ruby-readability-discourse 0.6.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/.rspec +2 -0
- data/.travis.yml +6 -0
- data/.yardopts +3 -0
- data/Gemfile +12 -0
- data/Guardfile +9 -0
- data/LICENSE +202 -0
- data/README.md +107 -0
- data/Rakefile +6 -0
- data/bin/readability +41 -0
- data/lib/readability.rb +492 -0
- data/lib/ruby-readability.rb +1 -0
- data/ruby-readability.gemspec +25 -0
- data/spec/fixtures/bbc.html +2069 -0
- data/spec/fixtures/boing_boing.html +876 -0
- data/spec/fixtures/cant_read.html +426 -0
- data/spec/fixtures/code.html +13 -0
- data/spec/fixtures/images/dim_1416768a.jpg +0 -0
- data/spec/fixtures/images/sign_up_emails_682__703711a.gif +0 -0
- data/spec/fixtures/images/sign_up_emails_682__703712a.gif +0 -0
- data/spec/fixtures/nytimes.html +58 -0
- data/spec/fixtures/sample.html +1198 -0
- data/spec/fixtures/samples/blogpost_with_links-fragments.rb +10 -0
- data/spec/fixtures/samples/blogpost_with_links.html +137 -0
- data/spec/fixtures/samples/channel4-1-fragments.rb +13 -0
- data/spec/fixtures/samples/channel4-1.html +1330 -0
- data/spec/fixtures/samples/foxnews-india1-fragments.rb +13 -0
- data/spec/fixtures/samples/foxnews-india1.html +2058 -0
- data/spec/fixtures/samples/globemail-ottawa-cuts-fragments.rb +31 -0
- data/spec/fixtures/samples/globemail-ottawa-cuts.html +2410 -0
- data/spec/fixtures/should_not_truncate.txt +1077 -0
- data/spec/fixtures/thesun.html +1122 -0
- data/spec/readability_spec.rb +544 -0
- data/spec/spec.opts +4 -0
- data/spec/spec_helper.rb +11 -0
- metadata +152 -0
@@ -0,0 +1,544 @@
|
|
1
|
+
# encoding: UTF-8
|
2
|
+
|
3
|
+
require 'spec_helper'
|
4
|
+
require 'readability'
|
5
|
+
|
6
|
+
describe Readability do
|
7
|
+
before do
|
8
|
+
@simple_html_fixture = <<-HTML
|
9
|
+
<html>
|
10
|
+
<head>
|
11
|
+
<title>title!</title>
|
12
|
+
</head>
|
13
|
+
<body class='comment'>
|
14
|
+
<div>
|
15
|
+
<p class='comment'>a comment</p>
|
16
|
+
<div class='comment' id='body'>real content</div>
|
17
|
+
<div id="contains_blockquote"><blockquote>something in a table</blockquote></div>
|
18
|
+
</div>
|
19
|
+
</body>
|
20
|
+
</html>
|
21
|
+
HTML
|
22
|
+
end
|
23
|
+
|
24
|
+
describe "images" do
|
25
|
+
before do
|
26
|
+
@bbc = File.read(File.dirname(__FILE__) + "/fixtures/bbc.html")
|
27
|
+
@nytimes = File.read(File.dirname(__FILE__) + "/fixtures/nytimes.html")
|
28
|
+
@thesum = File.read(File.dirname(__FILE__) + "/fixtures/thesun.html")
|
29
|
+
|
30
|
+
FakeWeb::Registry.instance.clean_registry
|
31
|
+
FakeWeb.register_uri(:get, "http://img.thesun.co.uk/multimedia/archive/01416/dim_1416768a.jpg",
|
32
|
+
:body => File.read(File.dirname(__FILE__) + "/fixtures/images/dim_1416768a.jpg"))
|
33
