GDNewsScraper 2.0.2 → 3.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/GDNewsScraper.gemspec +10 -14
- data/Gemfile +0 -7
- data/lib/GDNewsScraper/scrapers/polygon_com/news.rb +250 -53
- data/lib/GDNewsScraper/scrapers/polygon_com/reviews.rb +3 -5
- data/lib/GDNewsScraper/version.rb +13 -2
- data/lib/GDNewsScraper.rb +1 -1
- metadata +4 -59
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 300b4b0c79a91907c9031699c874cd2339dda2e7
|
4
|
+
data.tar.gz: d452da316c641f609d3cb83c5d88601d5abca271
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 7023abbec8ca015b9152737cd72385cf01aec37b2de5dc6e53b6d94ae5fd433e5c27940eaecbe37f1ceb4e6549312740a9d422fc6873144f8d877a2739d8469e
|
7
|
+
data.tar.gz: 72260107eab5febed2a934117869e815ff46cf721cc5bc7a830d4c78e754cb260aa0df173ac5349862bc44528e00c2d596b2a81ea13c734899863b32944991e9
|
data/GDNewsScraper.gemspec
CHANGED
@@ -4,27 +4,23 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
|
4
4
|
require 'GDNewsScraper/version'
|
5
5
|
|
6
6
|
Gem::Specification.new do |spec|
|
7
|
-
spec.name =
|
7
|
+
spec.name = 'GDNewsScraper'
|
8
8
|
spec.version = GDNewsScraper::VERSION
|
9
|
-
spec.authors = [
|
10
|
-
spec.email = [
|
9
|
+
spec.authors = ['Vlad Radulescu']
|
10
|
+
spec.email = ['pacMakaveli90@gmail.co.uk']
|
11
11
|
|
12
12
|
spec.summary = %q{A Ruby web scraper for gaming News and Reviews}
|
13
13
|
spec.description = %q{A Ruby Scraper created for games.directory to crawl the web for gaming News and Reviews.}
|
14
|
-
spec.homepage =
|
15
|
-
spec.license =
|
14
|
+
spec.homepage = 'https://github.com/games-directory/scraper'
|
15
|
+
spec.license = 'MIT'
|
16
16
|
|
17
17
|
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
-
spec.bindir =
|
18
|
+
spec.bindir = 'exe'
|
19
19
|
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
|
-
spec.require_paths = [
|
20
|
+
spec.require_paths = ['lib']
|
21
21
|
|
22
|
-
spec.add_dependency
|
23
|
-
spec.add_dependency "httparty"
|
24
|
-
spec.add_dependency "activesupport"
|
22
|
+
spec.add_dependency 'nokogiri'
|
25
23
|
|
26
|
-
spec.add_development_dependency
|
27
|
-
spec.add_development_dependency
|
28
|
-
spec.add_development_dependency "rspec", "~> 3.0"
|
29
|
-
spec.add_development_dependency "pry"
|
24
|
+
spec.add_development_dependency 'bundler', '~> 1.12'
|
25
|
+
spec.add_development_dependency 'rake', '~> 10.0'
|
30
26
|
end
|
data/Gemfile
CHANGED
@@ -1,72 +1,269 @@
|
|
1
|
-
require '
|
1
|
+
require 'pry'
|
2
|
+
require 'base64'
|
3
|
+
require 'json'
|
2
4
|
|
3
|
-
module GDNewsScraper
|
4
|
-
|
5
|
-
|
5
|
+
module GDNewsScraper::Scrapers
|
6
|
+
|
7
|
+
HEADERS ||= {
|
8
|
+
"User-Agent" => "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36"
|
9
|
+
}
|
6
10
|
|
7
|
-
|
8
|
-
attr_accessor :page, :articles
|
11
|
+
STREAM_URI ||= 'https://www.polygon.com'
|
9
12
|
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
+
WHITELIST ||= {
|
14
|
+
default: ['h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'figure', 'blockquote', 'ul', 'ol'],
|
15
|
+
inner: ['strong', 'em', 'li']
|
16
|
+
}
|
13
17
|
|
14
|
-
|
15
|
-
|
18
|
+
DOM = {
|
19
|
+
article: {
|
20
|
+
wrapper: '.c-compact-river',
|
21
|
+
container: '.c-compact-river__entry',
|
22
|
+
inner_container: '.c-entry-box--compact',
|
23
|
+
inner_container_video: '.c-entry-box--compact--video',
|
24
|
+
title: '.c-entry-box--compact__title',
|
25
|
+
cover: '.c-entry-box--compact__image',
