crawlscope 0.1.0
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 +7 -0
- data/CHANGELOG.md +31 -0
- data/LICENSE.txt +21 -0
- data/README.md +323 -0
- data/exe/crawlscope +6 -0
- data/lib/crawlscope/audit.rb +128 -0
- data/lib/crawlscope/browser.rb +88 -0
- data/lib/crawlscope/cli.rb +245 -0
- data/lib/crawlscope/configuration.rb +123 -0
- data/lib/crawlscope/crawler.rb +28 -0
- data/lib/crawlscope/http.rb +77 -0
- data/lib/crawlscope/issue.rb +17 -0
- data/lib/crawlscope/issue_collection.rb +41 -0
- data/lib/crawlscope/page.rb +23 -0
- data/lib/crawlscope/railtie.rb +9 -0
- data/lib/crawlscope/reporter.rb +33 -0
- data/lib/crawlscope/result.rb +9 -0
- data/lib/crawlscope/rule_registry.rb +39 -0
- data/lib/crawlscope/rules/links.rb +220 -0
- data/lib/crawlscope/rules/metadata.rb +93 -0
- data/lib/crawlscope/rules/structured_data.rb +58 -0
- data/lib/crawlscope/rules/uniqueness.rb +88 -0
- data/lib/crawlscope/schema_registry.rb +431 -0
- data/lib/crawlscope/sitemap.rb +67 -0
- data/lib/crawlscope/structured_data/audit.rb +150 -0
- data/lib/crawlscope/structured_data/document.rb +93 -0
- data/lib/crawlscope/structured_data/report.rb +77 -0
- data/lib/crawlscope/structured_data/reporter.rb +73 -0
- data/lib/crawlscope/structured_data/writer.rb +26 -0
- data/lib/crawlscope/task.rb +131 -0
- data/lib/crawlscope/url.rb +43 -0
- data/lib/crawlscope/version.rb +5 -0
- data/lib/crawlscope.rb +34 -0
- data/lib/tasks/crawlscope_tasks.rake +44 -0
- data/test/crawlscope/audit_test.rb +165 -0
- data/test/crawlscope/cli_test.rb +157 -0
- data/test/crawlscope/configuration_test.rb +45 -0
- data/test/crawlscope/links_rule_test.rb +87 -0
- data/test/crawlscope/loader_test.rb +11 -0
- data/test/crawlscope/reporter_test.rb +50 -0
- data/test/crawlscope/schema_registry_test.rb +89 -0
- data/test/crawlscope/sitemap_test.rb +51 -0
- data/test/crawlscope/structured_data_audit_test.rb +118 -0
- data/test/crawlscope/structured_data_document_test.rb +28 -0
- data/test/crawlscope/structured_data_report_test.rb +37 -0
- data/test/crawlscope/structured_data_reporter_test.rb +32 -0
- data/test/crawlscope/structured_data_rule_test.rb +78 -0
- data/test/crawlscope/structured_data_writer_test.rb +32 -0
- data/test/crawlscope/task_test.rb +206 -0
- data/test/crawlscope/uniqueness_rule_test.rb +46 -0
- data/test/test_helper.rb +23 -0
- metadata +271 -0
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require "stringio"
|
|
4
|
+
require "test_helper"
|
|
5
|
+
|
|
6
|
+
class CrawlscopeStructuredDataReporterTest < Minitest::Test
|
|
7
|
+
def test_reports_failures_and_report_path
|
|
8
|
+
result = Crawlscope::StructuredData::Audit::Result.new(
|
|
9
|
+
entries: [
|
|
10
|
+
Crawlscope::StructuredData::Audit::Entry.new(
|
|
11
|
+
url: "https://example.com/article",
|
|
12
|
+
status: 200,
|
|
13
|
+
structured_items: [{source: "json-ld", data: {"@type" => "Article"}}],
|
|
14
|
+
errors: [{type: "Article", source: "json-ld", errors: [{field: "headline", issue: "is required"}]}],
|
|
15
|
+