|
+
|
34
|
+
FakeWeb.register_uri(:get, "http://img.thesun.co.uk/multimedia/archive/00703/sign_up_emails_682__703711a.gif",
|
35
|
+
:body => File.read(File.dirname(__FILE__) + "/fixtures/images/sign_up_emails_682__703711a.gif"))
|
36
|
+
|
37
|
+
FakeWeb.register_uri(:get, "http://img.thesun.co.uk/multimedia/archive/00703/sign_up_emails_682__703712a.gif",
|
38
|
+
:body => File.read(File.dirname(__FILE__) + "/fixtures/images/sign_up_emails_682__703712a.gif"))
|
39
|
+
end
|
40
|
+
|
41
|
+
it "should show one image, but outside of the best candidate" do
|
42
|
+
@doc = Readability::Document.new(@thesum)
|
43
|
+
@doc.images.should == ["http://img.thesun.co.uk/multimedia/archive/01416/dim_1416768a.jpg", "http://img.thesun.co.uk/multimedia/archive/00703/sign_up_emails_682__703711a.gif", "http://img.thesun.co.uk/multimedia/archive/00703/sign_up_emails_682__703712a.gif"]
|
44
|
+
@doc.best_candidate_has_image.should == false
|
45
|
+
end
|
46
|
+
|
47
|
+
it "should show one image inside of the best candidate" do
|
48
|
+
@doc = Readability::Document.new(@nytimes)
|
49
|
+
@doc.images.should == ["http://graphics8.nytimes.com/images/2011/12/02/opinion/02fixes-freelancersunion/02fixes-freelancersunion-blog427.jpg"]
|
50
|
+
@doc.best_candidate_has_image.should == true
|
51
|
+
end
|
52
|
+
|
53
|
+
it "should not try to download local images" do
|
54
|
+
@doc = Readability::Document.new(<<-HTML)
|
55
|
+
<html>
|
56
|
+
<head>
|
57
|
+
<title>title!</title>
|
58
|
+
</head>
|
59
|
+
<body class='comment'>
|
60
|
+
<div>
|
61
|
+
<img src="/something/local.gif" />
|
62
|
+
</div>
|
63
|
+
</body>
|
64
|
+
</html>
|
65
|
+
HTML
|
66
|
+
do_not_allow(@doc).load_image(anything)
|
67
|
+
@doc.images.should == []
|
68
|
+
end
|
69
|
+
|
70
|
+
describe "no images" do
|
71
|
+
it "shouldn't show images" do
|
72
|
+
@doc = Readability::Document.new(@bbc, :min_image_height => 600)
|
73
|
+
@doc.images.should == []
|
74
|
+
@doc.best_candidate_has_image.should == false
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
describe "poll of images" do
|
79
|
+
it "should show some images inside of the best candidate" do
|
80
|
+
@doc = Readability::Document.new(@bbc)
|
81
|
+
@doc.images.should =~ ["http://news.bbcimg.co.uk/media/images/57027000/jpg/_57027794_perseus_getty.jpg",
|
82
|
+
"http://news.bbcimg.co.uk/media/images/57027000/jpg/_57027786_john_capes229_rnsm.jpg",
|
83
|
+
"http://news.bbcimg.co.uk/media/images/57060000/gif/_57060487_sub_escapes304x416.gif",
|
84
|
+
"http://news.bbcimg.co.uk/media/images/57055000/jpg/_57055063_perseus_thoctarides.jpg"]
|
85
|
+
@doc.best_candidate_has_image.should == true
|
86
|
+
end
|
87
|
+
|
88
|
+
