metainspector 4.3.0 → 4.3.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (21) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +9 -3
  3. data/lib/meta_inspector/parsers/texts.rb +1 -0
  4. data/lib/meta_inspector/request.rb +1 -0
  5. data/lib/meta_inspector/version.rb +1 -1
  6. data/meta_inspector.gemspec +1 -1
  7. data/spec/document_spec.rb +18 -18
  8. data/spec/exception_log_spec.rb +7 -7
  9. data/spec/fixtures/no-content-type.response +14 -0
  10. data/spec/fixtures/title_not_present.response +21 -0
  11. data/spec/meta_inspector/images_spec.rb +28 -28
  12. data/spec/meta_inspector/links_spec.rb +38 -38
  13. data/spec/meta_inspector/meta_inspector_spec.rb +1 -1
  14. data/spec/meta_inspector/meta_tags_spec.rb +9 -9
  15. data/spec/meta_inspector/redirections_spec.rb +5 -5
  16. data/spec/meta_inspector/texts_spec.rb +14 -9
  17. data/spec/parser_spec.rb +2 -2
  18. data/spec/request_spec.rb +15 -9
  19. data/spec/spec_helper.rb +4 -1
  20. data/spec/url_spec.rb +16 -16
  21. metadata +8 -6
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 522b262bf637695bc4a4803c6001fd9c5407363a
4
- data.tar.gz: 11607a5a8a63de10d4ad74bf6b49a14e65d83139
3
+ metadata.gz: 521f4a333c421caaad3bcd737aecd9899d4be801
4
+ data.tar.gz: c97c25d293d3fc8f49a1e39c85d93ac9c0a65ba7
5
5
  SHA512:
6
- metadata.gz: 333e9453fc03ff78a0ad3428f1251b0ed3a4e0753f9a1b6299fffea59ff4ba79b97ac38b0903e8ddd09a24a5fd3f03bc4ae06fdc1ea30e90bf752c72f844ab57
7
- data.tar.gz: a5b3ae17b9abb9bee136af342185e711e83869eea779f935cd42b47805528c9a5a5fdba51529bdf345b5e03de8ad35ac69ef4105be73b4e0bb0d5ed4ac30f5ca
6
+ metadata.gz: b0f0c5914c5fe9c9320814c9d77506ccc33a29270fc3c0e2347d6102ad4a4d79f98421a4ca94105ac7cfb3d26c92ef023d4160ffb27eb0ab84bc7f1711e9f648
7
+ data.tar.gz: ae59d9a9a6c2d142164c744f47f9b2b9f900e46582fd2748bf3cd536ee4502294a384700a1d1d650b24167f4cbb4439c4e24eb395b8fbce3e9fdd8d402f93e1b
data/README.md CHANGED
@@ -406,15 +406,21 @@ $ irb
406
406
  => "/plans-and-pricing"
407
407
  ```
408
408
 
409
- ## ZOMG Fork! Thank you!
409
+ ## Contributing guidelines
410
410
 
411
- You're welcome to fork this project and send pull requests. Just remember to include specs.
411
+ You're more than welcome to fork this project and send pull requests. Just remember to:
412
+
413
+ * Create a topic branch for your changes.
414
+ * Add specs.
415
+ * Keep your fake responses as small as possible. For each change in `spec/fixtures`, a comment should be included explaining why it's needed.
416
+ * Update `version.rb`, following the [semantic versioning convention](http://semver.org/).
417
+ * Update `README.md` if needed (for example, when you're adding or changing a feature).
412
418
 
413
419
  Thanks to all the contributors:
414
420
 
415
421
  [https://github.com/jaimeiniesta/metainspector/graphs/contributors](https://github.com/jaimeiniesta/metainspector/graphs/contributors)
416
422
 
417
- You are more than welcome to come chat with us on our [Gitter room](https://gitter.im/jaimeiniesta/metainspector) and [Google group](https://groups.google.com/forum/#!forum/metainspector).
423
+ You can also come to chat with us on our [Gitter room](https://gitter.im/jaimeiniesta/metainspector) and [Google group](https://groups.google.com/forum/#!forum/metainspector).
418
424
 
419
425
  ## Related projects
420
426
 
data/lib/meta_inspector/parsers/texts.rb CHANGED
@@ -20,6 +20,7 @@ module MetaInspector
20
20
  candidates.flatten!
21
21
  candidates.map! { |c| (c.respond_to? :inner_text) ? c.inner_text : c }
22
22
  candidates.compact!
23
+ return nil if candidates.empty?
23
24
  candidates.map! { |c| c.gsub(/\s+/, ' ') }
24
25
  candidates.uniq!
25
26
  candidates.sort_by! { |t| -t.length }
data/lib/meta_inspector/request.rb CHANGED
@@ -29,6 +29,7 @@ module MetaInspector
29
29
  end
30
30
 
31
31
  def content_type
32
+ return nil if response.headers['content-type'].nil?
32
33
  response.headers['content-type'].split(';')[0] if response
33
34
  end
34
35
 
data/lib/meta_inspector/version.rb CHANGED
@@ -1,3 +1,3 @@
1
1
  module MetaInspector
2
- VERSION = "4.3.0"
2
+ VERSION = "4.3.1"
3
3
  end
data/meta_inspector.gemspec CHANGED
@@ -21,7 +21,7 @@ Gem::Specification.new do |gem|
21
21
  gem.add_dependency 'addressable', '~> 2.3.5'
22
22
  gem.add_dependency 'fastimage'
23
23
 
24
- gem.add_development_dependency 'rspec', '2.14.1'
24
+ gem.add_development_dependency 'rspec', '~> 3.0'
25
25
  gem.add_development_dependency 'fakeweb', '1.3.0'
26
26
  gem.add_development_dependency 'webmock'
27
27
  gem.add_development_dependency 'awesome_print'
data/spec/document_spec.rb CHANGED
@@ -5,21 +5,21 @@ describe MetaInspector::Document do
5
5
  let(:doc) { MetaInspector::Document.new('http://cnn.com/', :document => "<html><head><title>Hello From Passed Html</title><a href='/hello'>Hello link</a></head><body></body></html>") }
6
6
 
7
7
  it "should get correct links when the url html is passed as an option" do
8
- doc.links.internal.should == ["http://cnn.com/hello"]
8
+ expect(doc.links.internal).to eq(["http://cnn.com/hello"])
9
9
  end
10
10
 
11
11
  it "should get the title" do
12
- doc.title.should == "Hello From Passed Html"
12
+ expect(doc.title).to eq("Hello From Passed Html")
13
13
  end
14
14
  end
15
15
 
16
16
  it "should return a String as to_s" do
17
- MetaInspector::Document.new('http://pagerankalert.com').to_s.class.should == String
17
+ expect(MetaInspector::Document.new('http://pagerankalert.com').to_s.class).to eq(String)
18
18
  end
19
19
 
20
20
  it "should return a Hash with all the values set" do
21
21
  doc = MetaInspector::Document.new('http://pagerankalert.com')
22
- doc.to_hash.should == {
22
+ expect(doc.to_hash).to eq({
23
23
  "url" => "http://pagerankalert.com/",
24
24
  "scheme" => "http",
25
25
  "host" => "pagerankalert.com",
@@ -71,28 +71,28 @@ describe MetaInspector::Document do
71
71
  "via" => "1.1 varnish"
72
72
  }
73
73
  }
74
- }
74
+ })
75
75
  end
76
76
 
77
77
  describe 'exception handling' do
78
78
  let(:logger) { MetaInspector::ExceptionLog.new }
79
79
 
80
80
  it "should parse images when parse_html_content_type_only is not specified" do
