web_stat 0.1.12 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +1 -1
- data/Gemfile.lock +34 -31
- data/README.md +2 -2
- data/lib/web_stat/fetch.rb +3 -8
- data/lib/web_stat/version.rb +1 -1
- data/lib/web_stat.rb +10 -0
- data/spec/web_stat/fetch_spec.rb +8 -0
- data/web_stat.gemspec +11 -10
- metadata +35 -21
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 89fb8389fb61745427075c700e9ba094ed2fbfe78f22e6f9364d836472ba8334
|
4
|
+
data.tar.gz: 2f07517f36832489f2bd72f259d93d1ee60bab29247e4fd88990a29ee1d3f912
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 56e2f7e8ed3ad8e44100f5ac767206cbdfda1e8cac431813a005998823acbca4060d441ddf723dd17b46fbfbbd37fd9700f3e459ed99fe3e73eaadb42ca2c6d0
|
7
|
+
data.tar.gz: 64923ad006daa2db6cd196d2c6f3256b011673d48fc74eb315556aebea950550c7c1dc6c123c97b4fd55ef4ae2a1d3714ce93b62d34b8f61d16346dc9a1f870e
|
data/.gitignore
CHANGED
data/Gemfile.lock
CHANGED
@@ -1,29 +1,32 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
web_stat (0.
|
4
|
+
web_stat (0.2.0)
|
5
5
|
bundler (>= 2.0.2)
|
6
|
-
|
7
|
-
|
8
|
-
|
6
|
+
cld (>= 0.8.0)
|
7
|
+
final_redirect_url (>= 0.1.0)
|
8
|
+
mechanize (>= 2.7)
|
9
|
+
natto (>= 1.1.2)
|
9
10
|
nokogiri (>= 1.10.4)
|
10
|
-
ruby-readability (
|
11
|
-
sanitize (
|
11
|
+
ruby-readability (>= 0.7)
|
12
|
+
sanitize (>= 5.0.0)
|
12
13
|
|
13
14
|
GEM
|
14
15
|
remote: https://rubygems.org/
|
15
16
|
specs:
|
16
17
|
addressable (2.7.0)
|
17
18
|
public_suffix (>= 2.0.2, < 5.0)
|
19
|
+
cld (0.8.0)
|
20
|
+
ffi
|
18
21
|
coderay (1.1.2)
|
19
22
|
connection_pool (2.2.2)
|
20
23
|
crack (0.4.3)
|
21
24
|
safe_yaml (~> 1.0.0)
|
22
|
-
crass (1.0.
|
25
|
+
crass (1.0.5)
|
23
26
|
diff-lcs (1.3)
|
24
27
|
domain_name (0.5.20190701)
|
25
28
|
unf (>= 0.0.5, < 1.0.0)
|
26
|
-
ffi (1.11.
|
29
|
+
ffi (1.11.3)
|
27
30
|
final_redirect_url (0.1.0)
|
28
31
|
guess_html_encoding (0.0.11)
|
29
32
|
hashdiff (1.0.0)
|
@@ -39,50 +42,50 @@ GEM
|
|
39
42
|
ntlm-http (~> 0.1, >= 0.1.1)
|
40
43
|
webrobots (>= 0.0.9, < 0.2)
|
41
44
|
method_source (0.9.2)
|
42
|
-
mime-types (3.3)
|
45
|
+
mime-types (3.3.1)
|
43
46
|
mime-types-data (~> 3.2015)
|
44
|
-
mime-types-data (3.2019.
|
47
|
+
mime-types-data (3.2019.1009)
|
45
48
|
mini_portile2 (2.4.0)
|
46
49
|
natto (1.1.2)
|
47
50
|
ffi (>= 1.9.0)
|
48
51
|
net-http-digest_auth (1.4.1)
|
49
52
|
net-http-persistent (3.1.0)
|
50
53
|
connection_pool (~> 2.2)
|
51
|
-
nokogiri (1.10.
|
54
|
+
nokogiri (1.10.7)
|
52
55
|
mini_portile2 (~> 2.4.0)
|
53
|
-
nokogumbo (2.0.
|
56
|
+
nokogumbo (2.0.2)
|
54
57
|
nokogiri (~> 1.8, >= 1.8.4)
|
55
58
|
ntlm-http (0.1.1)
|
56
59
|
pry (0.12.2)
|
57
60
|
coderay (~> 1.1.0)
|
58
61
|
method_source (~> 0.9.0)
|
59
|
-
public_suffix (4.0.
|
60
|
-
rake (
|
61
|
-
rspec (3.
|
62
|
-
rspec-core (~> 3.
