zorki 0.1.7 → 0.1.20
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +2 -0
- data/Gemfile.lock +54 -95
- data/lib/zorki/scrapers/post_scraper.rb +0 -1
- data/lib/zorki/scrapers/scraper.rb +35 -14
- data/lib/zorki/scrapers/user_scraper.rb +4 -0
- data/lib/zorki/version.rb +1 -1
- data/lib/zorki.rb +9 -2
- data/zorki.gemspec +3 -3
- metadata +18 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 1e635e294bb6e73e0e57481ba79d23c603bab3ebbd73bbb4939d12f615644098
|
4
|
+
data.tar.gz: 876ce40814980d04a962c8002662bf7462a269fa7b6885d89c419b1a2a64c8e0
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 552de3b78d4bce7c18d6e0df96d3fdb4eb2b1b43e35961a64617e738510be4979453fe496a55e642329f47d2e4fc8ced52ff390263f39c010693eee4e71a9074
|
7
|
+
data.tar.gz: 07be9124885ef2eedf0b7433385e1a29a1c1fd33c58686530d99b7c9767784df6b1b7343c57c97157fed756c196d33125b35e621da9a7bf4737da1855a05c911
|
data/.gitignore
CHANGED
data/Gemfile.lock
CHANGED
@@ -1,33 +1,18 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
zorki (0.1.
|
4
|
+
zorki (0.1.9)
|
5
5
|
apparition
|
6
6
|
capybara
|
7
7
|
oj
|
8
8
|
selenium-devtools
|
9
|
-
selenium-webdriver
|
9
|
+
selenium-webdriver (~> 4.19)
|
10
10
|
typhoeus
|
11
11
|
|
12
12
|
GEM
|
13
13
|
remote: https://rubygems.org/
|
14
14
|
specs:
|
15
|
-
|
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)
|
21
|
-
rack-test (>= 0.6.3)
|
22
|
-
rails-dom-testing (~> 2.2)
|
23
|
-
rails-html-sanitizer (~> 1.6)
|
24
|
-
actionview (7.1.0.beta1)
|
25
|
-
activesupport (= 7.1.0.beta1)
|
26
|
-
builder (~> 3.1)
|
27
|
-
erubi (~> 1.11)
|
28
|
-
rails-dom-testing (~> 2.2)
|
29
|
-
rails-html-sanitizer (~> 1.6)
|
30
|
-
activesupport (7.1.0.beta1)
|
15
|
+
activesupport (7.1.3.2)
|
31
16
|
base64
|
32
17
|
bigdecimal
|
33
18
|
concurrent-ruby (~> 1.0, >= 1.0.2)
|
@@ -37,122 +22,98 @@ GEM
|
|
37
22
|
minitest (>= 5.1)
|
38
23
|
mutex_m
|
39
24
|
tzinfo (~> 2.0)
|
40
|
-
addressable (2.8.
|
25
|
+
addressable (2.8.6)
|
41
26
|
public_suffix (>= 2.0.2, < 6.0)
|
42
27
|
apparition (0.6.0)
|
43
28
|
capybara (~> 3.13, < 4)
|
44
29
|
websocket-driver (>= 0.6.5)
|
45
30
|
ast (2.4.2)
|
46
|
-
base64 (0.
|
47
|
-
bigdecimal (3.1.
|
48
|
-
|
49
|
-
capybara (3.39.2)
|
31
|
+
base64 (0.2.0)
|
32
|
+
bigdecimal (3.1.7)
|
33
|
+
capybara (3.40.0)
|
50
34
|
addressable
|
51
35
|
matrix
|
52
36
|
mini_mime (>= 0.1.3)
|
53
|
-
nokogiri (~> 1.
|
37
|
+
nokogiri (~> 1.11)
|
54
38
|
rack (>= 1.6.0)
|
55
39
|
rack-test (>= 0.6.3)
|
56
40
|
regexp_parser (>= 1.5, < 3.0)
|
57
41
|
xpath (~> 3.2)
|
58
|
-
concurrent-ruby (1.2.
|
42
|
+
concurrent-ruby (1.2.3)
|
59
43
|
connection_pool (2.4.1)
|
60
|
-
crass (1.0.6)
|
61
44
|
curb (1.0.5)
|
45
|
+
debug (1.9.1)
|
46
|
+
irb (~> 1.10)
|
47
|
+
reline (>= 0.3.8)
|
62
48
|
dotenv (2.7.6)
|
63
|
-
drb (2.
