jruby-readability 0.5.6
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/jruby-readability.rb +1 -0
- data/lib/readability.rb +475 -0
- metadata +130 -0
@@ -0,0 +1 @@
|
|
1
|
+
require 'readability'
|
data/lib/readability.rb
ADDED
@@ -0,0 +1,475 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'guess_html_encoding'
|
4
|
+
|
5
|
+
module Readability
|
6
|
+
class Document
|
7
|
+
DEFAULT_OPTIONS = {
|
8
|
+
:retry_length => 250,
|
9
|
+
:min_text_length => 25,
|
10
|
+
:remove_unlikely_candidates => true,
|
11
|
+
:weight_classes => true,
|
12
|
+
:clean_conditionally => true,
|
13
|
+
:remove_empty_nodes => true,
|
14
|
+
:min_image_width => 130,
|
15
|
+
:min_image_height => 80,
|
16
|
+
:ignore_image_format => []
|
17
|
+
}.freeze
|
18
|
+
|
19
|
+
attr_accessor :options, :html, :best_candidate, :candidates, :best_candidate_has_image
|
20
|
+
|
21
|
+
def initialize(input, options = {})
|
22
|
+
@options = DEFAULT_OPTIONS.merge(options)
|
23
|
+
@input = input
|
24
|
+
|
25
|
+
if RUBY_VERSION =~ /^1\.9\./ && !@options[:encoding]
|
26
|
+
@input = GuessHtmlEncoding.encode(@input, @options[:html_headers]) unless @options[:do_not_guess_encoding]
|
27
|
+
@options[:encoding] = @input.encoding.to_s
|
28
|
+
end
|
29
|
+
|
30
|
+
@input = @input.gsub(REGEXES[:replaceBrsRe], '</p><p>').gsub(REGEXES[:replaceFontsRe], '<\1span>')
|
31
|
+
@remove_unlikely_candidates = @options[:remove_unlikely_candidates]
|
32
|
+
@weight_classes = @options[:weight_classes]
|
33
|
+
@clean_conditionally = @options[:clean_conditionally]
|
34
|
+
@best_candidate_has_image = true
|
35
|
+
make_html
|
36
|
+
end
|
37
|
+
|
38
|
+
def prepare_candidates
|
39
|
+
@html.css("script, style").each { |i| i.remove }
|
40
|
+
remove_unlikely_candidates! if @remove_unlikely_candidates
|
41
|
+
transform_misused_divs_into_paragraphs!
|
42
|
+
|
43
|
+
@candidates = score_paragraphs(options[:min_text_length])
|
44
|
+
@best_candidate = select_best_candidate(@candidates)
|
45
|
+
end
|
46
|
+
|
47
|
+
def make_html
|
48
|
+
@html = Nokogiri::HTML(@input, nil, @options[:encoding])
|
49
|
+
# In case document has no body, such as from empty string or redirect
|
50
|
+
@html = Nokogiri::HTML('<body />', nil, @options[:encoding]) if @html.css('body').length == 0
|
51
|
+
|
52
|
+
# Remove html comment tags
|
53
|
+
@html.xpath('//comment()').each { |i| i.remove }
|
54
|
+
end
|
55
|
+
|
56
|
+
def images(content=nil, reload=false)
|
57
|
+
begin
|
58
|
+
require 'fastimage'
|
59
|
+
rescue LoadError
|
60
|
+
raise "Please install fastimage in order to use the #images feature."
|
61
|
+
end
|
62
|
+
|
63
|
+
@best_candidate_has_image = false if reload
|
64
|
+
|
65
|
+
prepare_candidates
|
66
|
+
list_images = []
|
67
|
+
tested_images = []
|
68
|
+
content = @best_candidate[:elem] unless reload
|
69
|
+
|
70
|
+
return list_images if content.nil?
|
71
|
+
elements = content.css("img").map(&:attributes)
|
72
|
+
|
73
|
+
elements.each do |element|
|
74
|
+
next unless element["src"]
|
75
|
+
|
76
|
+
url = element["src"].value
|
77
|
+
height = element["height"].nil? ? 0 : element["height"].value.to_i
|
78
|
+
width = element["width"].nil? ? 0 : element["width"].value.to_i
|
79
|
+
|
80
|
+
if url =~ /\Ahttps?:\/\//i && (height.zero? || width.zero?)