|
26
|
+
meta: '.c-byline'
|
27
|
+
},
|
16
28
|
|
17
|
-
|
29
|
+
pagination: {
|
30
|
+
previous: '.c-pagination__prev',
|
31
|
+
info: '.c-pagination__text',
|
32
|
+
next: '.c-pagination__next'
|
33
|
+
}
|
34
|
+
}
|
18
35
|
|
19
|
-
|
20
|
-
|
36
|
+
module PolygonCOM
|
37
|
+
class News
|
38
|
+
attr_accessor :stream
|
21
39
|
|
22
|
-
|
23
|
-
|
24
|
-
articles[:feed][:label] = 'Polygon'
|
40
|
+
def initialize(offset = 0)
|
41
|
+
uri = "#{ STREAM_URI }/news/archives/#{ offset }"
|
25
42
|
|
26
|
-
|
43
|
+
@page ||= Nokogiri::HTML(open(uri, HEADERS))
|
44
|
+
@stream = Hash.new
|
45
|
+
|
46
|
+
stream[:stream] = Hash.new
|
47
|
+
stream[:stream][:size] = @page.css(DOM[:pagination][:info]).text.split[0].gsub(/\D/, '').to_i
|
48
|
+
stream[:stream][:pages] = @page.css(DOM[:pagination][:info]).text.split[6].gsub(/\D/, '').to_i
|
49
|
+
stream[:stream][:prev] = @page.css(DOM[:pagination][:previous])&.first&.attr('href')&.split('/')&.last.to_i
|
50
|
+
stream[:stream][:next] = @page.css(DOM[:pagination][:next])&.first&.attr('href')&.split('/')&.last.to_i
|
51
|
+
|
52
|
+
stream[:feed] = Hash.new
|
53
|
+
stream[:feed][:url] = STREAM_URI
|
54
|
+
stream[:feed][:source] = 'polygon'
|
55
|
+
stream[:feed][:label] = 'Polygon'
|
56
|
+
|
57
|
+
stream[:articles] = Array.new
|
58
|
+
|
59
|
+
perform
|
60
|
+
rescue
|
61
|
+
return 'There was a problem initializing the PolygonCOM::News Service'
|
62
|
+
end
|
63
|
+
|
64
|
+
def perform
|
65
|
+
@page.css(DOM[:article][:container]).each do |article|
|
66
|
+
stream[:articles] << parse(article)
|
67
|
+
end
|
68
|
+
rescue
|
69
|
+
return 'There was a problem performing the initial task in the PolygonCOM::News Service'
|
70
|
+
end
|
71
|
+
|
72
|
+
def parse(article)
|
73
|
+
pulse = Hash.new
|
74
|
+
|
75
|
+
is_a_video = !article.at(DOM[:article][:inner_container_video]).nil?
|
76
|
+
|
77
|
+
key = article.css(DOM[:article][:inner_container]).first.attr('data-chorus-optimize-id').to_i
|
78
|
+
url = article.css(DOM[:article][:title]).children.first.attr('href')
|
79
|
+
title = article.css(DOM[:article][:title]).children.first.text
|
80
|
+
|
81
|
+
pulse[:id] = key
|
82
|
+
pulse[:hash] = ::Base64.encode64("#{ title } - #{ key }")
|
83
|
+
|
84
|
+
begin
|
85
|
+
pulse[:cover] = article.children.css(DOM[:article][:cover]).children.children.first.attr('src')
|
86
|
+
rescue
|
87
|
+
pulse[:cover] = nil
|
88
|
+
end
|
89
|
+
|
90
|
+
pulse[:url] = url
|
91
|
+
pulse[:title] = title
|
92
|
+
pulse[:author] = article.css(DOM[:article][:meta]).first.children[1].children[1].text
|
93
|
+
pulse[:date] = JSON.parse(article.css(DOM[:article][:meta]).first.attr('data-cdata'))['timestamp'].to_i
|
94
|
+
pulse[:content] = parse_article_body(url, is_a_video)
|
95
|
+
pulse[:tags] = title.downcase.split
|
96
|
+
|
97
|
+
|
98
|
+
return pulse
|
99
|
+
rescue
|
100
|
+
return 'There was a problem creating the article in the PolygonCOM::News Service'
|
101
|
+
end
|
102
|
+
|
103
|
+
private
|
104
|
+
|
105
|
+
def parse_article_body(article_url, is_a_video = false)
|
106
|
+
article_page = Nokogiri::HTML(open(article_url, HEADERS))
|
107
|
+
article_container = article_page.css('.c-entry-content')
|
108
|
+
|
109
|
+
article_body = {
|
110
|
+
galleries: { },
|
111
|
+
videos: { },
|
112
|
+
images: { },
|
113
|
+
|
114
|
+
anchors: { },
|
115
|
+
figures: { },
|
116
|
+
|
117
|
+
body: [ ]
|
118
|
+