81
- logger.should_not receive(:<<)
81
+ expect(logger).not_to receive(:<<)
82
82
 
83
83
  image_url = MetaInspector::Document.new('http://pagerankalert.com/image.png', exception_log: logger)
84
84
  image_url.title
85
85
  end
86
86
 
87
87
  it "should parse images when parse_html_content_type_only is false" do
88
- logger.should_not receive(:<<)
88
+ expect(logger).not_to receive(:<<)
89
89
 
90
90
  image_url = MetaInspector::Document.new('http://pagerankalert.com/image.png', html_content_only: false, exception_log: logger)
91
91
  image_url.title
92
92
  end
93
93
 
94
94
  it "should handle errors when content is image/jpeg and html_content_type_only is true" do
95
- logger.should_receive(:<<).with(an_instance_of(RuntimeError))
95
+ expect(logger).to receive(:<<).with(an_instance_of(RuntimeError))
96
96
 
97
97
  image_url = MetaInspector::Document.new('http://pagerankalert.com/image.png', html_content_only: true, exception_log: logger)
98
98
 
@@ -100,7 +100,7 @@ describe MetaInspector::Document do
100
100
  end
101
101
 
102
102
  it "should handle errors when content is not text/html and html_content_type_only is true" do
103
- logger.should_receive(:<<).with(an_instance_of(RuntimeError))
103
+ expect(logger).to receive(:<<).with(an_instance_of(RuntimeError))
104
104
 
105
105
  tar_url = MetaInspector::Document.new('http://pagerankalert.com/file.tar.gz', html_content_only: true, exception_log: logger)
106
106
 
@@ -114,11 +114,11 @@ describe MetaInspector::Document do
114
114
  end
115
115
 
116
116
  it 'stores the exceptions' do
117
- @bad_request.exceptions.should_not be_empty
117
+ expect(@bad_request.exceptions).not_to be_empty
118
118
  end
119
119
 
120
120
  it 'makes ok? to return false' do
121
- @bad_request.should_not be_ok
121
+ expect(@bad_request).not_to be_ok
122
122
  end
123
123
  end
124
124
 
@@ -136,7 +136,7 @@ describe MetaInspector::Document do
136
136
  bad_request.title
137
137
 
138
138
  $stderr.rewind
139
- $stderr.string.chomp.should eq("The url provided contains image/png content instead of text/html content")
139
+ expect($stderr.string.chomp).to eq("The url provided contains image/png content instead of text/html content")
140
140
  end
141
141
 
142
142
  it 'does not raise an exception' do
@@ -161,8 +161,8 @@ describe MetaInspector::Document do
161
161
  expected_headers = {'User-Agent' => "MetaInspector/#{MetaInspector::VERSION} (+https://github.com/jaimeiniesta/metainspector)"}
162
162
 
163
163
  headers = {}
164
- headers.should_receive(:merge!).with(expected_headers)
165
- Faraday::Connection.any_instance.stub(:headers){headers}
164
+ expect(headers).to receive(:merge!).with(expected_headers)
165
+ allow_any_instance_of(Faraday::Connection).to receive(:headers){headers}
166
166
  MetaInspector::Document.new(url)
167
167
  end
168
168
 
@@ -171,19 +171,19 @@ describe MetaInspector::Document do
171
171
  headers = {'User-Agent' => 'Mozilla', 'Referer' => 'https://github.com/'}
172
172
 
173
173
  headers = {}
174
- headers.should_receive(:merge!).with(headers)
175
- Faraday::Connection.any_instance.stub(:headers){headers}
174
+ expect(headers).to receive(:merge!).with(headers)
175
+ allow_any_instance_of(Faraday::Connection).to receive(:headers){headers}
176
176
  MetaInspector::Document.new(url, headers: headers)
177
177
  end
178
178
  end
179
179
 
180
180
  describe 'url normalization' do
181
181
  it 'should normalize by default' do
182
- MetaInspector.new('http://example.com/%EF%BD%9E').url.should == 'http://example.com/~'
182
+ expect(MetaInspector.new('http://example.com/%EF%BD%9E').url).to eq('http://example.com/~')
183
183
  end
184
184
 
185
185
  it 'should not normalize if the normalize_url option is false' do
186
- MetaInspector.new('http://example.com/%EF%BD%9E', normalize_url: false).url.should == 'http://example.com/%EF%BD%9E'
186
+ expect(MetaInspector.new('http://example.com/%EF%BD%9E', normalize_url: false).url).to eq('http://example.com/%EF%BD%9E')
187
187
  end
188
188
  end
189
189
  end
data/spec/exception_log_spec.rb CHANGED
@@ -4,7 +4,7 @@ describe MetaInspector::ExceptionLog do
4
4
 
5
5
  describe "warn_level" do
6
6
  it "should be :raise by default" do
7
- MetaInspector::ExceptionLog.new.warn_level.should == :raise
7
+ expect(MetaInspector::ExceptionLog.new.warn_level).to eq(:raise)
8
8
  end
9
9
 
10
10
  it "should raise exceptions when warn_level is :raise" do
@@ -20,7 +20,7 @@ describe MetaInspector::ExceptionLog do
20
20
  logger = MetaInspector::ExceptionLog.new(warn_level: :warn)
21
21
  exception = StandardError.new("an error message")
22
22
 
23
- logger.should_receive(:warn).with(exception)
23
+ expect(logger).to receive(:warn).with(exception)
24
24
  logger << exception
25
25
  end
26
26
 
@@ -49,28 +49,28 @@ describe MetaInspector::ExceptionLog do
49
49
  logger << first
50
50
  logger << second
51
51
 
52
- logger.exceptions.should == [first, second]
52
+ expect(logger.exceptions).to eq([first, second])
53
53
  end
54
54
 
55
55
  describe "ok?" do
56
56
  it "should be true if no exceptions stored" do
57
- logger.should be_ok
57
+ expect(logger).to be_ok
58
58
  end
59
59
 
60
60
  it "should be false if some exception stored" do
61
61
  logger << StandardError.new("some message")
62
- logger.should_not be_ok
62
+ expect(logger).not_to be_ok
63
63
  end
64
64
 
65
65
  it "should warn about misuse if warn_level is :raise" do
66
66
  logger = MetaInspector::ExceptionLog.new(warn_level: :raise)
67
- logger.should_receive(:warn).with("ExceptionLog#ok? should only be used when warn_level is :store")
67
+ expect(logger).to receive(:warn).with("ExceptionLog#ok? should only be used when warn_level is :store")
68
68
  logger.ok?
69
69
  end
70
70
 
71
71
  it "should warn about misuse if warn_level is :warn" do
72
72
  logger = MetaInspector::ExceptionLog.new(warn_level: :warn)
73
- logger.should_receive(:warn).with("ExceptionLog#ok? should only be used when warn_level is :store")
73
+ expect(logger).to receive(:warn).with("ExceptionLog#ok? should only be used when warn_level is :store")
74
74
  logger.ok?