fetch_error: nil,
|
|
16
|
+
content_type: "text/html",
|
|
17
|
+
skipped_reason: nil
|
|
18
|
+
)
|
|
19
|
+
]
|
|
20
|
+
)
|
|
21
|
+
io = StringIO.new
|
|
22
|
+
|
|
23
|
+
Crawlscope::StructuredData::Reporter.new(io: io, report_path: "/tmp/structured_data_report.json").report(result)
|
|
24
|
+
|
|
25
|
+
output = io.string
|
|
26
|
+
|
|
27
|
+
assert_includes output, "VALIDATION FAILED"
|
|
28
|
+
assert_includes output, "VALIDATION ERRORS (1):"
|
|
29
|
+
assert_includes output, "headline: is required"
|
|
30
|
+
assert_includes output, "/tmp/structured_data_report.json"
|
|
31
|
+
end
|
|
32
|
+
end
|
|
@@ -0,0 +1,78 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require "test_helper"
|
|
4
|
+
|
|
5
|
+
class CrawlscopeStructuredDataRuleTest < Minitest::Test
|
|
6
|
+
def test_reports_schema_errors_for_invalid_article_markup
|
|
7
|
+
issues = Crawlscope::IssueCollection.new
|
|
8
|
+
rule = Crawlscope::Rules::StructuredData.new
|
|
9
|
+
page = page(
|
|
10
|
+
url: "https://example.com/articles/test",
|
|
11
|
+
body: <<~HTML
|
|
12
|
+
<html>
|
|
13
|
+
<head>
|
|
14
|
+
<script type="application/ld+json">
|
|
15
|
+
{"@context":"https://schema.org","@type":"Article"}
|
|
16
|
+
</script>
|
|
17
|
+
</head>
|
|
18
|
+
<body>
|
|
19
|
+
<main><h1>Article</h1></main>
|
|
20
|
+
</body>
|
|
21
|
+
</html>
|
|
22
|
+
HTML
|
|
23
|
+
)
|
|
24
|
+
|
|
25
|
+
rule.call(
|
|
26
|
+
urls: [page.url],
|
|
27
|
+
pages: [page],
|
|
28
|
+
issues: issues,
|
|
29
|
+
context: {schema_registry: Crawlscope::SchemaRegistry.default}
|
|
30
|
+
)
|
|
31
|
+
|
|
32
|
+
assert_equal [:structured_data_schema_error], issues.to_a.map(&:code)
|
|
33
|
+
assert_includes issues.to_a.first.message, "headline"
|
|
34
|
+
end
|
|
35
|
+
|
|
36
|
+
def test_reports_parse_errors_for_invalid_json_ld
|
|
37
|
+
issues = Crawlscope::IssueCollection.new
|
|
38
|
+
rule = Crawlscope::Rules::StructuredData.new
|
|
39
|
+
page = page(
|
|
40
|
+
url: "https://example.com/articles/test",
|
|
41
|
+
body: <<~HTML
|
|
42
|
+
<html>
|
|
43
|
+
<head>
|
|
44
|
+
<script type="application/ld+json">
|
|
45
|
+
{"@context":"https://schema.org","@type":"Article"
|
|
46
|
+
</script>
|
|
47
|
+
</head>
|
|
48
|
+
</html>
|
|
49
|
+
HTML
|
|
50
|
+
)
|
|
51
|
+
|
|
52
|
+
rule.call(
|
|
53
|
+
urls: [page.url],
|
|
54
|
+
pages: [page],
|
|
55
|
+
issues: issues,
|
|
56
|
+
context: {schema_registry: Crawlscope::SchemaRegistry.default}
|
|
57
|
+
)
|
|
58
|
+
|
|
59
|
+
assert_equal [:structured_data_parse_error], issues.to_a.map(&:code)
|
|
60
|
+
end
|
|
61
|
+
|
|
62
|
+
private
|
|
63
|
+
|
|
64
|
+
def page(url:, body:)
|
|
65
|
+
doc = Nokogiri::HTML(body)
|
|
66
|
+
|
|
67
|
+
Crawlscope::Page.new(
|
|
68
|
+
url: url,
|
|
69
|
+
normalized_url: url,
|
|
70
|
+
final_url: url,
|
|
71
|
+
normalized_final_url: url,
|
|
72
|
+
status: 200,
|
|
73
|
+
headers: {"content-type" => "text/html"},
|
|
74
|
+
body: body,
|
|
75
|
+
doc: doc
|
|
76
|
+
)
|
|
77
|
+
end
|
|
78
|
+
end
