scraper_google_play 0.1.6 → 0.1.9
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 +4 -4
- data/Rakefile +1 -1
- data/lib/scraper_google_play.rb +4 -1
- data/lib/scraper_google_play/reviews.rb +83 -0
- data/lib/scraper_google_play/version.rb +1 -1
- metadata +4 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 579efb7a514a57f6a7995602b8ffb50a8188fcd0
|
4
|
+
data.tar.gz: a181c2fb6750f8c2e03b7e73d8411b15bbaf6997
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 585bcaddf706850bc881d8534fa96f44171f9e5e946949fd449aa5ff38e8a2c01cbefc63b2bf7c0a971bdd1a3607e42504b474244d8b5cf38834352af41f0744
|
7
|
+
data.tar.gz: 94137e754a57d1c138c35211419e618a21da04691043ab4b702698b7d2e2fc23db8ea21ee2649c9d85af4551840339bd347a388a607a110faf9a514fa5f46dc1
|
data/Rakefile
CHANGED
@@ -1,2 +1,2 @@
|
|
1
1
|
require "bundler/gem_tasks"
|
2
|
-
task :default => :spec
|
2
|
+
task :default => :spec
|
data/lib/scraper_google_play.rb
CHANGED
@@ -3,11 +3,14 @@ module ScraperGooglePlay
|
|
3
3
|
APPURL = "https://play.google.com/store/apps/details"
|
4
4
|
CATEGORYURL = "https://play.google.com/store/apps/category/"
|
5
5
|
SEARCHURL = "https://play.google.com/store/search"
|
6
|
+
REVIEWSURL = "https://play.google.com/store/getreviews"
|
7
|
+
|
6
8
|
end
|
7
9
|
|
8
10
|
require 'mechanize' # and any other gems you need
|
9
11
|
require 'active_support/all'
|
10
12
|
require 'scraper_google_play/base'
|
11
13
|
require 'scraper_google_play/app'
|
14
|
+
require 'scraper_google_play/reviews'
|
12
15
|
require 'scraper_google_play/category'
|
13
|
-
require 'scraper_google_play/search'
|
16
|
+
require 'scraper_google_play/search'
|
@@ -0,0 +1,83 @@
|
|
1
|
+
class ScraperGooglePlay::Reviews < ScraperGooglePlay::Base
|
2
|
+
attr_accessor :package_name
|
3
|
+
|
4
|
+
def initialize(package_name, options = {})
|
5
|
+
@package_name = package_name
|
6
|
+
@agent = Mechanize.new
|
7
|
+
@agent.user_agent_alias = 'Linux Firefox'
|
8
|
+
@agent.log = Logger.new(STDOUT)
|
9
|
+
|
10
|
+
@data = {
|
11
|
+
:pageNum => options[:page] || 0,
|
12
|
+
:id => package_name || options[:id],
|
13
|
+
:reviewSortOrder => options[:sort] || 0,
|
14
|
+
:hl => options[:lang] || 'en',
|
15
|
+
:reviewType => 0,
|
16
|
+
:xhr => 1
|
17
|
+
}
|
18
|
+
end
|
19
|
+
|
20
|
+
def fetch_reviews
|
21
|
+
@reviews ||= result
|
22
|
+
end
|
23
|
+
|
24
|
+
def result
|
25
|
+
@page = @agent.post(
|
26
|
+
"#{ScraperGooglePlay::REVIEWSURL}",
|
27
|
+
@data,
|
28
|
+
{
|
29
|
+
'Content-Type' => 'application/x-www-form-urlencoded;charset=UTF-8',
|
30
|
+
}
|
31
|
+
)
|
32
|
+
data = JSON.parse @page.body[6..-1]
|
33
|
+
@page = Nokogiri::HTML(data[0][2])
|
34
|
+
|
35
|
+
parse_fields
|
36
|
+
while (@page.search('.single-review').count >= 40) do
|
37
|
+
@data[:pageNum] += 1
|
38
|
+
result
|
39
|
+
end
|
40
|
+
@reviews
|
41
|
+
end
|
42
|
+
|
43
|
+
def parse_fields
|
44
|
+
@reviews ||= []
|
45
|
+
@page.search('.single-review').each do |elm_review|
|
46
|
+
review = {
|
47
|
+
id: elm_review.at('.review-header').attr('data-reviewid').strip(),
|
48
|
+
info: elm_review.at('.review-info').text,
|
49
|
+
userName: elm_review.at('.author-name').text(),
|
50
|
+
userImage: getUserImage(elm_review),
|
51
|
+
date: elm_review.at('span.review-date').text().strip(),
|
52
|
+
score: getScore(elm_review),
|
53
|
+
reviewContent: elm_review.at('.review-body').text.gsub(' Full Review ', ''),
|
54
|
+
title: elm_review.at('span.review-title').text,
|
55
|
+
text: elm_review.at('.review-body').text.gsub(' Full Review ', ''),
|
56
|
+
}
|
57
|
+
@reviews << review
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def getUserImage elm_review
|
62
|
+
nil
|
63
|
+
end
|
64
|
+
|
65
|
+
def getScore elm_review
|
66
|
+
start_rating = elm_review.at('.review-info .current-rating').attributes["style"].text
|
67
|
+
case start_rating
|
68
|
+
when "width: 100%;"
|
69
|
+
5
|
70
|
+
when "width: 80%;"
|
71
|
+
4
|
72
|
+
when "width: 60%;"
|
73
|
+
3
|
74
|
+
when "width: 40%;"
|
75
|
+
2
|
76
|
+
when "width: 20%;"
|
77
|
+
1
|
78
|
+
else
|
79
|
+
0
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: scraper_google_play
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.9
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Nguyen Bach
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-06-
|
11
|
+
date: 2017-06-10 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -83,6 +83,7 @@ files:
|
|
83
83
|
- lib/scraper_google_play/app.rb
|
84
84
|
- lib/scraper_google_play/base.rb
|
85
85
|
- lib/scraper_google_play/category.rb
|
86
|
+
- lib/scraper_google_play/reviews.rb
|
86
87
|
- lib/scraper_google_play/search.rb
|
87
88
|
- lib/scraper_google_play/version.rb
|
88
89
|
- scraper_google_play-0.1.0.gem
|
@@ -106,7 +107,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
106
107
|
version: '0'
|
107
108
|
requirements: []
|
108
109
|
rubyforge_project:
|
109
|
-
rubygems_version: 2.
|
110
|
+
rubygems_version: 2.6.11
|
110
111
|
signing_key:
|
111
112
|
specification_version: 4
|
112
113
|
summary: Write a short summary, because Rubygems requires one.
|