|
81
|
+
image = get_image_size(url)
|
82
|
+
next unless image
|
83
|
+
else
|
84
|
+
image = {:width => width, :height => height}
|
85
|
+
end
|
86
|
+
|
87
|
+
image[:format] = File.extname(url).gsub(".", "")
|
88
|
+
|
89
|
+
if tested_images.include?(url)
|
90
|
+
debug("Image was tested: #{url}")
|
91
|
+
next
|
92
|
+
end
|
93
|
+
|
94
|
+
tested_images.push(url)
|
95
|
+
if image_meets_criteria?(image)
|
96
|
+
list_images << url
|
97
|
+
else
|
98
|
+
debug("Image discarded: #{url} - height: #{image[:height]} - width: #{image[:width]} - format: #{image[:format]}")
|
99
|
+
end
|
100
|
+
end
|
101
|
+
|
102
|
+
(list_images.empty? and content != @html) ? images(@html, true) : list_images
|
103
|
+
end
|
104
|
+
|
105
|
+
def get_image_size(url)
|
106
|
+
begin
|
107
|
+
w, h = FastImage.size(url)
|
108
|
+
raise "Couldn't get size." if w.nil? || h.nil?
|
109
|
+
{width: w, height: h}
|
110
|
+
rescue => e
|
111
|
+
debug("Image error: #{e}")
|
112
|
+
nil
|
113
|
+
end
|
114
|
+
end
|
115
|
+
|
116
|
+
def image_meets_criteria?(image)
|
117
|
+
return false if options[:ignore_image_format].include?(image[:format].downcase)
|
118
|
+
image[:width] >= (options[:min_image_width] || 0) && image[:height] >= (options[:min_image_height] || 0)
|
119
|
+
end
|
120
|
+
|
121
|
+
REGEXES = {
|
122
|
+
:unlikelyCandidatesRe => /combx|comment|community|disqus|extra|foot|header|menu|remark|rss|shoutbox|sidebar|sponsor|ad-break|agegate|pagination|pager|popup/i,
|
123
|
+
:okMaybeItsACandidateRe => /and|article|body|column|main|shadow/i,
|
124
|
+
:positiveRe => /article|body|content|entry|hentry|main|page|pagination|post|text|blog|story/i,
|
125
|
+
:negativeRe => /combx|comment|com-|contact|foot|footer|footnote|masthead|media|meta|outbrain|promo|related|scroll|shoutbox|sidebar|sponsor|shopping|tags|tool|widget/i,
|
126
|
+
:divToPElementsRe => /<(a|blockquote|dl|div|img|ol|p|pre|table|ul)/i,
|
127
|
+
:replaceBrsRe => /(<br[^>]*>[ \n\r\t]*){2,}/i,
|
128
|
+
:replaceFontsRe => /<(\/?)font[^>]*>/i,
|
129
|
+
:trimRe => /^\s+|\s+$/,
|
130
|
+
:normalizeRe => /\s{2,}/,
|
131
|
+
:killBreaksRe => /(<br\s*\/?>(\s| ?)*){1,}/,
|
132
|
+
:videoRe => /http:\/\/(www\.)?(youtube|vimeo)\.com/i
|
133
|
+
}
|
134
|
+
|
135
|
+
def title
|
136
|
+
title = @html.css("title").first
|
137
|
+
title ? title.text : nil
|
138
|
+
end
|
139
|
+
|
140
|
+
# Look through the @html document looking for the author
|
141
|
+
# Precedence Information here on the wiki: (TODO attach wiki URL if it is accepted)
|
142
|
+
# Returns nil if no author is detected
|
143
|
+
def author
|
144
|
+
# Let's grab this author:
|
145
|
+
# <meta name="dc.creator" content="Finch - http://www.getfinch.com" />
|
146
|
+
author_elements = @html.xpath('//meta[@name = "dc.creator"]')
|
147
|
+
unless author_elements.empty?