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require "json"
|
|
4
|
+
require "test_helper"
|
|
5
|
+
|
|
6
|
+
class CrawlscopeStructuredDataWriterTest < Minitest::Test
|
|
7
|
+
def test_writes_json_report
|
|
8
|
+
result = Crawlscope::StructuredData::Audit::Result.new(
|
|
9
|
+
entries: [
|
|
10
|
+
Crawlscope::StructuredData::Audit::Entry.new(
|
|
11
|
+
url: "https://example.com/article",
|
|
12
|
+
status: 200,
|
|
13
|
+
structured_items: [{source: "json-ld", data: {"@type" => "Article"}}],
|
|
14
|
+
errors: [],
|
|
15
|
+
fetch_error: nil,
|
|
16
|
+
content_type: "text/html",
|
|
17
|
+
skipped_reason: nil
|
|
18
|
+
)
|
|
19
|
+
]
|
|
20
|
+
)
|
|
21
|
+
tmp_dir = Dir.mktmpdir
|
|
22
|
+
path = File.join(tmp_dir, "structured_data_report.json")
|
|
23
|
+
|
|
24
|
+
Crawlscope::StructuredData::Writer.new(path: path).write(result)
|
|
25
|
+
|
|
26
|
+
payload = JSON.parse(File.read(path))
|
|
27
|
+
assert payload["generated_at"]
|
|
28
|
+
assert_equal 1, payload["results"]["https://example.com/article"]["json_ld_count"]
|
|
29
|
+
ensure
|
|
30
|
+
FileUtils.rm_rf(tmp_dir) if tmp_dir
|
|
31
|
+
end
|
|
32
|
+
end
|
|
@@ -0,0 +1,206 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require "test_helper"
|
|
4
|
+
|
|
5
|
+
class CrawlscopeTaskTest < Minitest::Test
|
|
6
|
+
FakeResult = Data.define(:reported) do
|
|
7
|
+
def ok?
|
|
8
|
+
true
|
|
9
|
+
end
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
class FakeReporter
|
|
13
|
+
attr_reader :result
|
|
14
|
+
|
|
15
|
+
def report(result)
|
|
16
|
+
@result = result
|
|
17
|
+
end
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
class FakeAudit
|
|
21
|
+
def initialize(result:)
|
|
22
|
+
@result = result
|
|
23
|
+
end
|
|
24
|
+
|
|
25
|
+
def call
|
|
26
|
+
@result
|
|
27
|
+
end
|
|
28
|
+
end
|
|
29
|
+
|
|
30
|
+
class FakeConfiguration
|
|
31
|
+
attr_reader :base_url, :received_arguments, :sitemap_path
|
|
32
|
+
|
|
33
|
+
def initialize(result:, base_url: "https://example.com", sitemap_path: "/tmp/sitemap.xml")
|
|
34
|
+
@result = result
|
|
35
|
+
@base_url = base_url
|
|
36
|
+
@sitemap_path = sitemap_path
|
|
37
|
+
end
|
|
38
|
+
|
|
39
|
+
def audit(base_url:, sitemap_path:, rule_names:)
|
|
40
|
+
@received_arguments = {
|
|
41
|
+
base_url: base_url,
|
|
42
|
+
sitemap_path: sitemap_path,
|
|
43
|
+
rule_names: rule_names
|
|
44
|
+
}
|
|
45
|
+
|
|
46
|
+
FakeAudit.new(result: @result)
|
|
47
|
+
end
|
|
48
|
+
end
|
|
49
|
+
|
|
50
|
+
class LdjsonConfiguration
|
|
51
|
+
attr_reader :output
|
|
52
|
+
|
|
53
|
+
def initialize(output:, browser:)
|
|
54
|
+
@output = output
|
|
55
|
+
@browser = browser
|
|
56
|
+
end
|
|
57
|
+
|
|
58
|
+
def browser_factory
|
|
59
|
+
-> { @browser }
|
|
60
|
+
end
|
|
61
|
+
|
|
62
|
+
def network_idle_timeout_seconds
|
|
63
|
+
5
|
|
64
|
+
end
|
|
65
|
+
|
|
66
|
+
def renderer
|
|
67
|
+
:browser
|
|
68
|
+
end
|
|
69
|
+
|
|
70
|
+
def schema_registry
|
|
71
|
+
Crawlscope::SchemaRegistry.default
|
|
72
|
+
end
|
|
73
|
+
|
|
74
|
+
def scroll_page?