|
64
|
-
ruby2_keywords
|
65
|
-
erubi (1.12.0)
|
49
|
+
drb (2.2.1)
|
66
50
|
ethon (0.16.0)
|
67
51
|
ffi (>= 1.15.0)
|
68
|
-
ffi (1.
|
69
|
-
i18n (1.14.
|
52
|
+
ffi (1.16.3)
|
53
|
+
i18n (1.14.4)
|
70
54
|
concurrent-ruby (~> 1.0)
|
71
|
-
io-console (0.
|
72
|
-
irb (1.
|
55
|
+
io-console (0.7.2)
|
56
|
+
irb (1.12.0)
|
73
57
|
rdoc
|
74
|
-
reline (>= 0.
|
75
|
-
json (2.
|
58
|
+
reline (>= 0.4.2)
|
59
|
+
json (2.7.1)
|
76
60
|
language_server-protocol (3.17.0.3)
|
77
|
-
loofah (2.21.3)
|
78
|
-
crass (~> 1.0.2)
|
79
|
-
nokogiri (>= 1.12.0)
|
80
61
|
matrix (0.4.2)
|
81
62
|
mini_mime (1.1.5)
|
82
|
-
minitest (5.
|
83
|
-
mutex_m (0.
|
84
|
-
nokogiri (1.
|
63
|
+
minitest (5.22.3)
|
64
|
+
mutex_m (0.2.0)
|
65
|
+
nokogiri (1.16.3-arm64-darwin)
|
85
66
|
racc (~> 1.4)
|
86
|
-
oj (3.16.
|
87
|
-
|
88
|
-
|
67
|
+
oj (3.16.3)
|
68
|
+
bigdecimal (>= 3.0)
|
69
|
+
parallel (1.24.0)
|
70
|
+
parser (3.3.0.5)
|
89
71
|
ast (~> 2.4.1)
|
90
72
|
racc
|
91
|
-
psych (5.1.
|
73
|
+
psych (5.1.2)
|
92
74
|
stringio
|
93
|
-
public_suffix (5.0.
|
94
|
-
racc (1.7.
|
75
|
+
public_suffix (5.0.4)
|
76
|
+
racc (1.7.3)
|
95
77
|
rack (3.0.8)
|
96
|
-
rack-session (2.0.0)
|
97
|
-
rack (>= 3.0.0)
|
98
78
|
rack-test (2.1.0)
|
99
79
|
rack (>= 1.3)
|
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
|
106
|
-
nokogiri (>= 1.6)
|
107
|
-
rails-html-sanitizer (1.6.0)
|
108
|
-
loofah (~> 2.21)
|
109
|
-
nokogiri (~> 1.14)
|
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)
|
115
|
-
rake (>= 12.2)
|
116
|
-
thor (~> 1.0, >= 1.2.2)
|
117
|
-
zeitwerk (~> 2.6)
|
118
80
|
rainbow (3.1.1)
|
119
|
-
rake (13.0
|
120
|
-
rdoc (6.
|
81
|
+
rake (13.1.0)
|
82
|
+
rdoc (6.6.3.1)
|
121
83
|
psych (>= 4.0.0)
|
122
|
-
regexp_parser (2.
|
123
|
-
reline (0.
|
84
|
+
regexp_parser (2.9.0)
|
85
|
+
reline (0.5.0)
|
124
86
|
io-console (~> 0.5)
|
125
87
|
rexml (3.2.6)
|
126
|
-
rubocop (1.
|
127
|
-
base64 (~> 0.1.1)
|
88
|
+
rubocop (1.62.1)
|
128
89
|
json (~> 2.3)
|
129
90
|
language_server-protocol (>= 3.17.0)
|
130
91
|
parallel (~> 1.10)
|
131
|
-
parser (>= 3.
|
92
|
+
parser (>= 3.3.0.2)
|
132
93
|
rainbow (>= 2.2.2, < 4.0)
|
133
94
|
regexp_parser (>= 1.8, < 3.0)
|
134
95
|
rexml (>= 3.2.5, < 4.0)
|
135
|
-
rubocop-ast (>= 1.