}
|
119
|
+
|
120
|
+
if is_a_video
|
121
|
+
iframe = article_page.at('.c-video-embed--media').at('iframe')
|
122
|
+
iframe_id = random_string
|
123
|
+
|
124
|
+
article_body[:videos][iframe_id] = {}
|
125
|
+
article_body[:videos][iframe_id][:url] = iframe.attr('src')
|
126
|
+
|
127
|
+
article_body[:body] << iframe.replace("[video]#{ iframe_id }").to_html
|
27
128
|
end
|
28
129
|
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
130
|
+
article_container.children.each do |node|
|
131
|
+
if node.name == 'div'
|
132
|
+
|
133
|
+
# Check to see if the div contains a embeded video
|
134
|
+
#
|
135
|
+
iframe = node.at('iframe')
|
136
|
+
|
137
|
+
if iframe # YouTube videos
|
138
|
+
iframe_id = random_string
|
139
|
+
|
140
|
+
article_body[:videos][iframe_id] = {}
|
141
|
+
article_body[:videos][iframe_id][:url] = iframe.attr('src')
|
142
|
+
|
143
|
+
article_body[:body] << iframe.replace("[video]#{ iframe_id }").to_html
|
144
|
+
end
|
145
|
+
|
146
|
+
# Check to see if the div contains a gallery
|
147
|
+
#
|
148
|
+
gallery = node.at('.c-image-gallery')
|
149
|
+
|
150
|
+
if gallery
|
151
|
+
gallery_container = gallery.at('.c-image-gallery__thumbs-viewport')
|
152
|
+
|
153
|
+
gallery_id = random_string
|
154
|
+
article_body[:galleries][gallery_id] = []
|
155
|
+
|
156
|
+
gallery_container.children.children.each do |image_container|
|
157
|
+
image = image_container.at('a')
|
158
|
+
|
159
|
+
if image
|
160
|
+
article_body[:galleries][gallery_id] << image.attr('href')
|
161
|
+
end
|
53
162
|
end
|
54
|
-
|
55
|
-
|
163
|
+
|
164
|
+
article_body[:body] << gallery.replace("[gallery]#{ gallery_id }").to_html
|
165
|
+
end
|
166
|
+
|
167
|
+
twitdget = node.at('.twitter-tweet')
|
168
|
+
|
169
|
+
if twitdget
|
170
|
+
article_body[:body] << twitdget.to_html
|
56
171
|
end
|
57
172
|
end
|
58
173
|
|
59
|
-
|
60
|
-
|
174
|
+
# First ensure the node is an actual element. This removes random HTML elements
|
175
|
+
#
|
176
|
+
# => node.element?
|
177
|
+
#
|
178
|
+
# Secondly, ensure the node is what we actual want. We don't want <div>'s
|
179
|
+
# which are usualy used for placing inline advertisments or content specific
|
180
|
+
# only to that website
|
181
|
+
#
|
182
|
+
# => WHITELIST[:default].include?(node.name)
|
183
|
+
#
|
184
|
+
if node.element? && WHITELIST[:default].include?(node.name)
|
185
|
+
case node.name
|
186
|
+
when 'figure'
|
187
|
+
|
188
|
+
image = node.css('.e-image__image').first
|
189
|
+
image_url = image.attr('data-original')
|
190
|
+
|
191
|
+
begin
|
192
|
+
if image_url.split('.').last == 'gif'
|
193
|
+
image_id = random_string
|
194
|
+
|
195
|
+
article_body[:images][image_id] = {}
|
196
|
+
article_body[:images][image_id][:url] = image_url
|
197
|
+
|
198
|
+
article_body[:body] << node.replace("[image]#{ image_id }").to_html
|
199
|
+
else
|
200
|
+
image_alt = image.children.at('img').attr('alt')
|
201
|
+
image_title = image.children.at('img').attr('title')
|
61
202
|
|
62
|
-
|
203
|
+
image_meta = node.css('.e-image__meta')
|
63
204
|
|
64
|
-
|
65
|
-
|
205
|
+
figure_id = random_string
|
206
|
+
|
207
|
+
article_body[:figures][figure_id] = {}
|
208
|
+
|
209
|
+
article_body[:figures][figure_id][:image] = image_url
|
210
|
+
article_body[:figures][figure_id][:title] = image_title
|
211
|
+
article_body[:figures][figure_id][:alt] = image_alt
|
212
|
+
|
213
|
+
unless image_meta.empty?