|
|
75
|
+
false
|
|
76
|
+
end
|
|
77
|
+
|
|
78
|
+
def timeout_seconds
|
|
79
|
+
20
|
|
80
|
+
end
|
|
81
|
+
end
|
|
82
|
+
|
|
83
|
+
class FakeBrowser
|
|
84
|
+
attr_reader :closed
|
|
85
|
+
|
|
86
|
+
def initialize(page:)
|
|
87
|
+
@page = page
|
|
88
|
+
@closed = false
|
|
89
|
+
end
|
|
90
|
+
|
|
91
|
+
def close
|
|
92
|
+
@closed = true
|
|
93
|
+
end
|
|
94
|
+
|
|
95
|
+
def fetch(_url)
|
|
96
|
+
@page
|
|
97
|
+
end
|
|
98
|
+
end
|
|
99
|
+
|
|
100
|
+
def test_validate_passes_rule_names_to_configuration_audit
|
|
101
|
+
result = FakeResult.new(reported: true)
|
|
102
|
+
configuration = FakeConfiguration.new(result: result)
|
|
103
|
+
reporter = FakeReporter.new
|
|
104
|
+
|
|
105
|
+
task = Crawlscope::Task.new(configuration: configuration, reporter: reporter)
|
|
106
|
+
returned_result = task.validate(rule_names: "links")
|
|
107
|
+
|
|
108
|
+
assert_equal(
|
|
109
|
+
{
|
|
110
|
+
base_url: "https://example.com",
|
|
111
|
+
sitemap_path: "/tmp/sitemap.xml",
|
|
112
|
+
rule_names: "links"
|
|
113
|
+
},
|
|
114
|
+
configuration.received_arguments
|
|
115
|
+
)
|
|
116
|
+
assert_same result, reporter.result
|
|
117
|
+
assert_same result, returned_result
|
|
118
|
+
end
|
|
119
|
+
|
|
120
|
+
def test_validate_defaults_to_base_url_sitemap_when_not_configured
|
|
121
|
+
result = FakeResult.new(reported: true)
|
|
122
|
+
configuration = FakeConfiguration.new(result: result, base_url: "https://example.com", sitemap_path: nil)
|
|
123
|
+
reporter = FakeReporter.new
|
|
124
|
+
|
|
125
|
+
Crawlscope::Task.new(configuration: configuration, reporter: reporter).validate
|
|
126
|
+
|
|
127
|
+
assert_equal(
|
|
128
|
+
{
|
|
129
|
+
base_url: "https://example.com",
|
|
130
|
+
sitemap_path: "https://example.com/sitemap.xml",
|
|
131
|
+
rule_names: nil
|
|
132
|
+
},
|
|
133
|
+
configuration.received_arguments
|
|
134
|
+
)
|
|
135
|
+
end
|
|
136
|
+
|
|
137
|
+
def test_validate_prefers_local_sitemap_for_localhost
|
|
138
|
+
result = FakeResult.new(reported: true)
|
|
139
|
+
configuration = FakeConfiguration.new(result: result, base_url: "http://localhost:3000", sitemap_path: nil)
|
|
140
|
+
reporter = FakeReporter.new
|
|
141
|
+
tmp_dir = Dir.mktmpdir
|
|
142
|
+
sitemap_path = File.join(tmp_dir, "public", "sitemap.xml")
|
|
143
|
+
FileUtils.mkdir_p(File.dirname(sitemap_path))
|
|
144
|
+
File.write(sitemap_path, "<urlset></urlset>")
|
|
145
|
+
|
|
146
|
+
Dir.chdir(tmp_dir) do
|
|
147
|
+
Crawlscope::Task.new(configuration: configuration, reporter: reporter).validate
|
|
148
|
+
end
|
|
149
|
+
|
|
150
|
+
assert_equal(
|
|
151
|
+
{
|
|
152
|
+
base_url: "http://localhost:3000",
|
|
153
|
+
sitemap_path: sitemap_path,
|
|
154
|
+
rule_names: nil
|
|
155
|
+
},
|
|
156
|
+
configuration.received_arguments
|
|
157
|
+
)
|
|
158
|
+
ensure
|
|
159
|
+
FileUtils.rm_rf(tmp_dir) if tmp_dir
|
|
160
|
+
end
|
|
161
|
+
|
|
162
|
+
def test_validate_ldjson_uses_real_audit_and_writes_report
|
|
163
|
+
body = <<~HTML
|
|
164
|
+
<html>
|
|
165
|
+
<head>
|
|
166
|
+
<script type="application/ld+json">
|
|
167
|
+
{"@type":"WebSite","name":"Example","url":"https://example.com"}
|
|
168
|
+
</script>