|
96
|
+
rubocop-ast (>= 1.31.1, < 2.0)
|
136
97
|
ruby-progressbar (~> 1.7)
|
137
98
|
unicode-display_width (>= 2.4.0, < 3.0)
|
138
|
-
rubocop-ast (1.
|
139
|
-
parser (>= 3.
|
140
|
-
rubocop-md (1.2.
|
99
|
+
rubocop-ast (1.31.2)
|
100
|
+
parser (>= 3.3.0.4)
|
101
|
+
rubocop-md (1.2.2)
|
141
102
|
rubocop (>= 1.0)
|
142
|
-
rubocop-minitest (0.
|
143
|
-
rubocop (>= 1.
|
103
|
+
rubocop-minitest (0.35.0)
|
104
|
+
rubocop (>= 1.61, < 2.0)
|
105
|
+
rubocop-ast (>= 1.31.1, < 2.0)
|
144
106
|
rubocop-packaging (0.5.2)
|
145
107
|
rubocop (>= 1.33, < 2.0)
|
146
|
-
rubocop-performance (1.
|
147
|
-
rubocop (>= 1.
|
148
|
-
rubocop-ast (>=
|
108
|
+
rubocop-performance (1.20.2)
|
109
|
+
rubocop (>= 1.48.1, < 2.0)
|
110
|
+
rubocop-ast (>= 1.30.0, < 2.0)
|
149
111
|
rubocop-rails (2.19.1)
|
150
112
|
activesupport (>= 4.2.0)
|
151
113
|
rack (>= 1.1)
|
152
114
|
rubocop (>= 1.33.0, < 2.0)
|
153
|
-
rubocop-rails_config (1.
|
154
|
-
|
155
|
-
rubocop (>= 1.48.0)
|
115
|
+
rubocop-rails_config (1.16.0)
|
116
|
+
rubocop (>= 1.57.0)
|
156
117
|
rubocop-ast (>= 1.26.0)
|
157
118
|
rubocop-md
|
158
119
|
rubocop-minitest (~> 0.22)
|
@@ -160,35 +121,33 @@ GEM
|
|
160
121
|
rubocop-performance (~> 1.11)
|
161
122
|
rubocop-rails (~> 2.0)
|
162
123
|
ruby-progressbar (1.13.0)
|
163
|
-
ruby2_keywords (0.0.5)
|
164
124
|
rubyzip (2.3.2)
|
165
|
-
selenium-devtools (0.
|
125
|
+
selenium-devtools (0.123.0)
|
166
126
|
selenium-webdriver (~> 4.2)
|
167
|
-
selenium-webdriver (4.
|
127
|
+
selenium-webdriver (4.19.0)
|
128
|
+
base64 (~> 0.2)
|
168
129
|
rexml (~> 3.2, >= 3.2.5)
|
169
130
|
rubyzip (>= 1.2.2, < 3.0)
|
170
131
|
websocket (~> 1.0)
|
171
|
-
stringio (3.0
|
172
|
-
|
173
|
-
typhoeus (1.4.0)
|
132
|
+
stringio (3.1.0)
|
133
|
+
typhoeus (1.4.1)
|
174
134
|
ethon (>= 0.9.0)
|
175
135
|
tzinfo (2.0.6)
|
176
136
|
concurrent-ruby (~> 1.0)
|
177
|
-
unicode-display_width (2.
|
178
|
-
webrick (1.8.1)
|
137
|
+
unicode-display_width (2.5.0)
|
179
138
|
websocket (1.2.10)
|
180
139
|
websocket-driver (0.7.6)
|
181
140
|
websocket-extensions (>= 0.1.0)
|
182
141
|
websocket-extensions (0.1.5)
|
183
142
|
xpath (3.2.0)
|
184
143
|
nokogiri (~> 1.8)
|
185
|
-
zeitwerk (2.6.11)
|
186
144
|
|
187
145
|
PLATFORMS
|
188
146
|
arm64-darwin-22
|
189
147
|
|
190
148
|
DEPENDENCIES
|
191
149
|
curb (~> 1.0, >= 1.0.5)
|
150
|
+
debug
|
192
151
|
dotenv (~> 2.7.6)
|
193
152
|
minitest (~> 5.0)
|
194
153
|
rack (= 3.0.8)
|
@@ -114,27 +114,32 @@ module Zorki
|
|
114
114
|
# e.attributes.has_key?("type") && e.attributes["type"].value == "application/ld+json"
|
115
115
|
# end
|
116
116
|
|
117
|
-
elements = doc.search("script").