|
63
|
-
rspec-expectations (~> 3.
|
64
|
-
rspec-mocks (~> 3.
|
65
|
-
rspec-core (3.
|
66
|
-
rspec-support (~> 3.
|
67
|
-
rspec-expectations (3.
|
62
|
+
public_suffix (4.0.2)
|
63
|
+
rake (13.0.1)
|
64
|
+
rspec (3.9.0)
|
65
|
+
rspec-core (~> 3.9.0)
|
66
|
+
rspec-expectations (~> 3.9.0)
|
67
|
+
rspec-mocks (~> 3.9.0)
|
68
|
+
rspec-core (3.9.1)
|
69
|
+
rspec-support (~> 3.9.1)
|
70
|
+
rspec-expectations (3.9.0)
|
68
71
|
diff-lcs (>= 1.2.0, < 2.0)
|
69
|
-
rspec-support (~> 3.
|
70
|
-
rspec-mocks (3.
|
72
|
+
rspec-support (~> 3.9.0)
|
73
|
+
rspec-mocks (3.9.1)
|
71
74
|
diff-lcs (>= 1.2.0, < 2.0)
|
72
|
-
rspec-support (~> 3.
|
73
|
-
rspec-support (3.
|
75
|
+
rspec-support (~> 3.9.0)
|
76
|
+
rspec-support (3.9.2)
|
74
77
|
ruby-readability (0.7.0)
|
75
78
|
guess_html_encoding (>= 0.0.4)
|
76
79
|
nokogiri (>= 1.6.0)
|
77
80
|
safe_yaml (1.0.5)
|
78
|
-
sanitize (5.
|
81
|
+
sanitize (5.1.0)
|
79
82
|
crass (~> 1.0.2)
|
80
83
|
nokogiri (>= 1.8.0)
|
81
84
|
nokogumbo (~> 2.0)
|
82
85
|
unf (0.1.4)
|
83
86
|
unf_ext
|
84
87
|
unf_ext (0.0.7.6)
|
85
|
-
webmock (3.6
|
88
|
+
webmock (3.7.6)
|
86
89
|
addressable (>= 2.3.6)
|
87
90
|
crack (>= 0.3.2)
|
88
91
|
hashdiff (>= 0.4.0, < 2.0.0)
|
@@ -92,11 +95,11 @@ PLATFORMS
|
|
92
95
|
ruby
|
93
96
|
|
94
97
|
DEPENDENCIES
|
95
|
-
pry (
|
96
|
-
rake (
|
97
|
-
rspec (
|
98
|
+
pry (>= 0.12.2)
|
99
|
+
rake (>= 10.0)
|
100
|
+
rspec (>= 3.0)
|
98
101
|
web_stat!
|
99
|
-
webmock (
|
102
|
+
webmock (>= 3.6.0)
|
100
103
|
|
101
104
|
BUNDLED WITH
|
102
105
|
2.1.2
|
data/README.md
CHANGED
data/lib/web_stat/fetch.rb
CHANGED
@@ -1,10 +1,3 @@
|
|
1
|
-
require 'uri'
|
2
|
-
require 'digest'
|
3
|
-
require 'sanitize'
|
4
|
-
require 'nokogiri'
|
5
|
-
require 'open-uri'
|
6
|
-
require 'ruby-readability'
|
7
|
-
require 'final_redirect_url'
|
8
1
|
module WebStat
|
9
2
|
class Fetch
|
10
3
|
attr_accessor :url, :html, :nokogiri
|
@@ -60,7 +53,7 @@ module WebStat
|
|
60
53
|
def save_local_path(url)
|
61
54
|
return nil if url.nil?