|
148
|
+
author_elements.each do |element|
|
149
|
+
if element['content']
|
150
|
+
return element['content'].strip
|
151
|
+
end
|
152
|
+
end
|
153
|
+
end
|
154
|
+
|
155
|
+
# Now let's try to grab this
|
156
|
+
# <span class="byline author vcard"><span>By</span><cite class="fn">Austin Fonacier</cite></span>
|
157
|
+
# <div class="author">By</div><div class="author vcard"><a class="url fn" href="http://austinlivesinyoapp.com/">Austin Fonacier</a></div>
|
158
|
+
author_elements = @html.xpath('//*[contains(@class, "vcard")]//*[contains(@class, "fn")]')
|
159
|
+
unless author_elements.empty?
|
160
|
+
author_elements.each do |element|
|
161
|
+
if element.text
|
162
|
+
return element.text.strip
|
163
|
+
end
|
164
|
+
end
|
165
|
+
end
|
166
|
+
|
167
|
+
# Now let's try to grab this
|
168
|
+
# <a rel="author" href="http://dbanksdesign.com">Danny Banks (rel)</a>
|
169
|
+
# TODO: strip out the (rel)?
|
170
|
+
author_elements = @html.xpath('//a[@rel = "author"]')
|
171
|
+
unless author_elements.empty?
|
172
|
+
author_elements.each do |element|
|
173
|
+
if element.text
|
174
|
+
return element.text.strip
|
175
|
+
end
|
176
|
+
end
|
177
|
+
end
|
178
|
+
|
179
|
+
author_elements = @html.xpath('//*[@id = "author"]')
|
180
|
+
unless author_elements.empty?
|
181
|
+
author_elements.each do |element|
|
182
|
+
if element.text
|
183
|
+
return element.text.strip
|
184
|
+
end
|
185
|
+
end
|
186
|
+
end
|
187
|
+
end
|
188
|
+
|
189
|
+
def content(remove_unlikely_candidates = :default)
|
190
|
+
@remove_unlikely_candidates = false if remove_unlikely_candidates == false
|
191
|
+
|
192
|
+
prepare_candidates
|
193
|
+
article = get_article(@candidates, @best_candidate)
|
194
|
+
|
195
|
+
cleaned_article = sanitize(article, @candidates, options)
|
196
|
+
if article.text.strip.length < options[:retry_length]
|
197
|
+
if @remove_unlikely_candidates
|
198
|
+
@remove_unlikely_candidates = false
|
199
|
+
elsif @weight_classes
|
200
|
+
@weight_classes = false
|
201
|
+
elsif @clean_conditionally
|
202
|
+
@clean_conditionally = false
|
203
|
+
else
|
204
|
+
# nothing we can do
|
205
|
+
return cleaned_article
|
206
|
+
end
|
207
|
+
|
208
|
+
make_html
|
209
|
+
content
|
210
|
+
else
|
211
|
+
cleaned_article
|
212
|
+
end
|
213
|
+
end
|
214
|
+
|
215
|
+
def get_article(candidates, best_candidate)
