
require_paths:
|
85
|
+
- lib
|
86
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
87
|
+
none: false
|
88
|
+
requirements:
|
89
|
+
- - ! '>='
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
version: '0'
|
92
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
93
|
+
none: false
|
94
|
+
requirements:
|
95
|
+
- - ! '>='
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '0'
|
98
|
+
requirements: []
|
99
|
+
rubyforge_project: google_play_scraper
|
100
|
+
rubygems_version: 1.8.25
|
101
|
+
signing_key:
|
102
|
+
specification_version: 3
|
103
|
+
summary: Get Google Play App search results from ruby by scraping their website.
|
104
|
+
test_files:
|
105
|
+
- spec/google_play_scraper/search_spec.rb
|
106
|
+
- spec/spec_helper.rb
|