|
214
|
+
article_body[:figures][figure_id][:caption] = image_meta.first.at('figcaption')&.text
|
215
|
+
article_body[:figures][figure_id][:cite] = image_meta.first.at('cite')&.text
|
216
|
+
end
|
217
|
+
|
218
|
+
article_body[:body] << node.replace("[figure]#{ figure_id }").to_html
|
219
|
+
end
|
220
|
+
rescue
|
221
|
+
raise 'Unknown format, please review.'
|
222
|
+
end
|
223
|
+
else
|
224
|
+
|
225
|
+
node.children.each do |url|
|
226
|
+
begin
|
227
|
+
if url.name == 'a'
|
228
|
+
url_id = random_string
|
229
|
+
|
230
|
+
article_body[:anchors][url_id.to_sym] = {
|
231
|
+
text: url.children.text,
|
232
|
+
url: url.attributes['href'].value
|
233
|
+
}
|
234
|
+
|
235
|
+
url.replace("[anchor]#{ url_id }")
|
236
|
+
end
|
237
|
+
rescue
|
238
|
+
raise 'Unknown format, please review.'
|
239
|
+
end
|
240
|
+
end
|
241
|
+
|
242
|
+
# Remove all attributes
|
243
|
+
#
|
244
|
+
parsed_node = node.xpath('.//@*').remove
|
245
|
+
|
246
|
+
# Return clean HTML, including HTML elements and text
|
247
|
+
#
|
248
|
+
parsed_node = node.to_html
|
249
|
+
end
|
250
|
+
|
251
|
+
article_body[:body] << parsed_node
|
252
|
+
end
|
66
253
|
end
|
67
254
|
|
68
|
-
|
255
|
+
return article_body
|
256
|
+
rescue
|
257
|
+
return 'There was a problem parsing the article body in the PolygonCOM::News Service'
|
258
|
+
end
|
259
|
+
|
260
|
+
def attr(attribute)
|
261
|
+
attributes&.fetch(attribute, nil)&.value
|
262
|
+
end
|
69
263
|
|
70
|
-
|
71
|
-
|
72
|
-
end
|
264
|
+
def random_string
|
265
|
+
(0...50).map { (65 + rand(25)).chr }.join
|
266
|
+
end
|
267
|
+
end # News
|
268
|
+
end # PolygonCOM
|
269
|
+
end # GDNewsScraper::Scrapers
|
@@ -1,5 +1,3 @@
|
|
1
|
-
require 'active_support/hash_with_indifferent_access'
|
2
|
-
|
3
1
|
module GDNewsScraper
|
4
2
|
module Scrapers
|
5
3
|
module PolygonCOM
|
@@ -12,7 +10,7 @@ module GDNewsScraper
|
|
12
10
|
uri = "https://www.polygon.com/games/reviewed/#{offset}"
|
13
11
|
|
14
12
|
@page ||= Nokogiri::HTML(HTTParty.get(uri, headers: headers))
|
15
|
-
@articles =
|
13
|
+
@articles = Hash.new
|
16
14
|
|
17
15
|
pagination = container.css('.pagination').children[3].children.text.split
|
18
16
|
|
@@ -20,7 +18,7 @@ module GDNewsScraper
|
|
20
18
|
articles[:offset] = pagination[3].to_i
|
21
19
|
articles[:total] = get_all_reviews.size
|
22
20
|
|
23
|
-
articles[:feed] =
|
21
|
+
articles[:feed] = Hash.new
|
24
22
|
articles[:feed][:source] = 'polygon'
|
25
23
|
articles[:feed][:label] = 'Polygon'
|
26
24
|
|
@@ -28,7 +26,7 @@ module GDNewsScraper
|
|
28
26
|
end
|
29
27
|
|
30
28
|
def get_all_reviews
|
31
|
-
reviews =
|
29
|
+
reviews = Hash.new
|
32
30
|
|
33
31
|
page.css('.m-game--index__list').children.each do |review|
|
34
32
|
|
@@ -1,6 +1,12 @@
|
|
1
1
|
module GDNewsScraper
|
2
|
-
VERSION
|
2
|
+
VERSION ||= '3.0.0'
|
3
3
|
|
4
|
+
# => major: A new Source has been added or removed
|
5
|
+
# => minor: A Source code has changed drastically to a point where it's not
|
6
|
+
# backwards compatible anymore
|
7
|
+
# => patch: Small addition to an existing Source. The new code shouldn't break
|
8
|
+
# any existing implementation. If it does, it needs backwards compatibility
|