|
216
|
+
# Now that we have the top candidate, look through its siblings for content that might also be related.
|
217
|
+
# Things like preambles, content split by ads that we removed, etc.
|
218
|
+
|
219
|
+
sibling_score_threshold = [10, best_candidate[:content_score] * 0.2].max
|
220
|
+
output = Nokogiri::XML::Node.new('div', @html)
|
221
|
+
best_candidate[:elem].parent.children.each do |sibling|
|
222
|
+
append = false
|
223
|
+
append = true if sibling == best_candidate[:elem]
|
224
|
+
append = true if candidates[sibling] && candidates[sibling][:content_score] >= sibling_score_threshold
|
225
|
+
|
226
|
+
if sibling.name.downcase == "p"
|
227
|
+
link_density = get_link_density(sibling)
|
228
|
+
node_content = sibling.text
|
229
|
+
node_length = node_content.length
|
230
|
+
|
231
|
+
if node_length > 80 && link_density < 0.25
|
232
|
+
append = true
|
233
|
+
elsif node_length < 80 && link_density == 0 && node_content =~ /\.( |$)/
|
234
|
+
append = true
|
235
|
+
end
|
236
|
+
end
|
237
|
+
|
238
|
+
if append
|
239
|
+
sibling_dup = sibling.dup # otherwise the state of the document in processing will change, thus creating side effects
|
240
|
+
sibling_dup.name = "div" unless %w[div p].include?(sibling.name.downcase)
|
241
|
+
output << sibling_dup
|
242
|
+
end
|
243
|
+
end
|
244
|
+
|
245
|
+
output
|
246
|
+
end
|
247
|
+
|
248
|
+
def select_best_candidate(candidates)
|
249
|
+
sorted_candidates = candidates.values.sort { |a, b| b[:content_score] <=> a[:content_score] }
|
250
|
+
|
251
|
+
debug("Top 5 candidates:")
|
252
|
+
sorted_candidates[0...5].each do |candidate|
|
253
|
+
debug("Candidate #{candidate[:elem].name}##{candidate[:elem][:id]}.#{candidate[:elem][:class]} with score #{candidate[:content_score]}")
|
254
|
+
end
|
255
|
+
|
256
|
+
best_candidate = sorted_candidates.first || { :elem => @html.css("body").first, :content_score => 0 }
|
257
|
+
debug("Best candidate #{best_candidate[:elem].name}##{best_candidate[:elem][:id]}.#{best_candidate[:elem][:class]} with score #{best_candidate[:content_score]}")
|
258
|
+
|
259
|
+
best_candidate
|
260
|
+
end
|
261
|
+
|
262
|
+
def get_link_density(elem)
|
263
|
+
link_length = elem.css("a").map(&:text).join("").length
|
264
|
+
text_length = elem.text.length
|
265
|
+
link_length / text_length.to_f
|
266
|
+
end
|
267
|
+
|
268
|
+
def score_paragraphs(min_text_length)
|
269
|
+
candidates = {}
|
270
|
+
@html.css("p,td").each do |elem|
|
271
|
+
parent_node = elem.parent
|
272
|
+
grand_parent_node = parent_node.respond_to?(:parent) ? parent_node.parent : nil
|
273
|
+
inner_text = elem.text
|
274
|
+
|
275
|
+
# If this paragraph is less than 25 characters, don't even count it.
|
276
|
+
next if inner_text.length < min_text_length
|
277
|
+
|
278
|
+
candidates[parent_node] ||= score_node(parent_node)
|
279
|
+
candidates[grand_parent_node] ||= score_node(grand_parent_node) if grand_parent_node
|
280
|
+
|
281
|
+
content_score = 1
|
282
|
+
content_score += inner_text.split(',').length
|
283
|
+
content_score += [(inner_text.length / 100).to_i, 3].min
|
284
|
+
|
285
|
+
candidates[parent_node][:content_score] += content_score
|
286
|
+
candidates[grand_parent_node][:content_score] += content_score / 2.0 if grand_parent_node
|
287
|
+
end
|
288
|
+
|
289
|
+
# Scale the final candidates score based on link density. Good content should have a
|
290
|
+
# relatively small link density (5% or less) and be mostly unaffected by this operation.
|
291
|
+
candidates.each do |elem, candidate|
|
292
|
+
candidate[:content_score] = candidate[:content_score] * (1 - get_link_density(elem))
|
293
|
+
end
|
294
|
+
|
295
|
+
candidates
|
296
|
+
end
|
297
|
+
|
298
|
+
def class_weight(e)
|
299
|
+
weight = 0
|
300
|
+
return weight unless @weight_classes
|
301
|
+
|
302
|
+
if e[:class] && e[:class] != ""
|
303
|
+
if e[:class] =~ REGEXES[:negativeRe]
|
304
|
+
weight -= 25
|
305
|
+
end
|
306
|
+
|
307
|
+
if e[:class] =~ REGEXES[:positiveRe]
|
308
|
+
weight += 25
|
309
|
+
end
|
310
|
+
end
|
311
|
+
|
312
|
+
if e[:id] && e[:id] != ""
|
313
|
+
if e[:id] =~ REGEXES[:negativeRe]
|
314
|
+
weight -= 25
|
315
|
+
end
|
316
|
+
|
317
|
+
if e[:id] =~ REGEXES[:positiveRe]
|
318
|
+
weight += 25
|
319
|
+
end
|
320
|
+
end
|
321
|
+
|
322
|
+
weight
|
323
|
+
end
|
324
|
+
|
325
|
+
def score_node(elem)
|
326
|
+
content_score = class_weight(elem)
|
327
|
+
case elem.name.downcase
|
328
|
+
when "div"
|
329
|
+
content_score += 5
|
330
|
+
when "blockquote"
|
331
|
+
content_score += 3
|
332
|
+
when "form"
|
333
|
+
content_score -= 3
|
334
|
+
when "th"
|
335
|
+
content_score -= 5
|
336
|
+
end
|
337
|
+
{ :content_score => content_score, :elem => elem }
|
338
|
+
end
|
339
|
+
|
340
|
+
def debug(str)
|
341
|
+
puts str if options[:debug]
|
342
|
+
end
|
343
|
+
|
344
|
+
def remove_unlikely_candidates!
