web_stat 0.3.3 → 0.3.8
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/lib/web_stat/fetch.rb +20 -9
- data/lib/web_stat/version.rb +1 -1
- 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: bbf065f5482ee7bf68e14e41af1e48b855f4219b9f44a7e16440834c92f404d5
|
4
|
+
data.tar.gz: a16fc8b8a66cb534bb8ce61c6da28212faff44f2df6324772261f9b6847cfc7f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 83b8b7d71a1047ec2614a9bfbc3c6305806cf7a616ba6b2568382b72ef91f5b0947e7aefb3d926b33c4970d291d2a34c99a86ba0f0e320a3e7fde9dd2b5bc154
|
7
|
+
data.tar.gz: aa4af6063d7dd81c7c78c0100ff5354d7c54f28d7b2fac7393656cb5bde932b7260c95d1fe08fc560784e85ead7bbf49134c4d56cb108cef522cef753e477032
|
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 (0.3.7)
|
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 (5.2.1)
|
87
87
|
crass (~> 1.0.2)
|
88
88
|
nokogiri (>= 1.8.0)
|
89
89
|
nokogumbo (~> 2.0)
|
data/lib/web_stat/fetch.rb
CHANGED
@@ -47,6 +47,9 @@ module WebStat
|
|
47
47
|
break
|
48
48
|
end
|
49
49
|
end
|
50
|
+
if path.nil? || path.empty? || @nokogiri.at('body').xpath('//img').first
|
51
|
+
path = @nokogiri.at('body').xpath('//img').first.attr('src')
|
52
|
+
end
|
50
53
|
if ! path.nil? && path.match(/^\//)
|
51
54
|
"#{URI.parse(@url).scheme}://#{URI.parse(@url).host}#{path}"
|
52
55
|
else
|
@@ -57,7 +60,7 @@ module WebStat
|
|
57
60
|
# Get local path to save url
|
58
61
|
# @param [String] url
|
59
62
|
def save_local_path(url)
|
60
|
-
return nil if url.nil?
|
63
|
+
return nil if url.nil? || ! url.match(%{^http})
|
61
64
|
tmp_file = "/tmp/#{Digest::SHA1.hexdigest(url)}"
|
62
65
|
agent = Mechanize.new { |_agent| _agent.user_agent = WebStat::Configure.get["user_agent"] }
|
63
66
|
image = agent.get(url)
|
@@ -75,17 +78,25 @@ module WebStat
|
|
75
78
|
# @param [String] url
|
76
79
|
# @param [String] body
|
77
80
|
def get_url(url)
|
78
|
-
|
81
|
+
mech = Mechanize.new { |_mech| _mech.user_agent = WebStat::Configure.get["user_agent"] }
|
79
82
|
# Enable to read Robots.txt
|
80
|
-
|
83
|
+
mech.robots = true
|
81
84
|
begin
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
+
if mech.agent.robots_disallowed?(url)
|
86
|
+
raise Mechanize::RobotsDisallowedError.new(url)
|
87
|
+
end
|
88
|
+
if WebStat::Configure.get["use_chromedirver"]
|
89
|
+
document = WebStat::WebDriverHelper.get_last_url(url)
|
90
|
+
@status = 200
|
85
91
|
else
|
86
|
-
|
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
|
87
99
|
end
|
88
|
-
@status = document.code
|
89
100
|
rescue Mechanize::ResponseCodeError => e
|
90
101
|
body = e.page.body
|
91
102
|
@status = e.page.code
|
@@ -96,7 +107,7 @@ module WebStat
|
|
96
107
|
# Get the informations of @url
|
97
108
|
# @param [Hash] Specify a dictionary for each language code. example ) {"ja": /***/**.dic, "other": /***/***.dic}
|
98
109
|
def stat(userdics: nil)
|
99
|
-
clean_content = content.scrub('').gsub(/[\n\t\r ]/, "").gsub(/\s{2,}/, "\s")
|
110
|
+
clean_content = content.scrub('').gsub(/[\n\t\r ]/, "").gsub(/\s{2,}/, "\s").gsub(URI.regexp, "")
|
100
111
|
language_code = CLD.detect_language(clean_content)[:code]
|
101
112
|
if userdics && userdics.has_key?(language_code) && File.exists?(userdics[language_code])
|
102
113
|
tag = WebStat::Tag.new("#{title} #{content}", userdic: userdics[language_code])
|
data/lib/web_stat/version.rb
CHANGED
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: 0.3.8
|
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: 2020-06-17 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|