zorki 0.1.4 → 0.1.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile +1 -0
- data/Gemfile.lock +76 -40
- data/lib/zorki/monkeypatch.rb +3 -1
- data/lib/zorki/scrapers/scraper.rb +2 -4
- data/lib/zorki/version.rb +1 -1
- metadata +3 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: e720f45ab99fab246cdb6431d001833cc33bdee49278947e425c9b88654ec454
|
4
|
+
data.tar.gz: e51242c9b1c64a88a5b00eb0450ed5ca602addd1ab36676fbe3ea1e8aa0878e2
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: ca1546e4c18d1d6d90723ac13d6e5c255dcd6d20761614a3a030be157aaf0d59ae886805ecdf17fb9718574a2c59a3ffedc14464f64221a060ddbd520cfe740f
|
7
|
+
data.tar.gz: cfcb54bcc569a005406ad3b52bb98e6990bb8089a80bf295c6f4a8331268e571b7c6f98afbc29c188b5de54ef2e2fded7d788cda42f618580989f01cb2fb9522
|
data/Gemfile
CHANGED
data/Gemfile.lock
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
zorki (0.1.
|
4
|
+
zorki (0.1.5)
|
5
5
|
apparition
|
6
6
|
capybara
|
7
7
|
oj
|
@@ -12,30 +12,39 @@ PATH
|
|
12
12
|
GEM
|
13
13
|
remote: https://rubygems.org/
|
14
14
|
specs:
|
15
|
-
actionpack (7.0.
|
16
|
-
actionview (= 7.0.
|
17
|
-
activesupport (= 7.0.
|
18
|
-
|
15
|
+
actionpack (7.1.0.beta1)
|
16
|
+
actionview (= 7.1.0.beta1)
|
17
|
+
activesupport (= 7.1.0.beta1)
|
18
|
+
nokogiri (>= 1.8.5)
|
19
|
+
rack (>= 2.2.4)
|
20
|
+
rack-session (>= 1.0.1)
|
19
21
|
rack-test (>= 0.6.3)
|
20
|
-
rails-dom-testing (~> 2.
|
21
|
-
rails-html-sanitizer (~> 1.
|
22
|
-
actionview (7.0.
|
23
|
-
activesupport (= 7.0.
|
22
|
+
rails-dom-testing (~> 2.2)
|
23
|
+
rails-html-sanitizer (~> 1.6)
|
24
|
+
actionview (7.1.0.beta1)
|
25
|
+
activesupport (= 7.1.0.beta1)
|
24
26
|
builder (~> 3.1)
|
25
|
-
erubi (~> 1.
|
26
|
-
rails-dom-testing (~> 2.
|
27
|
-
rails-html-sanitizer (~> 1.
|
28
|
-
activesupport (7.0.
|
27
|
+
erubi (~> 1.11)
|
28
|
+
rails-dom-testing (~> 2.2)
|
29
|
+
rails-html-sanitizer (~> 1.6)
|
30
|
+
activesupport (7.1.0.beta1)
|
31
|
+
base64
|
32
|
+
bigdecimal
|
29
33
|
concurrent-ruby (~> 1.0, >= 1.0.2)
|
34
|
+
connection_pool (>= 2.2.5)
|
35
|
+
drb
|
30
36
|
i18n (>= 1.6, < 2)
|
31
37
|
minitest (>= 5.1)
|
38
|
+
mutex_m
|
32
39
|
tzinfo (~> 2.0)
|
33
|
-
addressable (2.8.
|
40
|
+
addressable (2.8.5)
|
34
41
|
public_suffix (>= 2.0.2, < 6.0)
|
35
42
|
apparition (0.6.0)
|
36
43
|
capybara (~> 3.13, < 4)
|
37
44
|
websocket-driver (>= 0.6.5)
|
38
45
|
ast (2.4.2)
|
46
|
+
base64 (0.1.1)
|
47
|
+
bigdecimal (3.1.4)
|
39
48
|
builder (3.2.4)
|
40
49
|
capybara (3.39.2)
|
41
50
|
addressable
|
@@ -47,78 +56,101 @@ GEM
|
|
47
56
|
regexp_parser (>= 1.5, < 3.0)
|
48
57
|
xpath (~> 3.2)
|
49
58
|
concurrent-ruby (1.2.2)
|
59
|
+
connection_pool (2.4.1)
|
50
60
|
crass (1.0.6)
|
51
61
|
curb (1.0.5)
|
52
62
|
dotenv (2.7.6)
|
63
|
+
drb (2.1.1)
|
64
|
+
ruby2_keywords
|
53
65
|
erubi (1.12.0)
|
54
66
|
ethon (0.16.0)
|
55
67
|
ffi (>= 1.15.0)
|
56
68
|
ffi (1.15.5)
|
57
69
|
i18n (1.14.1)
|
58
70
|
concurrent-ruby (~> 1.0)
|
71
|
+
io-console (0.6.0)
|
72
|
+
irb (1.8.1)
|
73
|
+
rdoc
|
74
|
+
reline (>= 0.3.8)
|
59
75
|
json (2.6.3)
|
76
|
+
language_server-protocol (3.17.0.3)
|
60
77
|
loofah (2.21.3)
|
61
78
|
crass (~> 1.0.2)
|
62
79
|
nokogiri (>= 1.12.0)
|
63
80
|
matrix (0.4.2)
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
nokogiri (1.15.