|
345
|
+
@html.css("*").each do |elem|
|
346
|
+
str = "#{elem[:class]}#{elem[:id]}"
|
347
|
+
if str =~ REGEXES[:unlikelyCandidatesRe] && str !~ REGEXES[:okMaybeItsACandidateRe] && (elem.name.downcase != 'html') && (elem.name.downcase != 'body')
|
348
|
+
debug("Removing unlikely candidate - #{str}")
|
349
|
+
elem.remove
|
350
|
+
end
|
351
|
+
end
|
352
|
+
end
|
353
|
+
|
354
|
+
def transform_misused_divs_into_paragraphs!
|
355
|
+
@html.css("*").each do |elem|
|
356
|
+
if elem.name.downcase == "div"
|
357
|
+
# transform <div>s that do not contain other block elements into <p>s
|
358
|
+
if elem.inner_html !~ REGEXES[:divToPElementsRe]
|
359
|
+
debug("Altering div(##{elem[:id]}.#{elem[:class]}) to p");
|
360
|
+
elem.name = "p"
|
361
|
+
end
|
362
|
+
else
|
363
|
+
# wrap text nodes in p tags
|
364
|
+
# elem.children.each do |child|
|
365
|
+
# if child.text?
|
366
|
+
# debug("wrapping text node with a p")
|
367
|
+
# child.swap("<p>#{child.text}</p>")
|
368
|
+
# end
|
369
|
+
# end
|
370
|
+
end
|
371
|
+
end
|
372
|
+
end
|
373
|
+
|
374
|
+
def sanitize(node, candidates, options = {})
|
375
|
+
node.css("h1, h2, h3, h4, h5, h6").each do |header|
|
376
|
+
header.remove if class_weight(header) < 0 || get_link_density(header) > 0.33
|
377
|
+
end
|
378
|
+
|
379
|
+
node.css("form, object, iframe, embed").each do |elem|
|
380
|
+
elem.remove
|
381
|
+
end
|
382
|
+
|
383
|
+
if @options[:remove_empty_nodes]
|
384
|
+
# remove <p> tags that have no text content - this will also remove p tags that contain only images.
|
385
|
+
node.css("p").each do |elem|
|
386
|
+
elem.remove if elem.content.strip.empty?
|
387
|
+
end
|
388
|
+
end
|
389
|
+
|
390
|
+
# Conditionally clean <table>s, <ul>s, and <div>s
|
391
|
+
clean_conditionally(node, candidates, "table, ul, div")
|
392
|
+
|
393
|
+
# We'll sanitize all elements using a whitelist
|
394
|
+
base_whitelist = @options[:tags] || %w[div p]
|
395
|
+
# We'll add whitespace instead of block elements,
|
396
|
+
# so a<br>b will have a nice space between them
|
397
|
+
base_replace_with_whitespace = %w[br hr h1 h2 h3 h4 h5 h6 dl dd ol li ul address blockquote center]