75
75
  end
76
76
  end
data/spec/fixtures/no-content-type.response ADDED
@@ -0,0 +1,14 @@
1
+ HTTP/1.1 200 OK
2
+ Server: nginx/0.7.67
3
+ Date: Fri, 18 Nov 2011 21:46:46 GMT
4
+ Connection: keep-alive
5
+ Last-Modified: Mon, 14 Nov 2011 16:53:18 GMT
6
+ Content-Length: 101
7
+
8
+ <html>
9
+ <head>
10
+ <title>Thsi page has no content-type</title>
11
+ </head>
12
+ <body>
13
+ </body>
14
+ </html>
data/spec/fixtures/title_not_present.response ADDED
@@ -0,0 +1,21 @@
1
+ HTTP/1.1 200 OK
2
+ Age: 13
3
+ Cache-Control: max-age=120
4
+ Content-Type: text/html
5
+ Date: Mon, 06 Jan 2014 12:47:42 GMT
6
+ Expires: Mon, 06 Jan 2014 12:49:28 GMT
7
+ Server: Apache/2.2.14 (Ubuntu)
8
+ Vary: Accept-Encoding
9
+ Via: 1.1 varnish
10
+ X-Powered-By: PHP/5.3.2-1ubuntu4.22
11
+ X-Varnish: 1188792404 1188790413
12
+ Content-Length: 202
13
+ Connection: keep-alive
14
+
15
+ <!DOCTYPE html>
16
+ <html xmlns="http://www.w3.org/1999/xhtml" xmlns:fb="http://www.facebook.com/2008/fbml">
17
+ <head></head>
18
+ <body>
19
+ <p>A sample page with many types of meta tags</p>
20
+ </body>
21
+ </html>
data/spec/meta_inspector/images_spec.rb CHANGED
@@ -7,39 +7,39 @@ describe MetaInspector do
7
7
  let(:page) { MetaInspector.new('https://twitter.com/markupvalidator') }
8
8
 
9
9
  it "responds to #length" do
10
- page.images.length.should == 6
10
+ expect(page.images.length).to eq(6)
11
11
  end
12
12
 
13
13
  it "responds to #size" do
14
- page.images.size.should == 6
14
+ expect(page.images.size).to eq(6)
15
15
  end
16
16
 
17
17
  it "responds to #each" do
18
18
  c = []
19
19
  page.images.each {|i| c << i}
20
- c.length.should == 6
20
+ expect(c.length).to eq(6)
21
21
  end
22
22
 
23
23
  it "responds to #sort" do
24
- page.images.sort
25
- .should == ["https://si0.twimg.com/sticky/default_profile_images/default_profile_6_mini.png",
24
+ expect(page.images.sort)
25
+ .to eq(["https://si0.twimg.com/sticky/default_profile_images/default_profile_6_mini.png",
26
26
  "https://twimg0-a.akamaihd.net/a/1342841381/images/bigger_spinner.gif",
27
27
  "https://twimg0-a.akamaihd.net/profile_images/1538528659/jaime_nov_08_normal.jpg",
28
28
  "https://twimg0-a.akamaihd.net/profile_images/2293774732/v0pgo4xpdd9rou2xq5h0_normal.png",
29
29
  "https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_normal.png",
30
- "https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_reasonably_small.png"]
30
+ "https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_reasonably_small.png"])
31
31
  end
32
32
 
33
33
  it "responds to #first" do
34
- page.images.first.should == "https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_reasonably_small.png"
34
+ expect(page.images.first).to eq("https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_reasonably_small.png")
35
35
  end
36
36
 
37
37
  it "responds to #last" do
38
- page.images.last.should == "https://twimg0-a.akamaihd.net/a/1342841381/images/bigger_spinner.gif"
38
+ expect(page.images.last).to eq("https://twimg0-a.akamaihd.net/a/1342841381/images/bigger_spinner.gif")
39
39
  end
40
40
 
41
41
  it "responds to #[]" do
42
- page.images[0].should == "https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_reasonably_small.png"
42
+ expect(page.images[0]).to eq("https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_reasonably_small.png")
43
43
  end
44
44
 
45
45
  end
@@ -47,26 +47,26 @@ describe MetaInspector do
47
47
  it "should find all page images" do
48
48
  page = MetaInspector.new('http://pagerankalert.com')
49
49
 
50
- page.images.to_a.should == ["http://pagerankalert.com/images/pagerank_alert.png?1305794559"]
50
+ expect(page.images.to_a).to eq(["http://pagerankalert.com/images/pagerank_alert.png?1305794559"])
51
51
  end
52
52
 
53
53
  it "should find images on twitter" do
54
54
  page = MetaInspector.new('https://twitter.com/markupvalidator')
55
55
 
56
- page.images.length.should == 6
57
- page.images.to_a.should == ["https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_reasonably_small.png",
56
+ expect(page.images.length).to eq(6)
57
+ expect(page.images.to_a).to eq(["https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_reasonably_small.png",
58
58
  "https://twimg0-a.akamaihd.net/profile_images/2380086215/fcu46ozay5f5al9kdfvq_normal.png",
59
59
  "https://twimg0-a.akamaihd.net/profile_images/2293774732/v0pgo4xpdd9rou2xq5h0_normal.png",
60
60
  "https://twimg0-a.akamaihd.net/profile_images/1538528659/jaime_nov_08_normal.jpg",
61
61
  "https://si0.twimg.com/sticky/default_profile_images/default_profile_6_mini.png",
62
- "https://twimg0-a.akamaihd.net/a/1342841381/images/bigger_spinner.gif"]
62
+ "https://twimg0-a.akamaihd.net/a/1342841381/images/bigger_spinner.gif"])
63
63
  end
64
64
 