it "should show some images inside of the best candidate, include gif format" do
|
89
|
+
@doc = Readability::Document.new(@bbc, :ignore_image_format => [])
|
90
|
+
@doc.images.should == ["http://news.bbcimg.co.uk/media/images/57027000/jpg/_57027794_perseus_getty.jpg", "http://news.bbcimg.co.uk/media/images/57027000/jpg/_57027786_john_capes229_rnsm.jpg", "http://news.bbcimg.co.uk/media/images/57060000/gif/_57060487_sub_escapes304x416.gif", "http://news.bbcimg.co.uk/media/images/57055000/jpg/_57055063_perseus_thoctarides.jpg"]
|
91
|
+
@doc.best_candidate_has_image.should == true
|
92
|
+
end
|
93
|
+
|
94
|
+
describe "width, height and format" do
|
95
|
+
it "should show some images inside of the best candidate, but with width most equal to 400px" do
|
96
|
+
@doc = Readability::Document.new(@bbc, :min_image_width => 400, :ignore_image_format => [])
|
97
|
+
@doc.images.should == ["http://news.bbcimg.co.uk/media/images/57027000/jpg/_57027794_perseus_getty.jpg"]
|
98
|
+
@doc.best_candidate_has_image.should == true
|
99
|
+
end
|
100
|
+
|
101
|
+
it "should show some images inside of the best candidate, but with width most equal to 304px" do
|
102
|
+
@doc = Readability::Document.new(@bbc, :min_image_width => 304, :ignore_image_format => [])
|
103
|
+
@doc.images.should == ["http://news.bbcimg.co.uk/media/images/57027000/jpg/_57027794_perseus_getty.jpg", "http://news.bbcimg.co.uk/media/images/57060000/gif/_57060487_sub_escapes304x416.gif", "http://news.bbcimg.co.uk/media/images/57055000/jpg/_57055063_perseus_thoctarides.jpg"]
|
104
|
+
@doc.best_candidate_has_image.should == true
|
105
|
+
end
|
106
|
+
|
107
|
+
it "should show some images inside of the best candidate, but with width most equal to 304px and ignoring JPG format" do
|
108
|
+
@doc = Readability::Document.new(@bbc, :min_image_width => 304, :ignore_image_format => ["jpg"])
|
109
|
+
@doc.images.should == ["http://news.bbcimg.co.uk/media/images/57060000/gif/_57060487_sub_escapes304x416.gif"]
|
110
|
+
@doc.best_candidate_has_image.should == true
|
111
|
+
end
|
112
|
+
|
113
|
+
it "should show some images inside of the best candidate, but with height most equal to 400px, no ignoring no format" do
|
114
|
+
@doc = Readability::Document.new(@bbc, :min_image_height => 400, :ignore_image_format => [])
|
115
|
+
@doc.images.should == ["http://news.bbcimg.co.uk/media/images/57060000/gif/_57060487_sub_escapes304x416.gif"]
|
116
|
+
@doc.best_candidate_has_image.should == true
|
117
|
+
end
|
118
|
+
end
|
119
|
+
end
|
120
|
+
end
|
121
|
+
|
122
|
+
describe "transformMisusedDivsIntoParagraphs" do
|
123
|
+
before do
|
124
|
+
@doc = Readability::Document.new(@simple_html_fixture)
|
125
|
+
@doc.transform_misused_divs_into_paragraphs!