|
81
|
+
mini_mime (1.1.5)
|
82
|
+
minitest (5.20.0)
|
83
|
+
mutex_m (0.1.2)
|
84
|
+
nokogiri (1.15.4-arm64-darwin)
|
68
85
|
racc (~> 1.4)
|
69
|
-
oj (3.
|
86
|
+
oj (3.16.1)
|
70
87
|
parallel (1.23.0)
|
71
88
|
parser (3.2.2.3)
|
72
89
|
ast (~> 2.4.1)
|
73
90
|
racc
|
74
|
-
|
75
|
-
|
76
|
-
|
91
|
+
psych (5.1.0)
|
92
|
+
stringio
|
93
|
+
public_suffix (5.0.3)
|
94
|
+
racc (1.7.1)
|
95
|
+
rack (3.0.8)
|
96
|
+
rack-session (2.0.0)
|
97
|
+
rack (>= 3.0.0)
|
77
98
|
rack-test (2.1.0)
|
78
99
|
rack (>= 1.3)
|
79
|
-
|
80
|
-
|
100
|
+
rackup (2.1.0)
|
101
|
+
rack (>= 3)
|
102
|
+
webrick (~> 1.8)
|
103
|
+
rails-dom-testing (2.2.0)
|
104
|
+
activesupport (>= 5.0.0)
|
105
|
+
minitest
|
81
106
|
nokogiri (>= 1.6)
|
82
107
|
rails-html-sanitizer (1.6.0)
|
83
108
|
loofah (~> 2.21)
|
84
109
|
nokogiri (~> 1.14)
|
85
|
-
railties (7.0.
|
86
|
-
actionpack (= 7.0.
|
87
|
-
activesupport (= 7.0.
|
88
|
-
|
110
|
+
railties (7.1.0.beta1)
|
111
|
+
actionpack (= 7.1.0.beta1)
|
112
|
+
activesupport (= 7.1.0.beta1)
|
113
|
+
irb
|
114
|
+
rackup (>= 1.0.0)
|
89
115
|
rake (>= 12.2)
|
90
|
-
thor (~> 1.0)
|
91
|
-
zeitwerk (~> 2.
|
116
|
+
thor (~> 1.0, >= 1.2.2)
|
117
|
+
zeitwerk (~> 2.6)
|
92
118
|
rainbow (3.1.1)
|
93
119
|
rake (13.0.6)
|
120
|
+
rdoc (6.5.0)
|
121
|
+
psych (>= 4.0.0)
|
94
122
|
regexp_parser (2.8.1)
|
95
|
-
|
96
|
-
|
123
|
+
reline (0.3.8)
|
124
|
+
io-console (~> 0.5)
|
125
|
+
rexml (3.2.6)
|
126
|
+
rubocop (1.56.3)
|
127
|
+
base64 (~> 0.1.1)
|
97
128
|
json (~> 2.3)
|
129
|
+
language_server-protocol (>= 3.17.0)
|
98
130
|
parallel (~> 1.10)
|
99
131
|
parser (>= 3.2.2.3)
|
100
132
|
rainbow (>= 2.2.2, < 4.0)
|
101
133
|
regexp_parser (>= 1.8, < 3.0)
|
102
134
|
rexml (>= 3.2.5, < 4.0)
|
103
|
-
rubocop-ast (>= 1.28.
|
135
|
+
rubocop-ast (>= 1.28.1, < 2.0)
|
104
136
|
ruby-progressbar (~> 1.7)
|
105
137
|
unicode-display_width (>= 2.4.0, < 3.0)
|
106
138
|
rubocop-ast (1.29.0)
|
107
139
|
parser (>= 3.2.1.0)
|
108
140
|
rubocop-md (1.2.0)
|
109
141
|
rubocop (>= 1.0)
|
110
|
-
rubocop-minitest (0.31.
|
142
|
+
rubocop-minitest (0.31.1)
|
111
143
|
rubocop (>= 1.39, < 2.0)
|
112
144
|
rubocop-packaging (0.5.2)
|
113
145
|
rubocop (>= 1.33, < 2.0)
|
114
|
-
rubocop-performance (1.
|
146
|
+
rubocop-performance (1.19.0)
|
115
147
|
rubocop (>= 1.7.0, < 2.0)
|
116
148
|
rubocop-ast (>= 0.4.0)
|
117
149
|
rubocop-rails (2.19.1)
|
118
150
|
activesupport (>= 4.2.0)
|
119
151
|
rack (>= 1.1)
|
120
152
|
rubocop (>= 1.33.0, < 2.0)
|
121
|
-
rubocop-rails_config (1.