|
62
55
|
tmp_file = "/tmp/#{Digest::SHA1.hexdigest(url)}"
|
63
|
-
open(original_url(url)) do |remote_file|
|
56
|
+
URI.open(original_url(url)) do |remote_file|
|
64
57
|
File.open(tmp_file, "w+b") do |_file|
|
65
58
|
_file.puts(remote_file.read)
|
66
59
|
end
|
@@ -79,11 +72,13 @@ module WebStat
|
|
79
72
|
|
80
73
|
# Get the informations of @url
|
81
74
|
def stat
|
75
|
+
content.gsub!(/(\n|\t|\s| )/, "")
|
82
76
|
tag = WebStat::Tag.new(content)
|
83
77
|
{
|
84
78
|
title: title,
|
85
79
|
site_name: site_name,
|
86
80
|
content: content,
|
81
|
+
language_code: CLD.detect_language(content)[:code],
|
87
82
|
url: @url,
|
88
83
|
eyecatch_image_path: save_local_path(eyecatch_image_path),
|
89
84
|
tags: tag.nouns
|
data/lib/web_stat/version.rb
CHANGED
data/lib/web_stat.rb
CHANGED
@@ -1,4 +1,14 @@
|
|
1
1
|
require "bundler"
|
2
|
+
|
3
|
+
require 'uri'
|
4
|
+
require 'digest'
|
5
|
+
require 'sanitize'
|
6
|
+
require 'nokogiri'
|
7
|
+
require 'open-uri'
|
8
|
+
require 'ruby-readability'
|
9
|
+
require 'final_redirect_url'
|
10
|
+
require 'cld'
|
11
|
+
|
2
12
|
require "web_stat/categorize"
|
3
13
|
require "web_stat/configure"
|
4
14
|
require "web_stat/errors"
|
data/spec/web_stat/fetch_spec.rb
CHANGED
@@ -49,6 +49,14 @@ RSpec.describe WebStat::Fetch do
|
|
49
49
|
end
|
50
50
|
end
|
51
51
|
|
52
|
+
it "Get language_iso by #{fetch[:class].to_s}" do
|
53
|
+
fetch[:fixture].each do |fixture|
|
54
|
+
web_stat = fetch[:class].new(fixture)
|
55
|
+
web_stat.url = "https://newsdict.blog"
|
56
|
+
expect(web_stat.stat[:language_code]).to eq("ja")
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
52
60
|
it "Get local path of eyecatch image by #{fetch[:class].to_s}" do
|
53
61
|
fetch[:fixture].each do |fixture|
|
54
62
|
web_stat = fetch[:class].new(fixture)
|
data/web_stat.gemspec
CHANGED
@@ -22,14 +22,15 @@ Gem::Specification.new do |spec|
|
|
22
22
|
|
23
23
|
spec.add_runtime_dependency "bundler", ">= 2.0.2"
|
24
24
|
spec.add_runtime_dependency "nokogiri", ">= 1.10.4"
|
25
|
-
spec.add_runtime_dependency "mechanize", "
|
26
|
-
spec.add_runtime_dependency "ruby-readability", "
|
27
|
-
spec.add_runtime_dependency "final_redirect_url", "
|
28
|
-
spec.add_runtime_dependency "natto", "
|
29
|
-
spec.add_runtime_dependency "sanitize", "
|
30
|
-
|
31
|
-
|
32
|
-
spec.add_development_dependency "
|
33
|
-
spec.add_development_dependency "
|
34
|
-
spec.add_development_dependency "
|
25
|
+
spec.add_runtime_dependency "mechanize", ">= 2.7"
|
26
|
+
spec.add_runtime_dependency "ruby-readability", ">= 0.7"
|
27
|
+
spec.add_runtime_dependency "final_redirect_url", ">= 0.1.0"
|
28
|
+
spec.add_runtime_dependency "natto", ">= 1.1.2"
|
29
|
+
spec.add_runtime_dependency "sanitize", ">= 5.0.0"
|
30
|
+
spec.add_runtime_dependency "cld", ">= 0.8.0"
|
31
|
+
|
32
|
+
spec.add_development_dependency "rake", ">= 10.0"
|
33
|
+
spec.add_development_dependency "rspec", ">= 3.0"
|
34
|
+
spec.add_development_dependency "pry", ">= 0.12.2"
|
35
|
+
spec.add_development_dependency "webmock", ">= 3.6.0"
|
35
36
|
end
|
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.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- yusuke abe
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2020-01-02 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -42,126 +42,140 @@ dependencies:
|
|
42
42
|
name: mechanize
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- - "
|
45
|
+
- - ">="
|
46
46
|
- !ruby/object:Gem::Version
|
47
47
|
version: '2.7'
|
48
48
|
type: :runtime
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- - "
|
52
|
+
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: '2.7'
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
56
|
name: ruby-readability
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- - "
|
59
|
+
- - ">="
|
60
60
|
- !ruby/object:Gem::Version
|
61
61
|
version: '0.7'
|
62
62
|
type: :runtime
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
|
-
- - "
|
66
|
+
- - ">="
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: '0.7'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: final_redirect_url