65
65
  it "should ignore malformed image tags" do
66
66
  # There is an image tag without a source. The scraper should not fatal.
67
67
  page = MetaInspector.new("http://www.guardian.co.uk/media/pda/2011/sep/15/techcrunch-arrington-startups")
68
68
 
69
- page.images.size.should == 11
69
+ expect(page.images.size).to eq(11)
70
70
  end
71
71
  end
72
72
 
@@ -74,19 +74,19 @@ describe MetaInspector do
74
74
  it "should find the og image" do
75
75
  page = MetaInspector.new('http://www.theonion.com/articles/apple-claims-new-iphone-only-visible-to-most-loyal,2772/')
76
76
 
77
- page.images.best.should == "http://o.onionstatic.com/images/articles/article/2772/Apple-Claims-600w-R_jpg_130x110_q85.jpg"
77
+ expect(page.images.best).to eq("http://o.onionstatic.com/images/articles/article/2772/Apple-Claims-600w-R_jpg_130x110_q85.jpg")
78
78
  end
79
79
 
80
80
  it "should find image on youtube" do
81
81
  page = MetaInspector.new('http://www.youtube.com/watch?v=iaGSSrp49uc')
82
82
 
83
- page.images.best.should == "http://i2.ytimg.com/vi/iaGSSrp49uc/mqdefault.jpg"
83
+ expect(page.images.best).to eq("http://i2.ytimg.com/vi/iaGSSrp49uc/mqdefault.jpg")
84
84
  end
85
85
 
86
86
  it "should find image when og:image and twitter:image metatags are missing" do
87
87
  page = MetaInspector.new('http://example.com/largest_image_using_image_size')
88
88
 
89
- page.images.best.should == "http://example.com/100x100"
89
+ expect(page.images.best).to eq("http://example.com/100x100")
90
90
  end
91
91
  end
92
92
 
@@ -94,19 +94,19 @@ describe MetaInspector do
94
94
  it "should find the og image" do
95
95
  page = MetaInspector.new('http://www.theonion.com/articles/apple-claims-new-iphone-only-visible-to-most-loyal,2772/')
96
96
 
97
- page.images.owner_suggested.should == "http://o.onionstatic.com/images/articles/article/2772/Apple-Claims-600w-R_jpg_130x110_q85.jpg"
97
+ expect(page.images.owner_suggested).to eq("http://o.onionstatic.com/images/articles/article/2772/Apple-Claims-600w-R_jpg_130x110_q85.jpg")
98
98
  end
99
99
 
100
100
  it "should find image on youtube" do
101
101
  page = MetaInspector.new('http://www.youtube.com/watch?v=iaGSSrp49uc')
102
102
 
103
- page.images.owner_suggested.should == "http://i2.ytimg.com/vi/iaGSSrp49uc/mqdefault.jpg"
103
+ expect(page.images.owner_suggested).to eq("http://i2.ytimg.com/vi/iaGSSrp49uc/mqdefault.jpg")
104
104
  end
105
105
 
106
106
  it "should return nil when og:image and twitter:image metatags are missing" do
107
107
  page = MetaInspector.new('http://example.com/largest_image_using_image_size')
108
108
 
109
- page.images.owner_suggested.should be nil
109
+ expect(page.images.owner_suggested).to be nil
110
110
  end
111
111
  end
112
112
 
@@ -114,19 +114,19 @@ describe MetaInspector do
114
114
  it "should find the largest image on the page using html sizes" do
115
115
  page = MetaInspector.new('http://example.com/largest_image_in_html')
116
116
 
117
- page.images.largest.should == "http://example.com/largest"
117
+ expect(page.images.largest).to eq("http://example.com/largest")
118
118
  end
119
119
 
120
120
  it "should find the largest image on the page using actual image sizes" do
121
121
  page = MetaInspector.new('http://example.com/largest_image_using_image_size')
122
122
 
123
- page.images.largest.should == "http://example.com/100x100"
123
+ expect(page.images.largest).to eq("http://example.com/100x100")
124
124
  end
125
125
 
126
126
  it "should find the largest image without downloading images" do
127
127
  page = MetaInspector.new('http://example.com/largest_image_using_image_size', download_images: false)
128
128
 
129
- page.images.largest.should == "http://example.com/1x1"
129
+ expect(page.images.largest).to eq("http://example.com/1x1")
130
130
  end
131
131
  end
132
132
 
@@ -134,31 +134,31 @@ describe MetaInspector do
134
134
  it "should get favicon link when marked as icon" do
135
135
  page = MetaInspector.new('http://pagerankalert.com/')
136
136
 
137
- page.images.favicon.should == 'http://pagerankalert.com/src/favicon.ico'
137
+ expect(page.images.favicon).to eq('http://pagerankalert.com/src/favicon.ico')
138
138
  end
139
139
 
140
140
  it "should get favicon link when marked as shortcut" do
141
141
  page = MetaInspector.new('http://pagerankalert-shortcut.com/')
142
142
 
143
- page.images.favicon.should == 'http://pagerankalert-shortcut.com/src/favicon.ico'
143
+ expect(page.images.favicon).to eq('http://pagerankalert-shortcut.com/src/favicon.ico')
144
144
  end
145
145
 
146
146
  it "should get favicon link when marked as shorcut and icon" do
147
147
  page = MetaInspector.new('http://pagerankalert-shortcut-and-icon.com/')
148
148
 
149
- page.images.favicon.should == 'http://pagerankalert-shortcut-and-icon.com/src/favicon.ico'
149
+ expect(page.images.favicon).to eq('http://pagerankalert-shortcut-and-icon.com/src/favicon.ico')
150
150
  end
151
151
 
152
152
  it "should get favicon link when there is also a touch icon" do
153
153
  page = MetaInspector.new('http://pagerankalert-touch-icon.com/')
154
154
 
155
- page.images.favicon.should == 'http://pagerankalert-touch-icon.com/src/favicon.ico'
155
+ expect(page.images.favicon).to eq('http://pagerankalert-touch-icon.com/src/favicon.ico')
156
156
  end
157
157
 
158
158
  it "should get favicon link of nil" do
159
159
  page = MetaInspector.new('http://www.theonion.com/articles/apple-claims-new-iphone-only-visible-to-most-loyal,2772/')
160
160
 
161
- page.images.favicon.should == nil
161
+ expect(page.images.favicon).to eq(nil)
162
162
  end
163
163
  end
164
164
  end
data/spec/meta_inspector/links_spec.rb CHANGED
@@ -5,21 +5,21 @@ describe MetaInspector do
5
5
 
6
6
  describe '#links' do
7
7
  it 'returns the internal links' do
8
- page.links.internal.should == [ "http://example.com/",
8
+ expect(page.links.internal).to eq([ "http://example.com/",
9
9
  "http://example.com/faqs",
10
10
  "http://example.com/contact",
11
- "http://example.com/team.html" ]
11
+ "http://example.com/team.html" ])
12
12
  end
13
13
 
14
14
  it 'returns the external links' do
15
- page.links.external.should == [ "https://twitter.com/",
16
- "https://github.com/" ]
15
+ expect(page.links.external).to eq([ "https://twitter.com/",
16
+ "https://github.com/" ])
17
17
  end
18
18
 
19
19
  it 'returns the non-HTTP links' do
20
- page.links.non_http.should == [ "mailto:hello@example.com",
20
+ expect(page.links.non_http).to eq([ "mailto:hello@example.com",
21
21
  "javascript:alert('hi');",
22
- "ftp://ftp.example.com/" ]
22
+ "ftp://ftp.example.com/" ])
23
23
  end
24
24
  end
25
25
 
@@ -29,81 +29,81 @@ describe MetaInspector do
29
29
  end
30
30
 
31
31
  it "should get correct absolute links for internal pages" do
32