|
|
169
|
+
</head>
|
|
170
|
+
</html>
|
|
171
|
+
HTML
|
|
172
|
+
page = Crawlscope::Page.new(
|
|
173
|
+
url: "https://example.com",
|
|
174
|
+
normalized_url: "https://example.com",
|
|
175
|
+
final_url: "https://example.com",
|
|
176
|
+
normalized_final_url: "https://example.com",
|
|
177
|
+
status: 200,
|
|
178
|
+
headers: {"content-type" => "text/html"},
|
|
179
|
+
body: body,
|
|
180
|
+
doc: Nokogiri::HTML(body)
|
|
181
|
+
)
|
|
182
|
+
browser = FakeBrowser.new(page: page)
|
|
183
|
+
output = StringIO.new
|
|
184
|
+
configuration = LdjsonConfiguration.new(output: output, browser: browser)
|
|
185
|
+
report_dir = Dir.mktmpdir
|
|
186
|
+
report_path = File.join(report_dir, "structured-data.json")
|
|
187
|
+
|
|
188
|
+
result = Crawlscope::Task.new(configuration: configuration).validate_ldjson(
|
|
189
|
+
urls: [page.url],
|
|
190
|
+
debug: true,
|
|
191
|
+
report_path: report_path,
|
|
192
|
+
summary: true
|
|
193
|
+
)
|
|
194
|
+
|
|
195
|
+
assert result.ok?
|
|
196
|
+
assert browser.closed
|
|
197
|
+
assert File.exist?(report_path)
|
|
198
|
+
assert_includes File.read(report_path), "https://example.com"
|
|
199
|
+
assert_includes output.string, "JavaScript mode enabled (Ferrum)"
|
|
200
|
+
assert_includes output.string, "Validating JSON-LD on 1 URL(s)"
|
|
201
|
+
assert_includes output.string, "All valid!"
|
|
202
|
+
assert_includes output.string, "All 1 URLs passed validation."
|
|
203
|
+
ensure
|
|
204
|
+
FileUtils.rm_rf(report_dir) if report_dir
|
|
205
|
+
end
|
|
206
|
+
end
|
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require "test_helper"
|
|
4
|
+
|
|
5
|
+
class CrawlscopeUniquenessRuleTest < Minitest::Test
|
|
6
|
+
def test_reports_duplicate_title_description_and_content
|
|
7
|
+
issues = Crawlscope::IssueCollection.new
|
|
8
|
+
rule = Crawlscope::Rules::Uniqueness.new
|
|
9
|
+
pages = [
|
|
10
|
+
page(url: "https://example.com/a"),
|
|
11
|
+
page(url: "https://example.com/b")
|
|
12
|
+
]
|
|
13
|
+
|
|
14
|
+
rule.call(urls: pages.map(&:url), pages: pages, issues: issues, context: {})
|
|
15
|
+
|
|
16
|
+
assert_equal %i[duplicate_content_fingerprint duplicate_meta_description duplicate_title].sort, issues.to_a.map(&:code).sort
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
private
|
|
20
|
+
|
|
21
|
+
def page(url:)
|
|
22
|
+
repeated_text = ("Useful content " * 30).strip
|
|
23
|
+
body = <<~HTML
|
|
24
|
+
<html>
|
|
25
|
+
<head>
|
|
26
|
+
<title>Example Title</title>
|
|
27
|
+
<meta name="description" content="Example description">
|
|
28
|
+
</head>
|
|
29
|
+
<body>
|
|
30
|
+
<main>#{repeated_text}</main>
|
|
31
|
+
</body>
|
|
32
|
+
</html>
|
|
33
|
+
HTML
|
|
34
|
+
|
|
35
|
+
Crawlscope::Page.new(
|
|
36
|
+
url: url,
|
|
37
|
+
normalized_url: url,
|
|
38
|
+
final_url: url,
|
|
39
|
+
normalized_final_url: url,
|
|
40
|
+
status: 200,
|
|
41
|
+
headers: {"content-type" => "text/html"},
|
|
42
|
+
body: body,
|
|
43
|
+
doc: Nokogiri::HTML(body)
|
|
44
|
+
)
|
|
45
|
+
end
|
|
46
|
+
end
|
data/test/test_helper.rb
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
$LOAD_PATH.unshift File.expand_path("../lib", __dir__)
|
|
4
|
+
|
|
5
|
+