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
|
-
- - "
|
73
|
+
- - ">="
|
74
74
|
- !ruby/object:Gem::Version
|
75
75
|
version: 0.1.0
|
76
76
|
type: :runtime
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
|
-
- - "
|
80
|
+
- - ">="
|
81
81
|
- !ruby/object:Gem::Version
|
82
82
|
version: 0.1.0
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
84
|
name: natto
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
86
86
|
requirements:
|
87
|
-
- - "
|
87
|
+
- - ">="
|
88
88
|
- !ruby/object:Gem::Version
|
89
89
|
version: 1.1.2
|
90
90
|
type: :runtime
|
91
91
|
prerelease: false
|
92
92
|
version_requirements: !ruby/object:Gem::Requirement
|
93
93
|
requirements:
|
94
|
-
- - "
|
94
|
+
- - ">="
|
95
95
|
- !ruby/object:Gem::Version
|
96
96
|
version: 1.1.2
|
97
97
|
- !ruby/object:Gem::Dependency
|
98
98
|
name: sanitize
|
99
99
|
requirement: !ruby/object:Gem::Requirement
|
100
100
|
requirements:
|
101
|
-
- - "
|
101
|
+
- - ">="
|
102
102
|
- !ruby/object:Gem::Version
|
103
103
|
version: 5.0.0
|
104
104
|
type: :runtime
|
105
105
|
prerelease: false
|
106
106
|
version_requirements: !ruby/object:Gem::Requirement
|
107
107
|
requirements:
|
108
|
-
- - "
|
108
|
+
- - ">="
|
109
109
|
- !ruby/object:Gem::Version
|
110
110
|
version: 5.0.0
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: cld
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - ">="
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: 0.8.0
|
118
|
+
type: :runtime
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - ">="
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: 0.8.0
|
111
125
|
- !ruby/object:Gem::Dependency
|
112
126
|
name: rake
|
113
127
|
requirement: !ruby/object:Gem::Requirement
|
114
128
|
requirements:
|
115
|
-
- - "
|
129
|
+
- - ">="
|
116
130
|
- !ruby/object:Gem::Version
|
117
131
|
version: '10.0'
|
118
132
|
type: :development
|
119
133
|
prerelease: false
|
120
134
|
version_requirements: !ruby/object:Gem::Requirement
|
121
135
|
requirements:
|
122
|
-
- - "
|
136
|
+
- - ">="
|
123
137
|
- !ruby/object:Gem::Version
|
124
138
|
version: '10.0'
|
125
139
|
- !ruby/object:Gem::Dependency
|
126
140
|
name: rspec
|
127
141
|
requirement: !ruby/object:Gem::Requirement
|
128
142
|
requirements:
|
129
|
-
- - "
|
143
|
+
- - ">="
|
130
144
|
- !ruby/object:Gem::Version
|
131
145
|
version: '3.0'
|
132
146
|
type: :development
|
133
147
|
prerelease: false
|
134
148
|
version_requirements: !ruby/object:Gem::Requirement
|
135
149
|
requirements:
|
136
|
-
- - "
|
150
|
+
- - ">="
|
137
151
|
- !ruby/object:Gem::Version
|
138
152
|
version: '3.0'
|
139
153
|
- !ruby/object:Gem::Dependency
|
140
154
|
name: pry
|
141
155
|
requirement: !ruby/object:Gem::Requirement
|
142
156
|
requirements:
|
143
|
-
- - "
|
157
|
+
- - ">="
|
144
158
|
- !ruby/object:Gem::Version
|
145
159
|
version: 0.12.2
|
146
160
|
type: :development
|
147
161
|
prerelease: false
|
148
162
|
version_requirements: !ruby/object:Gem::Requirement
|
149
163
|
requirements:
|
150
|
-
- - "
|
164
|
+
- - ">="
|
151
165
|
- !ruby/object:Gem::Version
|
152
166
|
version: 0.12.2
|
153
167
|
- !ruby/object:Gem::Dependency
|
154
168
|
name: webmock
|
155
169
|
requirement: !ruby/object:Gem::Requirement
|
156
170
|
requirements:
|
157
|
-
- - "
|
171
|
+
- - ">="
|
158
172
|
- !ruby/object:Gem::Version
|
159
173
|
version: 3.6.0
|
160
174
|
type: :development
|
161
175
|
prerelease: false
|
162
176
|
version_requirements: !ruby/object:Gem::Requirement
|
163
177
|
requirements:
|
164
|
-
- - "
|
178
|
+
- - ">="
|
165
179
|
- !ruby/object:Gem::Version
|
166
180
|
version: 3.6.0
|
167
181
|
description: Fetch the web pages and stat.
|
@@ -221,7 +235,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
221
235
|
- !ruby/object:Gem::Version
|
222
236
|
version: '0'
|
223
237
|
requirements: []
|
224
|
-
rubygems_version: 3.
|
238
|
+
rubygems_version: 3.1.2
|
225
239
|
signing_key:
|
226
240
|
specification_version: 4
|
227
241
|
summary: Get the status of the web pages.
|