- @m.links.internal.should == [ "http://pagerankalert.com/",
32
+ expect(@m.links.internal).to eq([ "http://pagerankalert.com/",
33
33
  "http://pagerankalert.com/es?language=es",
34
34
  "http://pagerankalert.com/users/sign_up",
35
- "http://pagerankalert.com/users/sign_in" ]
35
+ "http://pagerankalert.com/users/sign_in" ])
36
36
  end
37
37
 
38
38
  it "should get correct absolute links for external pages" do
39
- @m.links.external.should == [ "http://pagerankalert.posterous.com/",
39
+ expect(@m.links.external).to eq([ "http://pagerankalert.posterous.com/",
40
40
  "http://twitter.com/pagerankalert",
41
- "http://twitter.com/share" ]
41
+ "http://twitter.com/share" ])
42
42
  end
43
43
 
44
44
  it "should get correct absolute links, correcting relative links from URL not ending with slash" do
45
45
  m = MetaInspector.new('http://alazan.com/websolution.asp')
46
46
 
47
- m.links.internal.should == [ "http://alazan.com/index.asp",
48
- "http://alazan.com/faqs.asp" ]
47
+ expect(m.links.internal).to eq([ "http://alazan.com/index.asp",
48
+ "http://alazan.com/faqs.asp" ])
49
49
  end
50
50
 
51
51
  describe "links with international characters" do
52
52
  it "should get correct absolute links, encoding the URLs as needed" do
53
53
  m = MetaInspector.new('http://international.com')
54
54
 
55
- m.links.internal.should == [ "http://international.com/espa%C3%B1a.asp",
55
+ expect(m.links.internal).to eq([ "http://international.com/espa%C3%B1a.asp",
56
56
  "http://international.com/roman%C3%A9e",
57
57
  "http://international.com/faqs#cami%C3%B3n",
58
58
  "http://international.com/search?q=cami%C3%B3n",
59
59
  "http://international.com/search?q=espa%C3%B1a#top",
60
- "http://international.com/index.php?q=espa%C3%B1a&url=aHR0zZQ==&cntnt01pageid=21"]
60
+ "http://international.com/index.php?q=espa%C3%B1a&url=aHR0zZQ==&cntnt01pageid=21"])
61
61
 
62
- m.links.external.should == [ "http://example.com/espa%C3%B1a.asp",
62
+ expect(m.links.external).to eq([ "http://example.com/espa%C3%B1a.asp",
63
63
  "http://example.com/roman%C3%A9e",
64
64
  "http://example.com/faqs#cami%C3%B3n",
65
65
  "http://example.com/search?q=cami%C3%B3n",
66
- "http://example.com/search?q=espa%C3%B1a#top"]
66
+ "http://example.com/search?q=espa%C3%B1a#top"])
67
67
  end
68
68
 
69
69
  describe "internal links" do
70
70
  it "should get correct internal links, encoding the URLs as needed but respecting # and ?" do
71
71
  m = MetaInspector.new('http://international.com')
72
- m.links.internal.should == [ "http://international.com/espa%C3%B1a.asp",
72
+ expect(m.links.internal).to eq([ "http://international.com/espa%C3%B1a.asp",
73
73
  "http://international.com/roman%C3%A9e",
74
74
  "http://international.com/faqs#cami%C3%B3n",
75
75
  "http://international.com/search?q=cami%C3%B3n",
76
76
  "http://international.com/search?q=espa%C3%B1a#top",
77
- "http://international.com/index.php?q=espa%C3%B1a&url=aHR0zZQ==&cntnt01pageid=21"]
77
+ "http://international.com/index.php?q=espa%C3%B1a&url=aHR0zZQ==&cntnt01pageid=21"])
78
78
  end
79
79
 
80
80
  it "should not crash when processing malformed hrefs" do
81
81
  m = MetaInspector.new('http://example.com/malformed_href')
82
- m.links.internal.should == [ "http://example.com/faqs" ]
82
+ expect(m.links.internal).to eq([ "http://example.com/faqs" ])
83
83
  end
84
84
  end
85
85
 
86
86
  describe "external links" do
87
87
  it "should get correct external links, encoding the URLs as needed but respecting # and ?" do
88
88
  m = MetaInspector.new('http://international.com')
89
- m.links.external.should == [ "http://example.com/espa%C3%B1a.asp",
89
+ expect(m.links.external).to eq([ "http://example.com/espa%C3%B1a.asp",
90
90
  "http://example.com/roman%C3%A9e",
91
91
  "http://example.com/faqs#cami%C3%B3n",
92
92
  "http://example.com/search?q=cami%C3%B3n",
93
- "http://example.com/search?q=espa%C3%B1a#top"]
93
+ "http://example.com/search?q=espa%C3%B1a#top"])
94
94
  end
95
95
 
96
96
  it "should not crash when processing malformed hrefs" do
97
97
  m = MetaInspector.new('http://example.com/malformed_href')
98
- m.links.non_http.should == ["skype:joeuser?call", "telnet://telnet.cdrom.com", "javascript:alert('ok');",
99
- "javascript://", "mailto:email(at)example.com"]
98
+ expect(m.links.non_http).to eq(["skype:joeuser?call", "telnet://telnet.cdrom.com", "javascript:alert('ok');",
99
+ "javascript://", "mailto:email(at)example.com"])
100
100
  end
101
101
  end
102
102
  end
103
103
 
104
104
  it "should not crash with links that have weird href values" do
105
105
  m = MetaInspector.new('http://example.com/invalid_href')
106
- m.links.non_http.should == ["%3Cp%3Eftp://ftp.cdrom.com", "skype:joeuser?call", "telnet://telnet.cdrom.com"]
106
+ expect(m.links.non_http).to eq(["%3Cp%3Eftp://ftp.cdrom.com", "skype:joeuser?call", "telnet://telnet.cdrom.com"])
107
107
  end
108
108
  end
109
109
 
@@ -114,7 +114,7 @@ describe MetaInspector do
114
114
  end
115
115
 
116
116
  it 'should get the relative links' do
117
- @m.links.internal.should == ['http://relative.com/about', 'http://relative.com/sitemap']
117
+ expect(@m.links.internal).to eq(['http://relative.com/about', 'http://relative.com/sitemap'])
118
118
  end
119
119
  end
120
120
 
@@ -124,7 +124,7 @@ describe MetaInspector do
124
124
  end
125
125
 
126
126
  it 'should get the relative links' do
127
- @m.links.internal.should == ['http://relative.com/about', 'http://relative.com/sitemap']
127
+ expect(@m.links.internal).to eq(['http://relative.com/about', 'http://relative.com/sitemap'])
128
128
  end
129
129
  end
130
130
 
@@ -134,7 +134,7 @@ describe MetaInspector do
134
134
  end
135
135
 
136
136
  it 'should get the relative links' do
137
- @m.links.internal.should == ['http://relative.com/company/about', 'http://relative.com/sitemap']
137
+ expect(@m.links.internal).to eq(['http://relative.com/company/about', 'http://relative.com/sitemap'])
138
138
  end
139
139
  end
140
140
  end
@@ -142,12 +142,12 @@ describe MetaInspector do
142
142
  describe 'Relative links with base' do
143
143
  it 'should get the relative links from a document' do
144
144
  m = MetaInspector.new('http://relativewithbase.com/company/page2')
145
- m.links.internal.should == ['http://relativewithbase.com/about', 'http://relativewithbase.com/sitemap']
145
+ expect(m.links.internal).to eq(['http://relativewithbase.com/about', 'http://relativewithbase.com/sitemap'])
146
146
  end
147
147
 
148
148
  it 'should get the relative links from a directory' do
149
149
  m = MetaInspector.new('http://relativewithbase.com/company/page2/')
150
- m.links.internal.should == ['http://relativewithbase.com/about', 'http://relativewithbase.com/sitemap']
150