|
118
|
-
|
117
|
+
elements = doc.search("script").filter_map do |element|
|
118
|
+
parsed_element_json = nil
|
119
119
|
begin
|
120
|
-
element_json = JSON.parse(element)
|
120
|
+
element_json = JSON.parse(element.text)
|
121
121
|
|
122
|
-
|
123
|
-
rescue StandardError
|
122
|
+
parsed_element_json = element_json["require"].first.last.first["__bbox"]["require"].first.last.last["__bbox"]["result"]["data"]["xdt_api__v1__media__shortcode__web_info"]
|
123
|
+
rescue StandardError
|
124
124
|
next
|
125
125
|
end
|
126
126
|
|
127
|
-
|
128
|
-
end
|
127
|
+
parsed_element_json
|
128
|
+
end
|
129
129
|
|
130
130
|
if elements&.empty?
|
131
|
-
raise ContentUnavailableError
|
131
|
+
raise ContentUnavailableError.new("Cannot find anything", additional_data: { page_source: page.driver.browser.page_source, elements: elements })
|
132
132
|
end
|
133
|
+
|
133
134
|
return elements
|
134
135
|
end
|
135
136
|
|
136
|
-
raise ContentUnavailableError if response_body.nil?
|
137
|
+
raise ContentUnavailableError.new("Response body nil") if response_body.nil?
|
137
138
|
Oj.load(response_body)
|
139
|
+
ensure
|
140
|
+
page.quit
|
141
|
+
# TRY THIS TO MAKE SURE CHROME GETS CLOSED?
|
142
|
+
# We may also want to not do this and make sure the same browser is reused instead for cookie purposes
|
138
143
|
end
|
139
144
|
|
140
145
|
private
|
@@ -166,8 +171,9 @@ module Zorki
|
|
166
171
|
end
|
167
172
|
|
168
173
|
def login
|
174
|
+
puts "Attempting to login..."
|
169
175
|
# Reset the sessions so that there's nothing laying around
|
170
|
-
page.
|
176
|
+
# page.driver.browser.close
|
171
177
|
|
172
178
|
# Check if we're on a Instagram page already, if not visit it.
|
173
179
|
unless page.driver.browser.current_url.include? "instagram.com"
|
@@ -188,16 +194,20 @@ module Zorki
|
|
188
194
|
# Try to log in
|
189
195
|
loop_count = 0
|
190
196
|
while loop_count < 5 do
|
197
|
+
puts "Attempting to fill login field ##{loop_count}"
|
198
|
+
|
191
199
|
fill_in("username", with: ENV["INSTAGRAM_USER_NAME"])
|
192
200
|
fill_in("password", with: ENV["INSTAGRAM_PASSWORD"])
|
193
201
|
|
194
202
|
begin
|
195
|
-
|
203
|
+
find_button("Log in").click() # Note: "Log in" (lowercase `in`) should be exact instead, it redirects to Facebook's login page
|
196
204
|
rescue Capybara::ElementNotFound; end # If we can't find it don't break horribly, just keep waiting
|
197
205
|
|
198
|
-
break unless has_css?('p[data-testid="login-error-message"', wait:
|
206
|
+
break unless has_css?('p[data-testid="login-error-message"', wait: 3)
|
199
207
|
loop_count += 1
|
200
|
-
|
208
|
+
random_length = rand(1...2)
|
209
|
+
puts "Sleeping for #{random_length} seconds"
|
210
|
+
sleep(random_length)
|
201
211
|
end
|
202
212
|
|
203
213
|
# Sometimes Instagram just... doesn't let you log in
|
@@ -205,7 +215,9 @@ module Zorki
|
|
205
215
|
|
206
216
|
# No we don't want to save our login credentials
|
207
217
|
begin
|
208
|
-
|
218
|
+
puts "Checking and clearing Save Info button..."