|
126
|
+
end
|
127
|
+
|
128
|
+
it "should transform divs containing no block elements into <p>s" do
|
129
|
+
@doc.html.css("#body").first.name.should == "p"
|
130
|
+
end
|
131
|
+
|
132
|
+
it "should not transform divs that contain block elements" do
|
133
|
+
@doc.html.css("#contains_blockquote").first.name.should == "div"
|
134
|
+
end
|
135
|
+
end
|
136
|
+
|
137
|
+
describe "author" do
|
138
|
+
it "should pick up <meta name='dc.creator'></meta> as an author" do
|
139
|
+
doc = Readability::Document.new(<<-HTML)
|
140
|
+
<html>
|
141
|
+
<head>
|
142
|
+
<meta name='dc.creator' content='Austin Fonacier' />
|
143
|
+
</head>
|
144
|
+
<body></body>
|
145
|
+
</html>
|
146
|
+
HTML
|
147
|
+
doc.author.should eql("Austin Fonacier")
|
148
|
+
end
|
149
|
+
|
150
|
+
it "should pick up readability's recommended author format" do
|
151
|
+
doc = Readability::Document.new(<<-HTML)
|
152
|
+
<html>
|
153
|
+
<head>
|
154
|
+
</head>
|
155
|
+
<body>
|
156
|
+
<p class="byline author vcard">
|
157
|
+
By <cite class="fn">Austin Fonacier</span>
|
158
|
+
</p>
|
159
|
+
</body>
|
160
|
+
</html>
|
161
|
+
HTML
|
162
|
+
doc.author.should eql("Austin Fonacier")
|
163
|
+
end
|
164
|
+
|
165
|
+
it "should pick up vcard fn" do
|
166
|
+
doc = Readability::Document.new(<<-HTML)
|
167
|
+
<html>
|
168
|
+
<head>
|
169
|
+
</head>
|
170
|
+
<body>
|
171
|
+
<div class="author">By</div>
|
172
|
+
<div class="author vcard">
|
173
|
+
<a class="url fn" href="http://austinlivesinyotests.com/">Austin Fonacier</a>
|
174
|
+
</div>
|
175
|
+
</body>
|
176
|
+
</html>
|
177
|
+
HTML
|
178
|
+
doc.author.should eql("Austin Fonacier")
|
179
|
+
end
|
180
|
+
|
181
|
+
it "should pick up <a rel='author'>" do
|
182
|
+
doc = Readability::Document.new(<<-HTML)
|
183
|
+
<html>
|
184
|
+
<head></head>
|
185
|
+
<body>
|
186
|
+
<a rel="author" href="http://google.com">Danny Banks (rel)</a>
|
187
|
+
</body>
|
188
|
+
</html>
|
189
|
+
HTML
|
190
|
+
doc.author.should eql("Danny Banks (rel)")
|
191
|
+
end
|
192
|
+
|
193
|
+
it "should pick up <div id='author'>" do
|
194
|
+
doc = Readability::Document.new(<<-HTML)
|
195
|
+
<html>
|
196
|
+
<head></head>
|
197
|
+
<body>
|
198
|
+
<div id="author">Austin Fonacier (author)</div>
|
199
|
+
</body>
|
200
|
+
</html>
|
201
|
+
HTML
|
202
|
+
doc.author.should eql("Austin Fonacier (author)")
|
203
|
+
end
|
204
|
+
end
|
205
|
+
|
206
|
+
describe "score_node" do
|
207
|
+
before do
|
208
|
+
@doc = Readability::Document.new(<<-HTML)
|
209
|
+
<html>
|
210
|
+
<body>
|
211
|
+
<div id='elem1'>
|
212
|
+
<p>some content</p>
|
213
|
+
</div>
|
214
|
+
<th id='elem2'>
|
215
|
+
<p>some other content</p>
|
216
|
+
</th>
|
217
|
+
</body>
|
218
|
+
</html>
|
219
|
+
HTML
|
220
|
+
@elem1 = @doc.html.css("#elem1").first
|
221
|
+
@elem2 = @doc.html.css("#elem2").first
|
222
|
+
end
|
223
|
+
|
224
|
+
it "should like <div>s more than <th>s" do
|
225
|
+
@doc.score_node(@elem1)[:content_score].should > @doc.score_node(@elem2)[:content_score]
|
226
|
+
end
|
227
|
+
|
228
|
+
it "should like classes like text more than classes like comment" do
|
229
|
+
@elem2.name = "div"
|
230
|
+
@doc.score_node(@elem1)[:content_score].should == @doc.score_node(@elem2)[:content_score]
|
231
|
+
@elem1['class'] = "text"
|
232
|
+
@elem2['class'] = "comment"
|
233
|
+
@doc.score_node(@elem1)[:content_score].should > @doc.score_node(@elem2)[:content_score]
|
234
|
+
end
|
235
|
+
end
|
236
|
+
|
237
|
+
describe "remove_unlikely_candidates!" do
|
238
|
+
before do
|
239
|
+
@doc = Readability::Document.new(@simple_html_fixture)
|
240
|
+
@doc.remove_unlikely_candidates!