+ expect(m.links.internal).to eq(['http://relativewithbase.com/about', 'http://relativewithbase.com/sitemap'])
151
151
  end
152
152
  end
153
153
 
@@ -157,13 +157,13 @@ describe MetaInspector do
157
157
  end
158
158
 
159
159
  it "should get the links" do
160
- @m.links.non_http.sort.should == [
160
+ expect(@m.links.non_http.sort).to eq([
161
161
  "ftp://ftp.cdrom.com/",
162
162
  "javascript:alert('hey');",
163
163
  "mailto:user@example.com",
164
164
  "skype:joeuser?call",
165
165
  "telnet://telnet.cdrom.com"
166
- ]
166
+ ])
167
167
  end
168
168
  end
169
169
 
@@ -174,30 +174,30 @@ describe MetaInspector do
174
174
  end
175
175
 
176
176
  it "should convert protocol-relative links to http" do
177
- @m_http.links.internal.should include('http://protocol-relative.com/contact')
178
- @m_http.links.external.should include('http://yahoo.com/')
177
+ expect(@m_http.links.internal).to include('http://protocol-relative.com/contact')
178
+ expect(@m_http.links.external).to include('http://yahoo.com/')
179
179
  end
180
180
 
181
181
  it "should convert protocol-relative links to https" do
182
- @m_https.links.internal.should include('https://protocol-relative.com/contact')
183
- @m_https.links.external.should include('https://yahoo.com/')
182
+ expect(@m_https.links.internal).to include('https://protocol-relative.com/contact')
183
+ expect(@m_https.links.external).to include('https://yahoo.com/')
184
184
  end
185
185
  end
186
186
 
187
187
  describe "Feed" do
188
188
  it "should get rss feed" do
189
189
  @m = MetaInspector.new('http://www.iteh.at')
190
- @m.feed.should == 'http://www.iteh.at/de/rss/'
190
+ expect(@m.feed).to eq('http://www.iteh.at/de/rss/')
191
191
  end
192
192
 
193
193
  it "should get atom feed" do
194
194
  @m = MetaInspector.new('http://www.tea-tron.com/jbravo/blog/')
195
- @m.feed.should == 'http://www.tea-tron.com/jbravo/blog/feed/'
195
+ expect(@m.feed).to eq('http://www.tea-tron.com/jbravo/blog/feed/')
196
196
  end
197
197
 
198
198
  it "should return nil if no feed found" do
199
199
  @m = MetaInspector.new('http://www.alazan.com')
200
- @m.feed.should == nil
200
+ expect(@m.feed).to eq(nil)
201
201
  end
202
202
  end
203
203
  end
data/spec/meta_inspector/meta_inspector_spec.rb CHANGED
@@ -2,6 +2,6 @@ require 'spec_helper'
2
2
 
3
3
  describe MetaInspector do
4
4
  it "returns a Document" do
5
- MetaInspector.new('http://example.com').class.should == MetaInspector::Document
5
+ expect(MetaInspector.new('http://example.com').class).to eq(MetaInspector::Document)
6
6
  end
7
7
  end
data/spec/meta_inspector/meta_tags_spec.rb CHANGED
@@ -6,7 +6,7 @@ describe MetaInspector do
6
6
  let(:page) { MetaInspector.new('http://example.com/meta-tags') }
7
7
 
8
8
  it "#meta_tags" do
9
- page.meta_tags.should == {
9
+ expect(page.meta_tags).to eq({
10
10
  'name' => {
11
11
  'keywords' => ['one, two, three'],
12
12
  'description' => ['the description'],
@@ -33,11 +33,11 @@ describe MetaInspector do
33
33
  },
34
34
 
35
35
  'charset' => ['UTF-8']
36
- }
36
+ })
37
37
  end
38
38
 
39
39
  it "#meta_tag" do
40
- page.meta_tag.should == {
40
+ expect(page.meta_tag).to eq({
41
41
  'name' => {
42
42
  'keywords' => 'one, two, three',
43
43
  'description' => 'the description',
@@ -62,11 +62,11 @@ describe MetaInspector do
62
62
  },
63
63
 
64
64
  'charset' => 'UTF-8'
65
- }
65
+ })
66
66
  end
67
67
 
68
68
  it "#meta" do
69
- page.meta.should == {
69
+ expect(page.meta).to eq({
70
70
  'keywords' => 'one, two, three',
71
71
  'description' => 'the description',
72
72
  'author' => 'Joe Sample',
@@ -82,7 +82,7 @@ describe MetaInspector do
82
82
  'og:image:width' => '300',
83
83
  'og:image:height' => '300',
84
84
  'charset' => 'UTF-8'
85
- }
85
+ })
86
86
  end
87
87
  end
88
88
 
@@ -90,19 +90,19 @@ describe MetaInspector do
90
90
  it "should get the charset from <meta charset />" do
91
91
  page = MetaInspector.new('http://charset001.com')
92
92
 
93
- page.charset.should == "utf-8"
93
+ expect(page.charset).to eq("utf-8")
94
94
  end
95
95
 
96
96
  it "should get the charset from meta content type" do
97
97
  page = MetaInspector.new('http://charset002.com')
98
98
 
99
- page.charset.should == "windows-1252"
99
+ expect(page.charset).to eq("windows-1252")
100
100
  end
101
101
 
102
102
  it "should get nil if no declared charset is found" do
103
103
  page = MetaInspector.new('http://charset000.com')
104
104
 
105
- page.charset.should == nil
105
+ expect(page.charset).to eq(nil)
106
106
  end
107
107
  end
108
108
  end
data/spec/meta_inspector/redirections_spec.rb CHANGED
@@ -8,17 +8,17 @@ describe MetaInspector do
8
8
  it "disallows redirections" do
9
9
  page = MetaInspector.new("http://facebook.com", :allow_redirections => false)
10
10
 
11
- page.url.should == "http://facebook.com/"
11
+ expect(page.url).to eq("http://facebook.com/")
12
12
  end
13
13
  end
14
14
 
15
15
  context "when redirections are on (default)" do
16
16
  it "allows follows redirections" do
17
- logger.should_not receive(:<<)
17
+ expect(logger).not_to receive(:<<)
18
18
 
19
19
  page = MetaInspector.new("http://facebook.com", exception_log: logger)
20
20
 
21
- page.url.should == "https://www.facebook.com/"
21
+ expect(page.url).to eq("https://www.facebook.com/")
22
22
  end
23
23
  end
24
24
 
@@ -37,11 +37,11 @@ describe MetaInspector do
37
37
  stub_request(:get, "http://blogs.clarionledger.com/dechols/2014/03/24/digital-medicine/?nclick_check=1")
38
38
  .with(:headers => {"Cookie" => "EMETA_COOKIE_CHECK=1"})
39
39
 
40
- logger.should_not receive(:<<)
40
+ expect(logger).not_to receive(:<<)
41
41
 
42
42
  page = MetaInspector.new("http://blogs.clarionledger.com/dechols/2014/03/24/digital-medicine/", exception_log: logger)
43
43
 
44
- page.url.should == "http://blogs.clarionledger.com/dechols/2014/03/24/digital-medicine/?nclick_check=1"
44
+ expect(page.url).to eq("http://blogs.clarionledger.com/dechols/2014/03/24/digital-medicine/?nclick_check=1")
45
45
  end
46
46
  end
47
47
  end
data/spec/meta_inspector/texts_spec.rb CHANGED
@@ -3,38 +3,43 @@ require 'spec_helper'
3
3
  describe MetaInspector do
4
4
  it "should get the title from the head section" do
5
5
  page = MetaInspector.new('http://example.com')
6
- page.title.should == 'An example page'
6
+ expect(page.title).to eq('An example page')
7
7
  end
8
8
 
9
9
  describe '#best_title' do
10
10
  it "should find 'head title' when that's the only thing" do
11
11
  page = MetaInspector.new('http://example.com/title_in_head')
12
- page.best_title.should == 'This title came from the head'
12
+ expect(page.best_title).to eq('This title came from the head')
13
13
  end
14
14
 
15
15
  it "should find 'body title' when that's the only thing" do
16
16
  page = MetaInspector.new('http://example.com/title_in_body')
