web_stat 0.3.7 → 0.3.12
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +1 -1
- 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 +17 -9
- 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: 2af80415014e94830b1e323f44e2e71732196bdfc535627295f1f6b7b2f44285
|
4
|
+
data.tar.gz: 85fc9facafff40063c434824ebc64fcd847f347bdfa0c928ee8c35b2b3e0c8b5
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 30870501431d61d5d90bdcfcf4f6ba339918b810fda48bd9a77abe183e341575bc9c7397aadb7494da1591d5d647fea7b17512ed24cea61471d4e112a0c17bd8
|
7
|
+
data.tar.gz: 8340739ddae12fd6a670d51e7fcd7e3987294bcb32219cde6e8dbcee2a067f064b2b632d102636471d0b7fd0ff27ca4f55c477eca94d88b7194a3cf17b1869c7
|
data/Gemfile.lock
CHANGED
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 +47,8 @@ module WebStat
|
|
47
47
|
break
|
48
48
|
end
|
49
49
|
end
|
50
|
-
if path.nil? || path.empty?
|
51
|
-
path = @nokogiri.
|
50
|
+
if (path.nil? || path.empty?) && @nokogiri.xpath('//img')
|
51
|
+
path = @nokogiri.xpath('//img').attr('src')
|
52
52
|
end
|
53
53
|
if ! path.nil? && path.match(/^\//)
|
54
54
|
"#{URI.parse(@url).scheme}://#{URI.parse(@url).host}#{path}"
|
@@ -78,17 +78,25 @@ module WebStat
|
|
78
78
|
# @param [String] url
|
79
79
|
# @param [String] body
|
80
80
|
def get_url(url)
|
81
|
-
|
81
|
+
mech = Mechanize.new { |_mech| _mech.user_agent = WebStat::Configure.get["user_agent"] }
|
82
82
|
# Enable to read Robots.txt
|
83
|
-
|
83
|
+
mech.robots = true
|
84
84
|
begin
|
85
|
-
|
86
|
-
|
87
|
-
|
85
|
+
if mech.agent.robots_disallowed?(url)
|
86
|
+
raise Mechanize::RobotsDisallowedError.new(url)
|
87
|
+
end
|
88
|
+
if WebStat::Configure.get["use_chromedirver"]
|
89
|
+
body = WebStat::WebDriverHelper.get_source(url)
|
90
|
+
@status = 200
|
88
91
|
else
|
89
|
-
|
92
|
+
document = mech.get(url, [], nil, { 'Accept-Language' => 'ja'})
|
93
|
+
if document.class == Mechanize::File
|
94
|
+
body = document.body
|
95
|
+
else
|
96
|
+
body = document.body.encode('UTF-8', document.encoding)
|
97
|
+
end
|
98
|
+
@status = document.code
|
90
99
|
end
|
91
|
-
@status = document.code
|
92
100
|
rescue Mechanize::ResponseCodeError => e
|
93
101
|
body = e.page.body
|
94
102
|
@status = e.page.code
|
@@ -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: 0.3.12
|
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
|