|
398
|
+
|
399
|
+
# Use a hash for speed (don't want to make a million calls to include?)
|
400
|
+
whitelist = Hash.new
|
401
|
+
base_whitelist.each {|tag| whitelist[tag] = true }
|
402
|
+
replace_with_whitespace = Hash.new
|
403
|
+
base_replace_with_whitespace.each { |tag| replace_with_whitespace[tag] = true }
|
404
|
+
|
405
|
+
([node] + node.css("*")).each do |el|
|
406
|
+
# If element is in whitelist, delete all its attributes
|
407
|
+
if whitelist[el.node_name]
|
408
|
+
el.attributes.each { |a, x| el.delete(a) unless @options[:attributes] && @options[:attributes].include?(a.to_s) }
|
409
|
+
|
410
|
+
# Otherwise, replace the element with its contents
|
411
|
+
else
|
412
|
+
if replace_with_whitespace[el.node_name]
|
413
|
+
el.swap(Nokogiri::XML::Text.new(' ' << el.text << ' ', el.document))
|
414
|
+
else
|
415
|
+
el.swap(Nokogiri::XML::Text.new(el.text, el.document))
|
416
|
+
end
|
417
|
+
end
|
418
|
+
|
419
|
+
end
|
420
|
+
|
421
|
+
# Get rid of duplicate whitespace
|
422
|
+
node.to_html.gsub(/[\r\n\f]+/, "\n" ).gsub(/[\t ]+/, " ")
|
423
|
+
end
|
424
|
+
|
425
|
+
def clean_conditionally(node, candidates, selector)
|
426
|
+
return unless @clean_conditionally
|
427
|
+
node.css(selector).each do |el|
|
428
|
+
weight = class_weight(el)
|
429
|
+
content_score = candidates[el] ? candidates[el][:content_score] : 0
|
430
|
+
name = el.name.downcase
|
431
|
+
|
432
|
+
if weight + content_score < 0
|
433
|
+
el.remove
|
434
|
+
debug("Conditionally cleaned #{name}##{el[:id]}.#{el[:class]} with weight #{weight} and content score #{content_score} because score + content score was less than zero.")
|
435
|
+
elsif el.text.count(",") < 10
|
436
|
+
counts = %w[p img li a embed input].inject({}) { |m, kind| m[kind] = el.css(kind).length; m }
|
437
|
+
counts["li"] -= 100
|
438
|
+
|
439
|
+
content_length = el.text.strip.length # Count the text length excluding any surrounding whitespace
|
440
|
+
link_density = get_link_density(el)
|
441
|
+
to_remove = false
|
442
|
+
reason = ""
|
443
|
+
|
444
|
+
if counts["img"] > counts["p"]
|
445
|
+
reason = "too many images"
|
446
|
+
to_remove = true
|
447
|
+
elsif counts["li"] > counts["p"] && name != "ul" && name != "ol"
|
448
|
+
reason = "more <li>s than <p>s"
|
449
|
+
to_remove = true
|
450
|
+
elsif counts["input"] > (counts["p"] / 3).to_i
|
451
|
+
reason = "less than 3x <p>s than <input>s"
|
452
|
+
to_remove = true
|
453
|
+
elsif content_length < (options[:min_text_length] || TEXT_LENGTH_THRESHOLD) && (counts["img"] == 0 || counts["img"] > 2)
|
454
|
+
reason = "too short a content length without a single image"
|
455
|
+
to_remove = true
|
456
|
+
elsif weight < 25 && link_density > 0.2
|
457
|
+
reason = "too many links for its weight (#{weight})"
|
458
|
+
to_remove = true
|
459
|
+
elsif weight >= 25 && link_density > 0.5
|
460
|
+
reason = "too many links for its weight (#{weight})"
|
461
|
+
to_remove = true
|
462
|
+
elsif (counts["embed"] == 1 && content_length < 75) || counts["embed"] > 1
|
463
|
+
reason = "<embed>s with too short a content length, or too many <embed>s"
|
464
|
+
to_remove = true
|
465
|
+
end
|
466
|
+
|
467
|
+
if to_remove
|
468
|
+
debug("Conditionally cleaned #{name}##{el[:id]}.#{el[:class]} with weight #{weight} and content score #{content_score} because it has #{reason}.")