|
153
|
+
rubocop-rails_config (1.14.1)
|
122
154
|
railties (>= 5.0)
|
123
155
|
rubocop (>= 1.48.0)
|
124
156
|
rubocop-ast (>= 1.26.0)
|
@@ -128,26 +160,29 @@ GEM
|
|
128
160
|
rubocop-performance (~> 1.11)
|
129
161
|
rubocop-rails (~> 2.0)
|
130
162
|
ruby-progressbar (1.13.0)
|
163
|
+
ruby2_keywords (0.0.5)
|
131
164
|
rubyzip (2.3.2)
|
132
|
-
selenium-devtools (0.
|
165
|
+
selenium-devtools (0.116.0)
|
133
166
|
selenium-webdriver (~> 4.2)
|
134
|
-
selenium-webdriver (4.
|
167
|
+
selenium-webdriver (4.12.0)
|
135
168
|
rexml (~> 3.2, >= 3.2.5)
|
136
169
|
rubyzip (>= 1.2.2, < 3.0)
|
137
170
|
websocket (~> 1.0)
|
171
|
+
stringio (3.0.8)
|
138
172
|
thor (1.2.2)
|
139
173
|
typhoeus (1.4.0)
|
140
174
|
ethon (>= 0.9.0)
|
141
175
|
tzinfo (2.0.6)
|
142
176
|
concurrent-ruby (~> 1.0)
|
143
177
|
unicode-display_width (2.4.2)
|
178
|
+
webrick (1.8.1)
|
144
179
|
websocket (1.2.9)
|
145
|
-
websocket-driver (0.7.
|
180
|
+
websocket-driver (0.7.6)
|
146
181
|
websocket-extensions (>= 0.1.0)
|
147
182
|
websocket-extensions (0.1.5)
|
148
183
|
xpath (3.2.0)
|
149
184
|
nokogiri (~> 1.8)
|
150
|
-
zeitwerk (2.6.
|
185
|
+
zeitwerk (2.6.11)
|
151
186
|
|
152
187
|
PLATFORMS
|
153
188
|
arm64-darwin-22
|
@@ -156,6 +191,7 @@ DEPENDENCIES
|
|
156
191
|
curb (~> 1.0, >= 1.0.5)
|
157
192
|
dotenv (~> 2.7.6)
|
158
193
|
minitest (~> 5.0)
|
194
|
+
rack (= 3.0.8)
|
159
195
|
rake (~> 13.0)
|
160
196
|
rubocop (~> 1.7)
|
161
197
|
rubocop-rails (~> 2.19.1)
|
data/lib/zorki/monkeypatch.rb
CHANGED
@@ -40,7 +40,9 @@ module SeleniumMonkeypatch
|
|
40
40
|
data = { method: method, params: params.compact }
|
41
41
|
data[:sessionId] = @session_id if @session_id
|
42
42
|
message = @ws.send_cmd(**data)
|
43
|
-
|
43
|
+
if message.nil? == false && message["error"] && (method != "Fetch.continueRequest")
|
44
|
+
raise Error::WebDriverError, error_message(message["error"])
|
45
|
+
end
|
44
46
|
|
45
47
|
message
|
46
48
|
end
|
@@ -68,14 +68,12 @@ module Zorki
|
|
68
68
|
page.driver.browser.intercept do |request, &continue|
|
69
69
|
# This passes the request forward unmodified, since we only care about the response
|
70
70
|
# puts "checking request: #{request.url}"
|
71
|
-
|
72
71
|
continue.call(request) && next unless request.url.include?(subpage_search)
|
73
72
|
|
74
73
|
continue.call(request) do |response|
|
75
74
|
# Check if not a CORS prefetch and finish up if not
|
76
|
-
if response.body.
|
75
|
+
if !response.body.empty? && response.body
|
77
76
|
check_passed = true
|
78
|
-
|
79
77
|
unless additional_search_parameters.nil?
|
80
78
|
body_to_check = Oj.load(response.body)
|
81
79
|
|
@@ -117,7 +115,7 @@ module Zorki
|
|
117
115
|
# end
|
118
116
|
|
119
117
|
elements = doc.search("script").map do |element|
|
120
|
-
|
118
|
+
element_json = nil
|
121
119
|
begin
|
122
120
|
element_json = JSON.parse(element)
|
123
121
|
|
data/lib/zorki/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: zorki
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.6
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Christopher Guess
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2023-
|
11
|
+
date: 2023-09-14 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: capybara
|
@@ -145,7 +145,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
145
145
|
- !ruby/object:Gem::Version
|
146
146
|
version: '0'
|
147
147
|
requirements: []
|
148
|
-
rubygems_version: 3.4.
|
148
|
+
rubygems_version: 3.4.10
|
149
149
|
signing_key:
|
150
150
|
specification_version: 4
|
151
151
|
summary: A gem to scrape Instagram pages for archive purposes.
|