require "simplecov"
|
|
6
|
+
|
|
7
|
+
SimpleCov.start do
|
|
8
|
+
enable_coverage :branch
|
|
9
|
+
add_filter "/test/"
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
require "minitest/autorun"
|
|
13
|
+
require "tmpdir"
|
|
14
|
+
require "date"
|
|
15
|
+
require "fileutils"
|
|
16
|
+
require "nokogiri"
|
|
17
|
+
require "webmock/minitest"
|
|
18
|
+
|
|
19
|
+
require "crawlscope"
|
|
20
|
+
|
|
21
|
+
if defined?(JSON::Validator)
|
|
22
|
+
JSON::Validator.use_multi_json = false
|
|
23
|
+
end
|
metadata
ADDED
|
@@ -0,0 +1,271 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: crawlscope
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Paulo Fidalgo
|
|
8
|
+
- Ethos Link
|
|
9
|
+
bindir: exe
|
|
10
|
+
cert_chain: []
|
|
11
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: concurrent-ruby
|
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
|
16
|
+
requirements:
|
|
17
|
+
- - ">="
|
|
18
|
+
- !ruby/object:Gem::Version
|
|
19
|
+
version: '1.3'
|
|
20
|
+
type: :runtime
|
|
21
|
+
prerelease: false
|
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
23
|
+
requirements:
|
|
24
|
+
- - ">="
|
|
25
|
+
- !ruby/object:Gem::Version
|
|
26
|
+
version: '1.3'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: faraday
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - ">="
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '2.0'
|
|
34
|
+
type: :runtime
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - ">="
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '2.0'
|
|
41
|
+
- !ruby/object:Gem::Dependency
|
|
42
|
+
name: faraday-follow_redirects
|
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
|
44
|
+
requirements:
|
|
45
|
+
- - ">="
|
|
46
|
+
- !ruby/object:Gem::Version
|
|
47
|
+
version: '0.3'
|
|
48
|
+
type: :runtime
|
|
49
|
+
prerelease: false
|
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
51
|
+
requirements:
|
|
52
|
+
- - ">="
|
|
53
|
+
- !ruby/object:Gem::Version
|
|
54
|
+
version: '0.3'
|
|
55
|
+
- !ruby/object:Gem::Dependency
|
|
56
|
+
name: json-schema
|
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
|
58
|
+
requirements:
|
|
59
|
+
- - ">="
|
|
60
|
+
- !ruby/object:Gem::Version
|
|
61
|
+
version: '5.0'
|
|
62
|
+
type: :runtime
|
|
63
|
+
prerelease: false
|
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
65
|
+
requirements:
|
|
66
|
+
- - ">="
|
|
67
|
+
- !ruby/object:Gem::Version
|
|
68
|
+
version: '5.0'
|
|
69
|
+
- !ruby/object:Gem::Dependency
|
|
70
|
+
name: nokogiri
|
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
|
72
|
+
requirements:
|
|
73
|
+
- - ">="
|
|
74
|
+
- !ruby/object:Gem::Version
|
|
75
|
+
version: '1.16'
|
|
76
|
+
type: :runtime
|
|
77
|
+
prerelease: false
|
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
79
|
+
requirements:
|
|
80
|
+
- - ">="
|
|
81
|
+
- !ruby/object:Gem::Version
|
|
82
|
+
version: '1.16'
|
|
83
|
+
- !ruby/object:Gem::Dependency
|
|
84
|
+
name: railties
|
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
|
86
|
+
requirements:
|
|
87
|
+
- - ">="
|
|
88
|
+
- !ruby/object:Gem::Version
|
|
89
|
+
version: '7.1'
|
|
90
|
+
type: :runtime
|
|
91
|
+
prerelease: false