17
- page.best_title.should == 'This title came from the body, not the head'
17
+ expect(page.best_title).to eq('This title came from the body, not the head')
18
18
  end
19
19
 
20
20
  it "should find 'og:title' when that's the only thing" do
21
21
  page = MetaInspector.new('http://example.com/meta-tags')
22
- page.best_title.should == 'An OG title'
22
+ expect(page.best_title).to eq('An OG title')
23
23
  end
24
24
 
25
25
  it "should find the first <h1> when that's the only thing" do
26
26
  page = MetaInspector.new('http://example.com/title_in_h1')
27
- page.best_title.should == 'This title came from the first h1'
27
+ expect(page.best_title).to eq('This title came from the first h1')
28
28
  end
29
29
 
30
30
  it "should choose the longest candidate from the available options" do
31
31
  page = MetaInspector.new('http://example.com/title_best_choice')
32
- page.best_title.should == 'This title came from the first h1 and should be the longest of them all, so should be chosen'
32
+ expect(page.best_title).to eq('This title came from the first h1 and should be the longest of them all, so should be chosen')
33
33
  end
34
34
 
35
35
  it "should strip leading and trailing whitespace and all line breaks" do
36
36
  page = MetaInspector.new('http://example.com/title_in_head_with_whitespace')
37
- page.best_title.should == 'This title came from the head and has leading and trailing whitespace'
37
+ expect(page.best_title).to eq('This title came from the head and has leading and trailing whitespace')
38
+ end
39
+
40
+ it "should return nil if none of the candidates are present" do
41
+ page = MetaInspector.new('http://example.com/title_not_present')
42
+ expect(page.best_title).to be(nil)
38
43
  end
39
44
 
40
45
  end
@@ -43,12 +48,12 @@ describe MetaInspector do
43
48
  it "should find description from meta description" do
44
49
  page = MetaInspector.new('http://www.youtube.com/watch?v=iaGSSrp49uc')
45
50
 
46
- page.description.should == "This is Youtube"
51
+ expect(page.description).to eq("This is Youtube")
47
52
  end
48
53
 
49
54
  it "should find a secondary description if no meta description" do
50
55
  page = MetaInspector.new('http://theonion-no-description.com')
51
- page.description.should == "SAN FRANCISCO—In a move expected to revolutionize the mobile device industry, Apple launched its fastest and most powerful iPhone to date Tuesday, an innovative new model that can only be seen by the company's hippest and most dedicated customers. This is secondary text picked up because of a missing meta description."
56
+ expect(page.description).to eq("SAN FRANCISCO—In a move expected to revolutionize the mobile device industry, Apple launched its fastest and most powerful iPhone to date Tuesday, an innovative new model that can only be seen by the company's hippest and most dedicated customers. This is secondary text picked up because of a missing meta description.")
52
57
  end
53
58
  end
54
59
  end
data/spec/parser_spec.rb CHANGED
@@ -5,10 +5,10 @@ describe MetaInspector::Parser do
5
5
  let(:parser) { MetaInspector::Parser.new(doc) }
6
6
 
7
7
  it "should have a Nokogiri::HTML::Document as parsed" do
8
- parser.parsed.class.should == Nokogiri::HTML::Document
8
+ expect(parser.parsed.class).to eq(Nokogiri::HTML::Document)
9
9
  end
10
10
 
11
11
  it "should return the document as a string" do
12
- parser.to_s.class.should == String
12
+ expect(parser.to_s.class).to eq(String)
13
13
  end
14
14
  end
data/spec/request_spec.rb CHANGED
@@ -6,24 +6,24 @@ describe MetaInspector::Request do
6
6
  it "should return the content of the page" do
7
7
  page_request = MetaInspector::Request.new(url('http://pagerankalert.com'))
8
8
 
9
- page_request.read[0..14].should == "<!DOCTYPE html>"
9
+ expect(page_request.read[0..14]).to eq("<!DOCTYPE html>")
10
10
  end
11
11
  end
12
12
 
13
13
  describe "response" do
14
14
  it "contains the response status" do
15
15
  page_request = MetaInspector::Request.new(url('http://example.com'))
16
- page_request.response.status.should == 200
16
+ expect(page_request.response.status).to eq(200)
17
17
  end
18
18
 
19
19
  it "contains the response headers" do
20
20
  page_request = MetaInspector::Request.new(url('http://example.com'))
21
- page_request.response.headers
22
- .should == {"server"=>"nginx/0.7.67", "date"=>"Fri, 18 Nov 2011 21:46:46 GMT",
21
+ expect(page_request.response.headers)
22
+ .to eq({"server"=>"nginx/0.7.67", "date"=>"Fri, 18 Nov 2011 21:46:46 GMT",
23
23
  "content-type"=>"text/html", "connection"=>"keep-alive",
24
24
  "last-modified"=>"Mon, 14 Nov 2011 16:53:18 GMT",
25
25
  "content-length"=>"4987", "x-varnish"=>"2000423390",
26
- "age"=>"0", "via"=>"1.1 varnish"}
26
+ "age"=>"0", "via"=>"1.1 varnish"})
27
27
  end
28
28
  end
29
29
 
@@ -31,13 +31,19 @@ describe MetaInspector::Request do
31
31
  it "should return the correct content type of the url for html pages" do
32
32
  page_request = MetaInspector::Request.new(url('http://pagerankalert.com'))
33
33
 
34
- page_request.content_type.should == "text/html"
34
+ expect(page_request.content_type).to eq("text/html")
35
35
  end
36
36
 
37
37
  it "should return the correct content type of the url for non html pages" do
38
38
  image_request = MetaInspector::Request.new(url('http://pagerankalert.com/image.png'))
39
39
 
40
- image_request.content_type.should == "image/png"
40
+ expect(image_request.content_type).to eq("image/png")
41
+ end
42
+
43
+ it "should return nil if there is not content type present" do
44
+ request = MetaInspector::Request.new(url('http://example.com/no-content-type'))
45
+
46
+ expect(request.content_type).to be(nil)
41
47
  end
42
48
  end
43
49
 
@@ -53,8 +59,8 @@ describe MetaInspector::Request do
53
59
  end
54
60
 
55
61
  it "should handle socket errors" do
56
- TCPSocket.stub(:open).and_raise(SocketError)
57
- logger.should receive(:<<).with(an_instance_of(Faraday::Error::ConnectionFailed))
62
+ allow(TCPSocket).to receive(:open).and_raise(SocketError)
63
+ expect(logger).to receive(:<<).with(an_instance_of(Faraday::Error::ConnectionFailed))
58
64
 
59
65
  MetaInspector::Request.new(url('http://caca232dsdsaer3sdsd-asd343.org'), exception_log: logger)
60
66
  end
data/spec/spec_helper.rb CHANGED
@@ -16,7 +16,6 @@ end
16
16
  RSpec.configure do |config|
17
17
  config.filter_run focus: true
18
18
  config.run_all_when_everything_filtered = true
19
- config.treat_symbols_as_metadata_keys_with_true_values = true #rspec 3 default
20
19
  end
21
20
 
22
21
  #######################
@@ -31,6 +30,9 @@ FakeWeb.register_uri(:get, "http://example.com/", :response => fixture_file("exa
31
30
  # Used to test response status codes
32
31