|
241
|
+
end
|
242
|
+
|
243
|
+
it "should remove things that have class comment" do
|
244
|
+
@doc.html.inner_html.should_not =~ /a comment/
|
245
|
+
end
|
246
|
+
|
247
|
+
it "should not remove body tags" do
|
248
|
+
@doc.html.inner_html.should =~ /<\/body>/
|
249
|
+
end
|
250
|
+
|
251
|
+
it "should not remove things with class comment and id body" do
|
252
|
+
@doc.html.inner_html.should =~ /real content/
|
253
|
+
end
|
254
|
+
end
|
255
|
+
|
256
|
+
describe "score_paragraphs" do
|
257
|
+
before(:each) do
|
258
|
+
@doc = Readability::Document.new(<<-HTML)
|
259
|
+
<html>
|
260
|
+
<head>
|
261
|
+
<title>title!</title>
|
262
|
+
</head>
|
263
|
+
<body id="body">
|
264
|
+
<div id="div1">
|
265
|
+
<div id="div2>
|
266
|
+
<p id="some_comment">a comment</p>
|
267
|
+
</div>
|
268
|
+
<p id="some_text">some text</p>
|
269
|
+
</div>
|
270
|
+
<div id="div3">
|
271
|
+
<p id="some_text2">some more text</p>
|
272
|
+
</div>
|
273
|
+
</body>
|
274
|
+
</html><!-- " -->
|
275
|
+
HTML
|
276
|
+
@candidates = @doc.score_paragraphs(0)
|
277
|
+
end
|
278
|
+
|
279
|
+
it "should score elements in the document" do
|
280
|
+
@candidates.values.length.should == 3
|
281
|
+
end
|
282
|
+
|
283
|
+
it "should prefer the body in this particular example" do
|
284
|
+
@candidates.values.sort { |a, b|
|
285
|
+
b[:content_score] <=> a[:content_score]
|
286
|
+
}.first[:elem][:id].should == "body"
|
287
|
+
end
|
288
|
+
|
289
|
+
context "when two consequent br tags are used instead of p" do
|
290
|
+
it "should assign the higher score to the first paragraph in this particular example" do
|
291
|
+
@doc = Readability::Document.new(<<-HTML)
|
292
|
+
<html>
|
293
|
+
<head>
|
294
|
+
<title>title!</title>
|
295
|
+
</head>
|
296
|
+
<body id="body">
|
297
|
+
<div id="post1">
|
298
|
+
This is the main content!<br/><br/>
|
299
|
+
Zebra found killed butcher with the chainsaw.<br/><br/>
|
300
|
+
If only I could think of an example, oh, wait.
|
301
|
+
</div>
|
302
|
+
<div id="post2">
|
303
|
+
This is not the content and although it's longer if you meaure it in characters,
|
304
|
+
it's supposed to have lower score than the previous paragraph. And it's only because
|
305
|
+
of the previous paragraph is not one paragraph, it's three subparagraphs
|
306
|
+
</div>
|
307
|
+
</body>
|
308
|
+
</html>
|
309
|
+
HTML
|
310
|
+
@candidates = @doc.score_paragraphs(0)
|
311
|
+
@candidates.values.sort_by { |a| -a[:content_score] }.first[:elem][:id].should == 'post1'
|
312
|
+
end
|
313
|
+
end
|
314
|
+
end
|
315
|
+
|
316
|
+
describe "the cant_read.html fixture" do
|
317
|
+
it "should work on the cant_read.html fixture with some allowed tags" do
|
318
|
+
allowed_tags = %w[div span table tr td p i strong u h1 h2 h3 h4 pre code br a]
|
319
|
+
allowed_attributes = %w[href]
|
320
|
+
html = File.read(File.dirname(__FILE__) + "/fixtures/cant_read.html")
|
321
|
+
Readability::Document.new(html, :tags => allowed_tags, :attributes => allowed_attributes).content.should match(/Can you talk a little about how you developed the looks for the/)
|
322
|
+
end
|
323
|
+
end
|
324
|
+
|
325
|
+
describe "general functionality" do
|
326
|
+
before do
|
327
|
+
@doc = Readability::Document.new("<html><head><title>title!</title></head><body><div><p>Some content</p></div></body>",
|
328
|
+
:min_text_length => 0, :retry_length => 1)
|
329
|
+
end
|
330
|
+
|
331
|
+
it "should return the main page content" do
|
332
|
+
@doc.content.should match("Some content")
|
333
|
+
end
|
334
|
+
|
335
|
+
it "should return the page title if present" do
|
336
|
+
@doc.title.should match("title!")
