web_stat 0.3.8 → 0.3.13
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/Gemfile.lock +2 -2
- data/README.md +4 -6
- data/lib/helpers/web_drive_helper.rb +21 -5
- data/lib/web_stat/configure.rb +1 -1
- data/lib/web_stat/fetch.rb +7 -3
- data/lib/web_stat/final_redirect_url.rb +1 -1
- data/lib/web_stat/version.rb +1 -1
- data/spec/spec_helper.rb +1 -6
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 6021c6bacb394385b1e5634449f4a3adfb27a5c2d799f9d0874084889a3ac66c
|
4
|
+
data.tar.gz: d35180f95d0937b69df93dc5ba051edb8eeb79b52bd6df0e8770c849bc33c511
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 812aa33c7a4d8642b1239d05b8a0f2fa6bc938379f48e998732d71dcdd40c5c15d04b2795dde6b7e9cee0f439a12ad5b7259bc58fe741076106108bbc6c16d90
|
7
|
+
data.tar.gz: 3bf21e030a43868ccee4c45fe1e8993c6375b85f05d74ec3b11d68b97fe10a09194e186cfd942c3fe03f9ad2ce009e5ed15edefb06d21830180f9b04bd2fd8ea
|
data/Gemfile.lock
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
web_stat (0.3.
|
4
|
+
web_stat (0.3.12)
|
5
5
|
bundler (>= 2.0.2)
|
6
6
|
cld (>= 0.8.0)
|
7
7
|
mechanize (>= 2.7)
|
@@ -83,7 +83,7 @@ GEM
|
|
83
83
|
nokogiri (>= 1.6.0)
|
84
84
|
rubyzip (2.3.0)
|
85
85
|
safe_yaml (1.0.5)
|
86
|
-
sanitize (5.2.
|
86
|
+
sanitize (5.2.0)
|
87
87
|
crass (~> 1.0.2)
|
88
88
|
nokogiri (>= 1.8.0)
|
89
89
|
nokogumbo (~> 2.0)
|
data/README.md
CHANGED
@@ -55,12 +55,10 @@ And then execute:
|
|
55
55
|
|
56
56
|
### spec
|
57
57
|
|
58
|
-
$
|
59
|
-
|
60
|
-
or
|
61
|
-
|
62
|
-
$ bundle exec rspec
|
58
|
+
$ docker/start -d
|
59
|
+
$ docker/exec ENV=development bundle exec rspec
|
63
60
|
|
64
61
|
Test a file
|
65
62
|
|
66
|
-
$
|
63
|
+
$ docker/start -d
|
64
|
+
$ docker/exec ENV=development bundle exec rspec spec/web_stat/fetch_spec.rb
|
@@ -5,14 +5,29 @@ module WebStat
|
|
5
5
|
# @param [String] url
|
6
6
|
# @param [Integer] delay
|
7
7
|
def get_last_url(url, delay=nil)
|
8
|
+
driver = get_driver(url, delay)
|
9
|
+
last_url = driver.current_url
|
10
|
+
driver.quit
|
11
|
+
last_url
|
12
|
+
end
|
13
|
+
# Get source of html
|
14
|
+
# @param [String] url
|
15
|
+
# @param [Integer] delay
|
16
|
+
def get_source(url, delay=nil)
|
17
|
+
driver = get_driver(url, delay)
|
18
|
+
source = driver.page_source
|
19
|
+
driver.quit
|
20
|
+
source
|
21
|
+
end
|
22
|
+
|
23
|
+
private
|
24
|
+
def get_driver(url, delay=nil)
|
8
25
|
Selenium::WebDriver.logger.output = File.join("/tmp", "selenium.log")
|
9
26
|
Selenium::WebDriver.logger.level = :info
|
10
27
|
options = Selenium::WebDriver::Chrome::Options.new(args: [
|
11
28
|
'headless',
|
12
29
|
'no-sandbox',
|
13
|
-
'disable-gpu'
|
14
|
-
'start-maximized',
|
15
|
-
'window-size=1920,1080'
|
30
|
+
'disable-gpu'
|
16
31
|
])
|
17
32
|
driver = Selenium::WebDriver.for(:chrome, options: options)
|
18
33
|
driver.manage.timeouts.implicit_wait = 10
|
@@ -21,9 +36,10 @@ module WebStat
|
|
21
36
|
if delay.is_a?(Integer)
|
22
37
|
sleep delay
|
23
38
|
end
|
24
|
-
|
39
|
+
driver
|
40
|
+
rescue => e
|
25
41
|
driver.quit
|
26
|
-
|
42
|
+
raise e
|
27
43
|
end
|
28
44
|
end
|
29
45
|
end
|
data/lib/web_stat/configure.rb
CHANGED
data/lib/web_stat/fetch.rb
CHANGED
@@ -47,8 +47,12 @@ module WebStat
|
|
47
47
|
break
|
48
48
|
end
|
49
49
|
end
|
50
|
-
|
51
|
-
|
50
|
+
readability_content = Readability::Document.new(@nokogiri.at('body')).content
|
51
|
+
if (path.nil? || path.empty?) && readability_content.xpath('//img').first
|
52
|
+
path = ::Nokogiri::HTML(readability_content).xpath('//img').first.attr('src')
|
53
|
+
end
|
54
|
+
if (path.nil? || path.empty?) && @nokogiri.xpath('//img').first
|
55
|
+
path = @nokogiri.xpath('//img').first.attr('src')
|
52
56
|
end
|
53
57
|
if ! path.nil? && path.match(/^\//)
|
54
58
|
"#{URI.parse(@url).scheme}://#{URI.parse(@url).host}#{path}"
|
@@ -86,7 +90,7 @@ module WebStat
|
|
86
90
|
raise Mechanize::RobotsDisallowedError.new(url)
|
87
91
|
end
|
88
92
|
if WebStat::Configure.get["use_chromedirver"]
|
89
|
-
|
93
|
+
body = WebStat::WebDriverHelper.get_source(url)
|
90
94
|
@status = 200
|
91
95
|
else
|
92
96
|
document = mech.get(url, [], nil, { 'Accept-Language' => 'ja'})
|
@@ -11,7 +11,7 @@ module WebStat
|
|
11
11
|
redirect_lookup_depth = options[:depth].to_i > 0 ? options[:depth].to_i : 10
|
12
12
|
response_uri = get_final_redirect_url(url, redirect_lookup_depth)
|
13
13
|
final_url = url_string_from_uri(response_uri)
|
14
|
-
rescue
|
14
|
+
rescue => e
|
15
15
|
# nothing
|
16
16
|
end
|
17
17
|
end
|
data/lib/web_stat/version.rb
CHANGED
data/spec/spec_helper.rb
CHANGED
@@ -7,12 +7,7 @@ require "web_stat"
|
|
7
7
|
require 'webmock'
|
8
8
|
include WebMock::API
|
9
9
|
WebMock.enable!
|
10
|
-
|
11
|
-
WebMock.disable_net_connect!({
|
12
|
-
allow_localhost: true,
|
13
|
-
allow: 'chromedriver.storage.googleapis.com'
|
14
|
-
})
|
15
|
-
|
10
|
+
|
16
11
|
RSpec.configure do |config|
|
17
12
|
# Enable flags like --only-failures and --next-failure
|
18
13
|
config.example_status_persistence_file_path = ".rspec_status"
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: web_stat
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.3.
|
4
|
+
version: 0.3.13
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- yusuke abe
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-06-
|
11
|
+
date: 2020-06-21 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|