|
219
|
+
|
220
|
+
find_button("Save Info").click()
|
209
221
|
rescue Capybara::ElementNotFound; end
|
210
222
|
end
|
211
223
|
|
@@ -242,6 +254,15 @@ module Zorki
|
|
242
254
|
# Multiply everything and insure we get an integer back
|
243
255
|
(number * multiplier).to_i
|
244
256
|
end
|
257
|
+
|
258
|
+
# def reset_window
|
259
|
+
# old_handle = page.driver.browser.window_handle
|
260
|
+
# page.driver.browser.switch_to.new_window(:window)
|
261
|
+
# new_handle = page.driver.browser.window_handle
|
262
|
+
# page.driver.browser.switch_to.window(old_handle)
|
263
|
+
# page.driver.browser.close
|
264
|
+
# page.driver.browser.switch_to.window(new_handle)
|
265
|
+
# end
|
245
266
|
end
|
246
267
|
end
|
247
268
|
|
@@ -21,6 +21,10 @@ module Zorki
|
|
21
21
|
graphql_script = get_content_of_subpage_from_url("https://instagram.com/#{username}/", "?username=")
|
22
22
|
graphql_script = graphql_script.first if graphql_script.class == Array
|
23
23
|
|
24
|
+
if graphql_script.nil?
|
25
|
+
graphql_script = get_content_of_subpage_from_url("https://instagram.com/#{username}/", "web_profile_info")
|
26
|
+
end
|
27
|
+
|
24
28
|
if graphql_script.has_key?("author") && !graphql_script["author"].nil?
|
25
29
|
user = graphql_script["author"]
|
26
30
|
|
data/lib/zorki/version.rb
CHANGED
data/lib/zorki.rb
CHANGED
@@ -20,8 +20,15 @@ module Zorki
|
|
20
20
|
end
|
21
21
|
|
22
22
|
class ContentUnavailableError < Error
|
23
|
-
|
24
|
-
|
23
|
+
attr_reader :additional_data
|
24
|
+
|
25
|
+
def initialize(msg = "Zorki could not find content requested", additional_data: {})
|
26
|
+
super(msg)
|
27
|
+
@additional_data = additional_data
|
28
|
+
end
|
29
|
+
|
30
|
+
def to_honeybadger_context
|
31
|
+
additional_data
|
25
32
|
end
|
26
33
|
end
|
27
34
|
|
data/zorki.gemspec
CHANGED
@@ -29,15 +29,15 @@ Gem::Specification.new do |spec|
|
|
29
29
|
spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
|
30
30
|
spec.require_paths = ["lib"]
|
31
31
|
|
32
|
-
# Uncomment to register a new dependency of your gem
|
33
|
-
# spec.add_dependency "example-gem", "~> 1.0"
|
34
32
|
spec.add_dependency "capybara" # For scraping and running browsers
|
35
33
|
spec.add_dependency "apparition" # A Chrome driver for Capybara
|
36
34
|
spec.add_dependency "typhoeus" # For making API requests
|
37
35
|
spec.add_dependency "oj" # A faster JSON parser/loader than stdlib
|
38
|
-
spec.add_dependency "selenium-webdriver" # Webdriver selenium
|
36
|
+
spec.add_dependency "selenium-webdriver", "~> 4.19" # Webdriver selenium
|
39
37
|
spec.add_dependency "selenium-devtools" # Allow us to intercept requests
|
40
38
|
|
39
|
+
spec.add_development_dependency "debug"
|
40
|
+
|
41
41
|
# For more information and examples about making a new gem, checkout our
|
42
42
|
# guide at: https://bundler.io/guides/creating_gem.html
|
43
43
|
end
|
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: 0.1.20
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Christopher Guess
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2024-03-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: capybara
|
@@ -68,6 +68,20 @@ dependencies:
|
|
68
68
|
version: '0'
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: selenium-webdriver
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '4.19'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '4.19'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: selenium-devtools
|
71
85
|
requirement: !ruby/object:Gem::Requirement
|
72
86
|
requirements:
|
73
87
|
- - ">="
|
@@ -81,13 +95,13 @@ dependencies:
|
|
81
95
|
- !ruby/object:Gem::Version
|
82
96
|
version: '0'
|
83
97
|
- !ruby/object:Gem::Dependency
|
84
|
-
name:
|
98
|
+
name: debug
|
85
99
|
requirement: !ruby/object:Gem::Requirement
|
86
100
|
requirements:
|
87
101
|
- - ">="
|
88
102
|
- !ruby/object:Gem::Version
|
89
103
|
version: '0'
|
90
|
-
type: :
|
104
|
+
type: :development
|
91
105
|
prerelease: false
|
92
106
|
version_requirements: !ruby/object:Gem::Requirement
|
93
107
|
requirements:
|