|
337
|
+
|
338
|
+
doc = Readability::Document.new("<html><head></head><body><div><p>Some content</p></div></body>",
|
339
|
+
:min_text_length => 0, :retry_length => 1)
|
340
|
+
doc.title.should be_nil
|
341
|
+
end
|
342
|
+
end
|
343
|
+
|
344
|
+
describe "ignoring sidebars" do
|
345
|
+
before do
|
346
|
+
@doc = Readability::Document.new("<html><head><title>title!</title></head><body><div><p>Some content</p></div><div class='sidebar'><p>sidebar<p></div></body>",
|
347
|
+
:min_text_length => 0, :retry_length => 1)
|
348
|
+
end
|
349
|
+
|
350
|
+
it "should not return the sidebar" do
|
351
|
+
@doc.content.should_not match("sidebar")
|
352
|
+
end
|
353
|
+
end
|
354
|
+
|
355
|
+
describe "inserting space for block elements" do
|
356
|
+
before do
|
357
|
+
@doc = Readability::Document.new(<<-HTML, :min_text_length => 0, :retry_length => 1)
|
358
|
+
<html><head><title>title!</title></head>
|
359
|
+
<body>
|
360
|
+
<div>
|
361
|
+
<p>a<br>b<hr>c<address>d</address>f/p>
|
362
|
+
</div>
|
363
|
+
</body>
|
364
|
+
</html>
|
365
|
+
HTML
|
366
|
+
end
|
367
|
+
|
368
|
+
it "should not return the sidebar" do
|
369
|
+
@doc.content.should_not match("a b c d f")
|
370
|
+
end
|
371
|
+
end
|
372
|
+
|
373
|
+
describe "outputs good stuff for known documents" do
|
374
|
+
before do
|
375
|
+
@html_files = Dir.glob(File.dirname(__FILE__) + "/fixtures/samples/*.html")
|
376
|
+
@samples = @html_files.map {|filename| File.basename(filename, '.html') }
|
377
|
+
end
|
378
|
+
|
379
|
+
it "should output expected fragments of text" do
|
380
|
+
checks = 0
|
381
|
+
@samples.each do |sample|
|
382
|
+
html = File.read(File.dirname(__FILE__) + "/fixtures/samples/#{sample}.html")
|
383
|
+
doc = Readability::Document.new(html).content
|
384
|
+
|
385
|
+
load "fixtures/samples/#{sample}-fragments.rb"
|
386
|
+
#puts "testing #{sample}..."
|
387
|
+
|
388
|
+
$required_fragments.each do |required_text|
|
389
|
+
doc.should include(required_text)
|
390
|
+
checks += 1
|
391
|
+
end
|
392
|
+
|
393
|
+
$excluded_fragments.each do |text_to_avoid|
|
394
|
+
doc.should_not include(text_to_avoid)
|
395
|
+
checks += 1
|
396
|
+
end
|
397
|
+
end
|
398
|
+
#puts "Performed #{checks} checks."