|
469
|
+
el.remove
|
470
|
+
end
|
471
|
+
end
|
472
|
+
end
|
473
|
+
end
|
474
|
+
end
|
475
|
+
end
|
metadata
ADDED
@@ -0,0 +1,130 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: jruby-readability
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.5.6
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Andrew Cantino
|
9
|
+
- starrhorne
|
10
|
+
- libc
|
11
|
+
- Kyle Maxwell
|
12
|
+
autorequire:
|
13
|
+
bindir: bin
|
14
|
+
cert_chain: []
|
15
|
+
date: 2012-12-14 00:00:00.000000000 Z
|
16
|
+
dependencies:
|
17
|
+
- !ruby/object:Gem::Dependency
|
18
|
+
name: rspec
|
19
|
+
requirement: !ruby/object:Gem::Requirement
|
20
|
+
none: false
|
21
|
+
requirements:
|
22
|
+
- - ! '>='
|
23
|
+
- !ruby/object:Gem::Version
|
24
|
+
version: '2.8'
|
25
|
+
type: :development
|
26
|
+
prerelease: false
|
27
|
+
version_requirements: !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ! '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '2.8'
|
33
|
+
- !ruby/object:Gem::Dependency
|
34
|
+
name: rspec-expectations
|
35
|
+
requirement: !ruby/object:Gem::Requirement
|
36
|
+
none: false
|
37
|
+
requirements:
|
38
|
+
- - ! '>='
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '2.8'
|
41
|
+
type: :development
|
42
|
+
prerelease: false
|
43
|
+
version_requirements: !ruby/object:Gem::Requirement
|
44
|
+
none: false
|
45
|
+
requirements:
|
46
|
+
- - ! '>='
|
47
|
+
- !ruby/object:Gem::Version
|
48
|
+
version: '2.8'
|
49
|
+
- !ruby/object:Gem::Dependency
|
50
|
+
name: rr
|
51
|
+
requirement: !ruby/object:Gem::Requirement
|
52
|
+
none: false
|
53
|
+
requirements:
|
54
|
+
- - ! '>='
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '1.0'
|
57
|
+
type: :development
|
58
|
+
prerelease: false
|
59
|
+
version_requirements: !ruby/object:Gem::Requirement
|
60
|
+
none: false
|
61
|
+
requirements:
|
62
|
+
- - ! '>='
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
version: '1.0'
|
65
|
+
- !ruby/object:Gem::Dependency
|
66
|
+
name: nokogiri
|
67
|
+
requirement: !ruby/object:Gem::Requirement
|
68
|
+
none: false
|
69
|
+
requirements:
|
70
|
+
- - ! '>='
|
71
|
+
- !ruby/object:Gem::Version
|
72
|
+
version: 1.4.2
|
73
|
+
type: :runtime
|
74
|
+
prerelease: false
|
75
|
+
version_requirements: !ruby/object:Gem::Requirement
|
76
|
+
none: false
|
77
|
+
requirements:
|
78
|
+
- - ! '>='
|
79
|
+
- !ruby/object:Gem::Version
|
80
|
+
version: 1.4.2
|
81
|
+
- !ruby/object:Gem::Dependency
|
82
|
+
name: guess_html_encoding
|
83
|
+
requirement: !ruby/object:Gem::Requirement
|
84
|
+
none: false
|
85
|
+
requirements:
|
86
|
+
- - ! '>='
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: 0.0.4
|
89
|
+
type: :runtime
|
90
|
+
prerelease: false
|
91
|
+
version_requirements: !ruby/object:Gem::Requirement
|
92
|
+
none: false
|
93
|
+
requirements:
|
94
|
+
- - ! '>='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: 0.0.4
|
97
|
+
description: Port of arc90's readability project to ruby
|
98
|
+
email:
|
99
|
+
- andrew@iterationlabs.com
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- lib/jruby-readability.rb
|
105
|
+
- lib/readability.rb
|
106
|
+
homepage: http://github.com/iterationlabs/ruby-readability
|
107
|
+
licenses: []
|
108
|
+
post_install_message:
|
109
|
+
rdoc_options: []
|
110
|
+
require_paths:
|
111
|
+
- lib
|
112
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
113
|
+
none: false
|
114
|
+
requirements:
|
115
|
+
- - ! '>='
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
119
|
+
none: false
|
120
|
+
requirements:
|
121
|
+
- - ! '>='
|
122
|
+
- !ruby/object:Gem::Version
|
123
|
+
version: '0'
|
124
|
+
requirements: []
|
125
|
+
rubyforge_project: ruby-readability
|
126
|
+
rubygems_version: 1.8.24
|
127
|
+
signing_key:
|
128
|
+
specification_version: 3
|
129
|
+
summary: Port of arc90's readability project to ruby
|
130
|
+
test_files: []
|