  FakeWeb.register_uri(:get, "http://example.com/404", :response => fixture_file("404.response"))
33
32
 
33
+ # Used to test headers
34
+ FakeWeb.register_uri(:get, "http://example.com/no-content-type", :response => fixture_file("no-content-type.response"))
35
+
34
36
  # Used to test largest image in page logic
35
37
  FakeWeb.register_uri(:get, "http://example.com/largest_image_in_html", :response => fixture_file("largest_image_in_html.response"))
36
38
  FakeWeb.register_uri(:get, "http://example.com/largest_image_using_image_size", :response => fixture_file("largest_image_using_image_size.response"))
@@ -43,6 +45,7 @@ FakeWeb.register_uri(:get, "http://example.com/title_in_body", :response => fixt
43
45
  FakeWeb.register_uri(:get, "http://example.com/title_in_h1", :response => fixture_file("title_in_h1.response"))
44
46
  FakeWeb.register_uri(:get, "http://example.com/title_best_choice", :response => fixture_file("title_best_choice.response"))
45
47
  FakeWeb.register_uri(:get, "http://example.com/title_in_head_with_whitespace", :response => fixture_file("title_in_head_with_whitespace.response"))
48
+ FakeWeb.register_uri(:get, "http://example.com/title_not_present", :response => fixture_file("title_not_present.response"))
46
49
 
47
50
  # These are older fixtures
48
51
  FakeWeb.register_uri(:get, "http://pagerankalert.com", :response => fixture_file("pagerankalert.com.response"))
data/spec/url_spec.rb CHANGED
@@ -2,38 +2,38 @@ require 'spec_helper'
2
2
 
3
3
  describe MetaInspector::URL do
4
4
  it "should normalize URLs" do
5
- MetaInspector::URL.new('http://example.com').url.should == 'http://example.com/'
5
+ expect(MetaInspector::URL.new('http://example.com').url).to eq('http://example.com/')
6
6
  end
7
7
 
8
8
  it 'should accept an URL with a scheme' do
9
- MetaInspector::URL.new('http://example.com/').url.should == 'http://example.com/'
9
+ expect(MetaInspector::URL.new('http://example.com/').url).to eq('http://example.com/')
10
10
  end
11
11
 
12
12
  it "should use http:// as a default scheme" do
13
- MetaInspector::URL.new('example.com').url.should == 'http://example.com/'
13
+ expect(MetaInspector::URL.new('example.com').url).to eq('http://example.com/')
14
14
  end
15
15
 
16
16
  it "should accept an URL with international characters" do
17
- MetaInspector::URL.new('http://international.com/olé').url.should == 'http://international.com/ol%C3%A9'
17
+ expect(MetaInspector::URL.new('http://international.com/olé').url).to eq('http://international.com/ol%C3%A9')
18
18
  end
19
19
 
20
20
  it "should return the scheme" do
21
- MetaInspector::URL.new('http://example.com').scheme.should == 'http'
22
- MetaInspector::URL.new('https://example.com').scheme.should == 'https'
23
- MetaInspector::URL.new('example.com').scheme.should == 'http'
21
+ expect(MetaInspector::URL.new('http://example.com').scheme).to eq('http')
22
+ expect(MetaInspector::URL.new('https://example.com').scheme).to eq('https')
23
+ expect(MetaInspector::URL.new('example.com').scheme).to eq('http')
24
24
  end
25
25
 
26
26
  it "should return the host" do
27
- MetaInspector::URL.new('http://example.com').host.should == 'example.com'
28
- MetaInspector::URL.new('https://example.com').host.should == 'example.com'
29
- MetaInspector::URL.new('example.com').host.should == 'example.com'
27
+ expect(MetaInspector::URL.new('http://example.com').host).to eq('example.com')
28
+ expect(MetaInspector::URL.new('https://example.com').host).to eq('example.com')
29
+ expect(MetaInspector::URL.new('example.com').host).to eq('example.com')
30
30
  end
31
31
 
32
32
  it "should return the root url" do
33
- MetaInspector::URL.new('http://example.com').root_url.should == 'http://example.com/'
34
- MetaInspector::URL.new('https://example.com').root_url.should == 'https://example.com/'
35
- MetaInspector::URL.new('example.com').root_url.should == 'http://example.com/'
36
- MetaInspector::URL.new('http://example.com/faqs').root_url.should == 'http://example.com/'
33
+ expect(MetaInspector::URL.new('http://example.com').root_url).to eq('http://example.com/')
34
+ expect(MetaInspector::URL.new('https://example.com').root_url).to eq('https://example.com/')
35
+ expect(MetaInspector::URL.new('example.com').root_url).to eq('http://example.com/')
36
+ expect(MetaInspector::URL.new('http://example.com/faqs').root_url).to eq('http://example.com/')
37
37
  end
38
38
 
39
39
  describe "url=" do
@@ -41,14 +41,14 @@ describe MetaInspector::URL do
41
41
  url = MetaInspector::URL.new('http://first.com/')
42
42
 
43
43
  url.url = 'http://second.com/'
44
- url.url.should == 'http://second.com/'
44
+ expect(url.url).to eq('http://second.com/')
45
45
  end
46
46
 
47
47
  it "should add the missing scheme and normalize" do
48
48
  url = MetaInspector::URL.new('http://first.com/')
49
49
 
50
50
  url.url = 'second.com'
51
- url.url.should == 'http://second.com/'
51
+ expect(url.url).to eq('http://second.com/')
52
52
  end
53
53
  end
54
54
  end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: metainspector
3
3
  version: !ruby/object:Gem::Version
4
- version: 4.3.0
4
+ version: 4.3.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Jaime Iniesta
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2015-01-29 00:00:00.000000000 Z
11
+ date: 2015-01-30 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: nokogiri
@@ -98,16 +98,16 @@ dependencies:
98
98
  name: rspec
99
99
  requirement: !ruby/object:Gem::Requirement
100
100
  requirements:
101
- - - '='
101
+ - - "~>"
102
102
  - !ruby/object:Gem::Version
103
- version: 2.14.1
103
+ version: '3.0'
104
104
  type: :development
105
105
  prerelease: false
106
106
  version_requirements: !ruby/object:Gem::Requirement
107
107
  requirements:
108
- - - '='
108
+ - - "~>"
109
109
  - !ruby/object:Gem::Version
110
- version: 2.14.1
110
+ version: '3.0'
111
111
  - !ruby/object:Gem::Dependency
112
112
  name: fakeweb
113
113
  requirement: !ruby/object:Gem::Requirement
@@ -278,6 +278,7 @@ files:
278
278
  - spec/fixtures/malformed_href.response
279
279
  - spec/fixtures/markupvalidator_faqs.response
280
280
  - spec/fixtures/meta_tags.response
281
+ - spec/fixtures/no-content-type.response
281
282
  - spec/fixtures/nonhttp.response
282
283
  - spec/fixtures/pagerankalert-shortcut-and-icon.com.response
283
284
  - spec/fixtures/pagerankalert-shortcut.com.response
@@ -294,6 +295,7 @@ files:
294
295
  - spec/fixtures/title_in_h1.response
295
296
  - spec/fixtures/title_in_head.response
296
297
  - spec/fixtures/title_in_head_with_whitespace.response
298
+ - spec/fixtures/title_not_present.response
297
299
  - spec/fixtures/twitter_markupvalidator.response
298
300
  - spec/fixtures/unsafe_facebook.com.response
299
301
  - spec/fixtures/unsafe_https.facebook.com.response