|
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
93
|
+
requirements:
|
|
94
|
+
- - ">="
|
|
95
|
+
- !ruby/object:Gem::Version
|
|
96
|
+
version: '7.1'
|
|
97
|
+
- !ruby/object:Gem::Dependency
|
|
98
|
+
name: zeitwerk
|
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
|
100
|
+
requirements:
|
|
101
|
+
- - ">="
|
|
102
|
+
- !ruby/object:Gem::Version
|
|
103
|
+
version: '2.6'
|
|
104
|
+
type: :runtime
|
|
105
|
+
prerelease: false
|
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
107
|
+
requirements:
|
|
108
|
+
- - ">="
|
|
109
|
+
- !ruby/object:Gem::Version
|
|
110
|
+
version: '2.6'
|
|
111
|
+
- !ruby/object:Gem::Dependency
|
|
112
|
+
name: minitest
|
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
|
114
|
+
requirements:
|
|
115
|
+
- - "~>"
|
|
116
|
+
- !ruby/object:Gem::Version
|
|
117
|
+
version: '5.0'
|
|
118
|
+
type: :development
|
|
119
|
+
prerelease: false
|
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
121
|
+
requirements:
|
|
122
|
+
- - "~>"
|
|
123
|
+
- !ruby/object:Gem::Version
|
|
124
|
+
version: '5.0'
|
|
125
|
+
- !ruby/object:Gem::Dependency
|
|
126
|
+
name: rake
|
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
|
128
|
+
requirements:
|
|
129
|
+
- - "~>"
|
|
130
|
+
- !ruby/object:Gem::Version
|
|
131
|
+
version: '13.0'
|
|
132
|
+
type: :development
|
|
133
|
+
prerelease: false
|
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
135
|
+
requirements:
|
|
136
|
+
- - "~>"
|
|
137
|
+
- !ruby/object:Gem::Version
|
|
138
|
+
version: '13.0'
|
|
139
|
+
- !ruby/object:Gem::Dependency
|
|
140
|
+
name: simplecov
|
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
|
142
|
+
requirements:
|
|
143
|
+
- - "~>"
|
|
144
|
+
- !ruby/object:Gem::Version
|
|
145
|
+
version: '0.22'
|
|
146
|
+
type: :development
|
|
147
|
+
prerelease: false
|
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
149
|
+
requirements:
|
|
150
|
+
- - "~>"
|
|
151
|
+
- !ruby/object:Gem::Version
|
|
152
|
+
version: '0.22'
|
|
153
|
+
- !ruby/object:Gem::Dependency
|
|
154
|
+
name: standard
|
|
155
|
+
requirement: !ruby/object:Gem::Requirement
|
|
156
|
+
requirements:
|
|
157
|
+
- - "~>"
|
|
158
|
+
- !ruby/object:Gem::Version
|
|
159
|
+
version: '1.0'
|
|
160
|
+
type: :development
|
|
161
|
+
prerelease: false
|
|
162
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
163
|
+
requirements:
|
|
164
|
+
- - "~>"
|
|
165
|
+
- !ruby/object:Gem::Version
|
|
166
|
+
version: '1.0'
|
|
167
|
+
- !ruby/object:Gem::Dependency
|
|
168
|
+
name: webmock
|
|
169
|
+
requirement: !ruby/object:Gem::Requirement
|
|
170
|
+
requirements:
|
|
171
|
+
- - "~>"
|
|
172
|
+
- !ruby/object:Gem::Version
|
|
173
|
+
version: '3.0'
|
|
174
|
+
type: :development
|
|
175
|
+
prerelease: false
|
|
176
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
177
|
+
requirements:
|
|
178
|
+
- - "~>"
|
|
179
|
+
- !ruby/object:Gem::Version
|
|
180
|
+
version: '3.0'
|
|
181
|
+
description: A small Ruby gem for sitemap-driven SEO validation with structured issues,
|
|
182
|
+
configurable rules and schema registries, optional browser rendering, and Rails
|
|
183
|
+
rake task integration.