9
|
+
#
|
4
10
|
# CHANGELOG
|
5
11
|
#
|
6
12
|
# v1.0.0 - Initial Gem Setup
|
@@ -13,5 +19,10 @@ module GDNewsScraper
|
|
13
19
|
# would cause the script to fail when requesting the photo for the
|
14
20
|
# Article
|
15
21
|
# v2.0.2 - Fix minor bug in PolygonCOM News scraper
|
16
|
-
|
22
|
+
# v2.1.0 - Updated PolygonCOM to reflect their new UI changes
|
23
|
+
# v2.1.1 - Fixed PolygonCOM Scraper to include videos if there are any
|
24
|
+
# v3.0.0 - Major overhaul to how an Article is parsed and returned to the User
|
25
|
+
# In a 'Wordpress' kind of style, various html elements are now
|
26
|
+
# returned in a way that an app can recognize and translate it into a
|
27
|
+
# widget
|
17
28
|
end
|
data/lib/GDNewsScraper.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: GDNewsScraper
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version:
|
4
|
+
version: 3.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Vlad Radulescu
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2017-11-26 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|
@@ -24,34 +24,6 @@ dependencies:
|
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
|
-
- !ruby/object:Gem::Dependency
|
28
|
-
name: httparty
|
29
|
-
requirement: !ruby/object:Gem::Requirement
|
30
|
-
requirements:
|
31
|
-
- - ">="
|
32
|
-
- !ruby/object:Gem::Version
|
33
|
-
version: '0'
|
34
|
-
type: :runtime
|
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: activesupport
|
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
27
|
- !ruby/object:Gem::Dependency
|
56
28
|
name: bundler
|
57
29
|
requirement: !ruby/object:Gem::Requirement
|
@@ -80,34 +52,6 @@ dependencies:
|
|
80
52
|
- - "~>"
|
81
53
|
- !ruby/object:Gem::Version
|
82
54
|
version: '10.0'
|
83
|
-
- !ruby/object:Gem::Dependency
|
84
|
-
name: rspec
|
85
|
-
requirement: !ruby/object:Gem::Requirement
|
86
|
-
requirements:
|
87
|
-
- - "~>"
|
88
|
-
- !ruby/object:Gem::Version
|
89
|
-
version: '3.0'
|
90
|
-
type: :development
|
91
|
-
prerelease: false
|
92
|
-
version_requirements: !ruby/object:Gem::Requirement
|
93
|
-
requirements:
|
94
|
-
- - "~>"
|
95
|
-
- !ruby/object:Gem::Version
|
96
|
-
version: '3.0'
|
97
|
-
- !ruby/object:Gem::Dependency
|
98
|
-
name: pry
|
99
|
-
requirement: !ruby/object:Gem::Requirement
|
100
|
-
requirements:
|
101
|
-
- - ">="
|
102
|
-
- !ruby/object:Gem::Version
|
103
|
-
version: '0'
|
104
|
-
type: :development
|
105
|
-
prerelease: false
|
106
|
-
version_requirements: !ruby/object:Gem::Requirement
|
107
|
-
requirements:
|
108
|
-
- - ">="
|
109
|
-
- !ruby/object:Gem::Version
|
110
|
-
version: '0'
|
111
55
|
description: A Ruby Scraper created for games.directory to crawl the web for gaming
|
112
56
|
News and Reviews.
|
113
57
|
email:
|
@@ -151,8 +95,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
151
95
|
version: '0'
|
152
96
|
requirements: []
|
153
97
|
rubyforge_project:
|
154
|
-
rubygems_version: 2.
|
98
|
+
rubygems_version: 2.6.12
|
155
99
|
signing_key:
|
156
100
|
specification_version: 4
|
157
101
|
summary: A Ruby web scraper for gaming News and Reviews
|
158
102
|
test_files: []
|
103
|
+
has_rdoc:
|