|
399
|
+
end
|
400
|
+
end
|
401
|
+
|
402
|
+
describe "encoding guessing" do
|
403
|
+
if RUBY_VERSION =~ /^1\.9\./
|
404
|
+
context "with ruby 1.9.2" do
|
405
|
+
it "should correctly guess and enforce HTML encoding" do
|
406
|
+
doc = Readability::Document.new("<html><head><meta http-equiv='content-type' content='text/html; charset=LATIN1'></head><body><div>hi!</div></body></html>")
|
407
|
+
content = doc.content
|
408
|
+
content.encoding.to_s.should == "ISO-8859-1"
|
409
|
+
content.should be_valid_encoding
|
410
|
+
end
|
411
|
+
|
412
|
+
it "should allow encoding guessing to be skipped" do
|
413
|
+
do_not_allow(GuessHtmlEncoding).encode
|
414
|
+
doc = Readability::Document.new(@simple_html_fixture, :do_not_guess_encoding => true)
|
415
|
+
doc.content
|
416
|
+
end
|
417
|
+
|
418
|
+
it "should allow encoding guessing to be overridden" do
|
419
|
+
do_not_allow(GuessHtmlEncoding).encode
|
420
|
+
doc = Readability::Document.new(@simple_html_fixture, :encoding => "UTF-8")
|
421
|
+
doc.content
|
422
|
+
end
|
423
|
+
end
|
424
|
+
end
|
425
|
+
end
|
426
|
+
|
427
|
+
describe "#make_html" do
|
428
|
+
it "should strip the html comments tag" do
|
429
|
+
doc = Readability::Document.new("<html><head><meta http-equiv='content-type' content='text/html; charset=LATIN1'></head><body><div>hi!<!-- bye~ --></div></body></html>")
|
430
|
+
content = doc.content
|
431
|
+
content.should include("hi!")
|
432
|
+
content.should_not include("bye")
|
433
|
+
end
|
434
|
+
|
435
|
+
it "should not error with empty content" do
|
436
|
+
Readability::Document.new('').content.should == '<div><div></div></div>'
|
437
|
+
end
|
438
|
+
|
439
|
+
it "should not error with a document with no <body>" do
|
440
|
+
Readability::Document.new('<html><head><meta http-equiv="refresh" content="0;URL=http://example.com"></head></html>').content.should == '<div><div></div></div>'
|
441
|
+
end
|
442
|
+
end
|
443
|
+
|
444
|
+
describe "No side-effects" do
|
445
|
+
before do
|
446
|
+
@bbc = File.read(File.dirname(__FILE__) + "/fixtures/bbc.html")
|
447
|
+
@nytimes = File.read(File.dirname(__FILE__) + "/fixtures/nytimes.html")
|
448
|
+
@thesum = File.read(File.dirname(__FILE__) + "/fixtures/thesun.html")
|
449
|
+
end
|
450
|
+
|
451
|
+
it "should not have any side-effects when calling content() and then images()" do
|
452
|
+
@doc=Readability::Document.new(@nytimes, :tags => %w[div p img a], :attributes => %w[src href], :remove_empty_nodes => false,
|
453
|
+
:do_not_guess_encoding => true)
|
454
|
+
@doc.images.should == ["http://graphics8.nytimes.com/images/2011/12/02/opinion/02fixes-freelancersunion/02fixes-freelancersunion-blog427.jpg"]
|
455
|
+
@doc.content
|
456
|
+
@doc.images.should == ["http://graphics8.nytimes.com/images/2011/12/02/opinion/02fixes-freelancersunion/02fixes-freelancersunion-blog427.jpg"]
|
457
|
+
end
|
458
|
+
|
459
|
+
it "should not have any side-effects when calling content() multiple times" do
|
460
|
+
@doc=Readability::Document.new(@nytimes, :tags => %w[div p img a], :attributes => %w[src href], :remove_empty_nodes => false,
|
461
|
+
:do_not_guess_encoding => true)
|
462
|
+
@doc.content.should == @doc.content
|
463
|
+
end
|
