grell 1.6.9 → 1.6.10
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/.travis.yml +6 -0
- data/CHANGELOG.md +4 -0
- data/README.md +1 -1
- data/grell.gemspec +7 -5
- data/lib/grell/page.rb +6 -1
- data/lib/grell/version.rb +1 -1
- data/spec/spec_helper.rb +1 -1
- metadata +30 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 866f1b7117624455b79791bacba549710eb7dc2b
|
4
|
+
data.tar.gz: 4a3646c053bb7b4884fa8b82ebb24809d2d37f97
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: dfb07e7c0a6a7fb2fe53a40a3da248a24ba683972c696ab7064481448cb4067403dc7350d34cbba21ff4f240fb09b3571adbb36b38bfecd28aeee1ea1551638e
|
7
|
+
data.tar.gz: 7f91a206fd4cb264d73b05468dce66d858637c6d675b92088b800a85b67599201f957f879d618a0f4fc7a538de79c3211f82ffc3d73b063fec760da09209578a
|
data/.travis.yml
CHANGED
@@ -6,3 +6,9 @@ rvm:
|
|
6
6
|
- 2.2.4
|
7
7
|
- 2.3.0
|
8
8
|
script: bundle exec rspec
|
9
|
+
|
10
|
+
before_install:
|
11
|
+
- mkdir travis-phantomjs
|
12
|
+
- wget https://bitbucket.org/ariya/phantomjs/downloads/phantomjs-2.1.1-linux-x86_64.tar.bz2 -O $PWD/travis-phantomjs/phantomjs-2.1.1-linux-x86_64.tar.bz2
|
13
|
+
- tar -xvf $PWD/travis-phantomjs/phantomjs-2.1.1-linux-x86_64.tar.bz2 -C $PWD/travis-phantomjs
|
14
|
+
- export PATH=$PWD/travis-phantomjs/phantomjs-2.1.1-linux-x86_64/bin:$PATH
|
data/CHANGELOG.md
CHANGED
data/README.md
CHANGED
@@ -23,7 +23,7 @@ Or install it yourself as:
|
|
23
23
|
|
24
24
|
Grell uses PhantomJS, you will need to download and install it in your
|
25
25
|
system. Check for instructions in http://phantomjs.org/
|
26
|
-
Grell has been tested with PhantomJS
|
26
|
+
Grell has been tested with PhantomJS v2.1.x
|
27
27
|
|
28
28
|
## Usage
|
29
29
|
|
data/grell.gemspec
CHANGED
@@ -24,12 +24,14 @@ Gem::Specification.new do |spec|
|
|
24
24
|
spec.add_dependency 'capybara', '~> 2.7'
|
25
25
|
spec.add_dependency 'poltergeist', '~> 1.10'
|
26
26
|
|
27
|
-
spec.add_development_dependency
|
28
|
-
spec.add_development_dependency
|
29
|
-
spec.add_development_dependency
|
30
|
-
spec.add_development_dependency
|
31
|
-
spec.add_development_dependency
|
27
|
+
spec.add_development_dependency 'bundler', '~> 1.6'
|
28
|
+
spec.add_development_dependency 'byebug', '~> 4.0'
|
29
|
+
spec.add_development_dependency 'kender', '~> 0.2'
|
30
|
+
spec.add_development_dependency 'rake', '~> 10.0'
|
31
|
+
spec.add_development_dependency 'webmock', '~> 1.18'
|
32
32
|
spec.add_development_dependency 'rspec', '~> 3.0'
|
33
33
|
spec.add_development_dependency 'puffing-billy', '~> 0.5'
|
34
34
|
spec.add_development_dependency 'timecop', '~> 0.8'
|
35
|
+
spec.add_development_dependency 'capybara-webkit', '~> 1.11.1'
|
36
|
+
spec.add_development_dependency 'selenium-webdriver', '~> 2.53.4'
|
35
37
|
end
|
data/lib/grell/page.rb
CHANGED
@@ -206,7 +206,7 @@ module Grell
|
|
206
206
|
private
|
207
207
|
def all_links
|
208
208
|
links = @rawpage.all_anchors.map { |anchor| Link.new(anchor) }
|
209
|
-
body_enabled_links = links.reject { |link| link.inside_header? || link.disabled? }
|
209
|
+
body_enabled_links = links.reject { |link| link.inside_header? || link.disabled? || link.js_href? }
|
210
210
|
body_enabled_links.map { |link| link.to_url(host) }.uniq.compact
|
211
211
|
|
212
212
|
rescue Capybara::Poltergeist::ObsoleteNode
|
@@ -232,6 +232,11 @@ module Grell
|
|
232
232
|
@anchor.disabled? || !!@anchor.native.attributes['disabled']
|
233
233
|
end
|
234
234
|
|
235
|
+
# Does the href use javascript?
|
236
|
+
def js_href?
|
237
|
+
href.start_with?('javascript:')
|
238
|
+
end
|
239
|
+
|
235
240
|
# Some links may use data-href + javascript to do interesting things
|
236
241
|
def href
|
237
242
|
@anchor['href'] || @anchor['data-href']
|
data/lib/grell/version.rb
CHANGED
data/spec/spec_helper.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: grell
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.6.
|
4
|
+
version: 1.6.10
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jordi Polo Carres
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-07-
|
11
|
+
date: 2016-07-27 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: capybara
|
@@ -150,6 +150,34 @@ dependencies:
|
|
150
150
|
- - "~>"
|
151
151
|
- !ruby/object:Gem::Version
|
152
152
|
version: '0.8'
|
153
|
+
- !ruby/object:Gem::Dependency
|
154
|
+
name: capybara-webkit
|
155
|
+
requirement: !ruby/object:Gem::Requirement
|
156
|
+
requirements:
|
157
|
+
- - "~>"
|
158
|
+
- !ruby/object:Gem::Version
|
159
|
+
version: 1.11.1
|
160
|
+
type: :development
|
161
|
+
prerelease: false
|
162
|
+
version_requirements: !ruby/object:Gem::Requirement
|
163
|
+
requirements:
|
164
|
+
- - "~>"
|
165
|
+
- !ruby/object:Gem::Version
|
166
|
+
version: 1.11.1
|
167
|
+
- !ruby/object:Gem::Dependency
|
168
|
+
name: selenium-webdriver
|
169
|
+
requirement: !ruby/object:Gem::Requirement
|
170
|
+
requirements:
|
171
|
+
- - "~>"
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: 2.53.4
|
174
|
+
type: :development
|
175
|
+
prerelease: false
|
176
|
+
version_requirements: !ruby/object:Gem::Requirement
|
177
|
+
requirements:
|
178
|
+
- - "~>"
|
179
|
+
- !ruby/object:Gem::Version
|
180
|
+
version: 2.53.4
|
153
181
|
description: Ruby web crawler using PhantomJS
|
154
182
|
email:
|
155
183
|
- jcarres@mdsol.com
|