GDNewsScraper 3.0.0 → 3.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/GDNewsScraper/scrapers/polygon_com/news.rb +8 -8
- data/lib/GDNewsScraper/version.rb +3 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 06e468f8771feccf3609fa31369c22b865c5645b
|
4
|
+
data.tar.gz: 1936f2409c7f4c7bfb33cc58d3feaa5243e47203
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 5a90733cf5b4403b607154fcc354153ae26aa4ca9cd57334258e59a88e9ffdf7c913cc9dddb7e4e5cb643a6481cb24ad874bdb1aad91b583923a45507ffb1686
|
7
|
+
data.tar.gz: 310056309d60efe507b8e5ca92025f55945cc8dc4d17f934444f77e94281c20f129ab29242275ace4de86a0ddbd381b665ada074937c793b7dd0b0b592ff52db
|
@@ -124,7 +124,7 @@ module GDNewsScraper::Scrapers
|
|
124
124
|
article_body[:videos][iframe_id] = {}
|
125
125
|
article_body[:videos][iframe_id][:url] = iframe.attr('src')
|
126
126
|
|
127
|
-
article_body[:body] << iframe.replace("
|
127
|
+
article_body[:body] << iframe.replace("{{video:#{ iframe_id }}}").to_html
|
128
128
|
end
|
129
129
|
|
130
130
|
article_container.children.each do |node|
|
@@ -140,7 +140,7 @@ module GDNewsScraper::Scrapers
|
|
140
140
|
article_body[:videos][iframe_id] = {}
|
141
141
|
article_body[:videos][iframe_id][:url] = iframe.attr('src')
|
142
142
|
|
143
|
-
article_body[:body] << iframe.replace("
|
143
|
+
article_body[:body] << iframe.replace("{{video:#{ iframe_id }}}").to_html
|
144
144
|
end
|
145
145
|
|
146
146
|
# Check to see if the div contains a gallery
|
@@ -161,7 +161,7 @@ module GDNewsScraper::Scrapers
|
|
161
161
|
end
|
162
162
|
end
|
163
163
|
|
164
|
-
article_body[:body] << gallery.replace("
|
164
|
+
article_body[:body] << gallery.replace("{{gallery:#{ gallery_id }}}").to_html
|
165
165
|
end
|
166
166
|
|
167
167
|
twitdget = node.at('.twitter-tweet')
|
@@ -195,7 +195,7 @@ module GDNewsScraper::Scrapers
|
|
195
195
|
article_body[:images][image_id] = {}
|
196
196
|
article_body[:images][image_id][:url] = image_url
|
197
197
|
|
198
|
-
article_body[:body] << node.replace("
|
198
|
+
article_body[:body] << node.replace("{{image:#{ image_id }}}").to_html
|
199
199
|
else
|
200
200
|
image_alt = image.children.at('img').attr('alt')
|
201
201
|
image_title = image.children.at('img').attr('title')
|
@@ -215,7 +215,7 @@ module GDNewsScraper::Scrapers
|
|
215
215
|
article_body[:figures][figure_id][:cite] = image_meta.first.at('cite')&.text
|
216
216
|
end
|
217
217
|
|
218
|
-
article_body[:body] << node.replace("
|
218
|
+
article_body[:body] << node.replace("{{figure:#{ figure_id }}}").to_html
|
219
219
|
end
|
220
220
|
rescue
|
221
221
|
raise 'Unknown format, please review.'
|
@@ -227,12 +227,12 @@ module GDNewsScraper::Scrapers
|
|
227
227
|
if url.name == 'a'
|
228
228
|
url_id = random_string
|
229
229
|
|
230
|
-
article_body[:anchors][url_id
|
230
|
+
article_body[:anchors][url_id] = {
|
231
231
|
text: url.children.text,
|
232
232
|
url: url.attributes['href'].value
|
233
233
|
}
|
234
234
|
|
235
|
-
url.replace("
|
235
|
+
url.replace("{{anchor:#{ url_id }}}")
|
236
236
|
end
|
237
237
|
rescue
|
238
238
|
raise 'Unknown format, please review.'
|
@@ -262,7 +262,7 @@ module GDNewsScraper::Scrapers
|
|
262
262
|
end
|
263
263
|
|
264
264
|
def random_string
|
265
|
-
(0...50).map { (65 + rand(25)).chr }.join
|
265
|
+
(0...50).map { (65 + rand(25)).chr }.join.to_sym
|
266
266
|
end
|
267
267
|
end # News
|
268
268
|
end # PolygonCOM
|
@@ -1,5 +1,5 @@
|
|
1
1
|
module GDNewsScraper
|
2
|
-
VERSION ||= '3.0.
|
2
|
+
VERSION ||= '3.0.1'
|
3
3
|
|
4
4
|
# => major: A new Source has been added or removed
|
5
5
|
# => minor: A Source code has changed drastically to a point where it's not
|
@@ -25,4 +25,6 @@ module GDNewsScraper
|
|
25
25
|
# In a 'Wordpress' kind of style, various html elements are now
|
26
26
|
# returned in a way that an app can recognize and translate it into a
|
27
27
|
# widget
|
28
|
+
# v3.0.1 - Change the placeholder from [] to {{:}} which makes it a lot easier
|
29
|
+
# to scan and replace with Regex using scan(/\{{(.*?)\}}/)
|
28
30
|
end
|
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: 3.0.
|
4
|
+
version: 3.0.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Vlad Radulescu
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2017-11-
|
11
|
+
date: 2017-11-27 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: nokogiri
|