464
|
+
|
465
|
+
it "should not have any side-effects when calling content and images multiple times" do
|
466
|
+
@doc=Readability::Document.new(@nytimes, :tags => %w[div p img a], :attributes => %w[src href], :remove_empty_nodes => false,
|
467
|
+
:do_not_guess_encoding => true)
|
468
|
+
@doc.images.should == ["http://graphics8.nytimes.com/images/2011/12/02/opinion/02fixes-freelancersunion/02fixes-freelancersunion-blog427.jpg"]
|
469
|
+
@doc.content.should == @doc.content
|
470
|
+
@doc.images.should == ["http://graphics8.nytimes.com/images/2011/12/02/opinion/02fixes-freelancersunion/02fixes-freelancersunion-blog427.jpg"]
|
471
|
+
end
|
472
|
+
|
473
|
+
end
|
474
|
+
|
475
|
+
describe "Code blocks" do
|
476
|
+
before do
|
477
|
+
@code = File.read(File.dirname(__FILE__) + "/fixtures/code.html")
|
478
|
+
@content = Readability::Document.new(@code,
|
479
|
+
:tags => %w[div p img a ul ol li h1 h2 h3 h4 h5 h6 blockquote strong em b code pre],
|
480
|
+
:attributes => %w[src href],
|
481
|
+
:remove_empty_nodes => false).content
|
482
|
+
@doc = Nokogiri::HTML(@content)
|
483
|
+
end
|
484
|
+
|
485
|
+
it "preserve the code blocks" do
|
486
|
+
@doc.css("code pre").text.should == "\nroot\n indented\n "
|
487
|
+
end
|
488
|
+
|
489
|
+
it "preserve backwards code blocks" do
|
490
|
+
@doc.css("pre code").text.should == "\nsecond\n indented\n "
|
491
|
+
end
|
492
|
+
end
|
493
|
+
|
494
|
+
describe "remove all tags" do
|
495
|
+
it "should work for an incomplete piece of HTML" do
|
496
|
+
doc = Readability::Document.new('<div>test</div', :tags => [])
|
497
|
+
doc.content.should == 'test'
|
498
|
+
end
|
499
|
+
|
500
|
+
it "should work for a HTML document" do
|
501
|
+
doc = Readability::Document.new('<html><head><title>title!</title></head><body><div><p>test</p></div></body></html>',
|
502
|
+
:tags => [])
|
503
|
+
doc.content.should == 'test'
|
504
|
+
end
|
505
|
+
|
506
|
+
it "should work for a plain text" do
|
507
|
+
doc = Readability::Document.new('test', :tags => [])
|
508
|
+
doc.content.should == 'test'
|
509
|
+
end
|
510
|
+
end
|
511
|
+
|
512
|
+
describe "boing boing" do
|
513
|
+
let(:boing_boing) {
|
514
|
+
File.read(File.dirname(__FILE__) + "/fixtures/boing_boing.html")
|
515
|
+
}
|
516
|
+
|
517
|
+
it "contains incorrect data by default" do
|
518
|
+
# NOTE: in an ideal world this spec starts failing
|
519
|
+
# and readability correctly detects content for the
|
520
|
+
# boing boing sample.
|
521
|
+
|
522
|
+
doc = Readability::Document.new(boing_boing)
|
523
|
+
|
524
|
+
content = doc.content
|
525
|
+
(content !~ /Bees and Bombs/).should == true
|
526
|
+
content.should =~ /ADVERTISE/
|
527
|
+
end
|
528
|
+
|
529
|
+
it "should apply whitelist" do
|
530
|
+
|
531
|
+
doc = Readability::Document.new(boing_boing,
|
532
|
+
whitelist: ".post-content")
|
533
|
+
content = doc.content
|
534
|
+
content.should =~ /Bees and Bombs/
|
535
|
+
end
|
536
|
+
|
537
|
+
it "should apply blacklist" do
|
538
|
+
doc = Readability::Document.new(boing_boing, blacklist: "#sidebar_adblock")
|
539
|
+
content = doc.content
|
540
|
+
(content !~ /ADVERTISE/).should == true
|
541
|
+
|
542
|
+
end
|
543
|
+
end
|
544
|
+
end
|