|
|
184
|
+
email:
|
|
185
|
+
- devel@ethos-link.com
|
|
186
|
+
executables:
|
|
187
|
+
- crawlscope
|
|
188
|
+
extensions: []
|
|
189
|
+
extra_rdoc_files: []
|
|
190
|
+
files:
|
|
191
|
+
- CHANGELOG.md
|
|
192
|
+
- LICENSE.txt
|
|
193
|
+
- README.md
|
|
194
|
+
- exe/crawlscope
|
|
195
|
+
- lib/crawlscope.rb
|
|
196
|
+
- lib/crawlscope/audit.rb
|
|
197
|
+
- lib/crawlscope/browser.rb
|
|
198
|
+
- lib/crawlscope/cli.rb
|
|
199
|
+
- lib/crawlscope/configuration.rb
|
|
200
|
+
- lib/crawlscope/crawler.rb
|
|
201
|
+
- lib/crawlscope/http.rb
|
|
202
|
+
- lib/crawlscope/issue.rb
|
|
203
|
+
- lib/crawlscope/issue_collection.rb
|
|
204
|
+
- lib/crawlscope/page.rb
|
|
205
|
+
- lib/crawlscope/railtie.rb
|
|
206
|
+
- lib/crawlscope/reporter.rb
|
|
207
|
+
- lib/crawlscope/result.rb
|
|
208
|
+
- lib/crawlscope/rule_registry.rb
|
|
209
|
+
- lib/crawlscope/rules/links.rb
|
|
210
|
+
- lib/crawlscope/rules/metadata.rb
|
|
211
|
+
- lib/crawlscope/rules/structured_data.rb
|
|
212
|
+
- lib/crawlscope/rules/uniqueness.rb
|
|
213
|
+
- lib/crawlscope/schema_registry.rb
|
|
214
|
+
- lib/crawlscope/sitemap.rb
|
|
215
|
+
- lib/crawlscope/structured_data/audit.rb
|
|
216
|
+
- lib/crawlscope/structured_data/document.rb
|
|
217
|
+
- lib/crawlscope/structured_data/report.rb
|
|
218
|
+
- lib/crawlscope/structured_data/reporter.rb
|
|
219
|
+
- lib/crawlscope/structured_data/writer.rb
|
|
220
|
+
- lib/crawlscope/task.rb
|
|
221
|
+
- lib/crawlscope/url.rb
|
|
222
|
+
- lib/crawlscope/version.rb
|
|
223
|
+
- lib/tasks/crawlscope_tasks.rake
|
|
224
|
+
- test/crawlscope/audit_test.rb
|
|
225
|
+
- test/crawlscope/cli_test.rb
|
|
226
|
+
- test/crawlscope/configuration_test.rb
|
|
227
|
+
- test/crawlscope/links_rule_test.rb
|
|
228
|
+
- test/crawlscope/loader_test.rb
|
|
229
|
+
- test/crawlscope/reporter_test.rb
|
|
230
|
+
- test/crawlscope/schema_registry_test.rb
|
|
231
|
+
- test/crawlscope/sitemap_test.rb
|
|
232
|
+
- test/crawlscope/structured_data_audit_test.rb
|
|
233
|
+
- test/crawlscope/structured_data_document_test.rb
|
|
234
|
+
- test/crawlscope/structured_data_report_test.rb
|
|
235
|
+
- test/crawlscope/structured_data_reporter_test.rb
|
|
236
|
+
- test/crawlscope/structured_data_rule_test.rb
|
|
237
|
+
- test/crawlscope/structured_data_writer_test.rb
|
|
238
|
+
- test/crawlscope/task_test.rb
|
|
239
|
+
- test/crawlscope/uniqueness_rule_test.rb
|
|
240
|
+
- test/test_helper.rb
|
|
241
|
+
homepage: https://www.ethos-link.com/opensource/crawlscope
|
|
242
|
+
licenses:
|
|
243
|
+
- MIT
|
|
244
|
+
metadata:
|
|
245
|
+
homepage_uri: https://www.ethos-link.com/opensource/crawlscope
|
|
246
|
+
source_code_uri: https://github.com/ethos-link/crawlscope
|
|
247
|
+
bug_tracker_uri: https://github.com/ethos-link/crawlscope/issues
|
|
248
|
+
changelog_uri: https://github.com/ethos-link/crawlscope/blob/main/CHANGELOG.md
|
|
249
|
+
documentation_uri: https://github.com/ethos-link/crawlscope/blob/main/README.md
|
|
250
|
+
funding_uri: https://www.reviato.com/
|
|
251
|
+
github_repo: ssh://github.com/ethos-link/crawlscope
|
|
252
|
+
allowed_push_host: https://rubygems.org
|
|
253
|
+
rubygems_mfa_required: 'true'
|
|
254
|
+
rdoc_options: []
|
|
255
|
+
require_paths:
|
|
256
|
+
- lib
|
|
257
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
258
|
+
requirements:
|
|
259
|
+
- - ">="
|
|
260
|
+
- !ruby/object:Gem::Version
|
|
261
|
+
version: 3.2.0
|
|
262
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
263
|
+
requirements:
|
|
264
|
+
- - ">="
|
|
265
|
+
- !ruby/object:Gem::Version
|
|
266
|
+
version: '0'
|
|
267
|
+
requirements: []
|
|
268
|
+
rubygems_version: 4.0.6
|
|
269
|
+
specification_version: 4
|
|
270
|
+
summary: Audit sitemap URLs for metadata, structured data, uniqueness, and links
|
|
271
|
+
test_files: []
|