pismo 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +32 -0
- data/README.rdoc +68 -0
- data/Rakefile +95 -0
- data/VERSION +1 -0
- data/bin/pismo +36 -0
- data/lib/pismo/document.rb +50 -0
- data/lib/pismo/external_attributes.rb +14 -0
- data/lib/pismo/internal_attributes.rb +202 -0
- data/lib/pismo/readability.rb +316 -0
- data/lib/pismo/stopwords.txt +893 -0
- data/lib/pismo.rb +44 -0
- data/pismo.gemspec +92 -0
- data/test/corpus/bbcnews.html +2131 -0
- data/test/corpus/briancray.html +269 -0
- data/test/corpus/cant_read.html +426 -0
- data/test/corpus/factor.html +1362 -0
- data/test/corpus/huffington.html +2932 -0
- data/test/corpus/metadata_expected.yaml +81 -0
- data/test/corpus/rubyinside.html +318 -0
- data/test/corpus/rww.html +1351 -0
- data/test/corpus/spolsky.html +298 -0
- data/test/corpus/techcrunch.html +1285 -0
- data/test/corpus/youtube.html +2348 -0
- data/test/helper.rb +15 -0
- data/test/test_corpus.rb +33 -0
- data/test/test_pismo_document.rb +34 -0
- data/test/test_readability.rb +152 -0
- metadata +146 -0
data/lib/pismo.rb
ADDED
@@ -0,0 +1,44 @@
|
|
1
|
+
require 'open-uri'
|
2
|
+
require 'nokogiri'
|
3
|
+
require 'fast_stemmer'
|
4
|
+
require 'chronic'
|
5
|
+
|
6
|
+
$: << File.dirname(__FILE__)
|
7
|
+
require 'pismo/document'
|
8
|
+
require 'pismo/readability'
|
9
|
+
|
10
|
+
module Pismo
|
11
|
+
# Sugar method to make creating document objects nicer
|
12
|
+
def self.document(handle, url = nil)
|
13
|
+
Document.new(handle, url)
|
14
|
+
end
|
15
|
+
|
16
|
+
class NFunctions
|
17
|
+
def self.match_href(list, expression)
|
18
|
+
list.find_all { |node| node['href'] =~ /#{expression}/ }
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
# Add some sugar to Nokogiri
|
24
|
+
class Nokogiri::HTML::Document
|
25
|
+
def get_the(search)
|
26
|
+
self.search(search).first rescue nil
|
27
|
+
end
|
28
|
+
|
29
|
+
def match(*queries)
|
30
|
+
queries.each do |query|
|
31
|
+
if query.is_a?(String)
|
32
|
+
result = self.search(query).first.inner_text.strip rescue nil
|
33
|
+
elsif query.is_a?(Array)
|
34
|
+
result = query[1].call(self.search(query.first).first).strip rescue nil
|
35
|
+
end
|
36
|
+
if result
|
37
|
+
result.gsub!(/\342\200\231/, '\'')
|
38
|
+
result.gsub!(/\342\200\224/, '-')
|
39
|
+
return result
|
40
|
+
end
|
41
|
+
end
|
42
|
+
return nil
|
43
|
+
end
|
44
|
+
end
|
data/pismo.gemspec
ADDED
@@ -0,0 +1,92 @@
|
|
1
|
+
# Generated by jeweler
|
2
|
+
# DO NOT EDIT THIS FILE DIRECTLY
|
3
|
+
# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
|
4
|
+
# -*- encoding: utf-8 -*-
|
5
|
+
|
6
|
+
Gem::Specification.new do |s|
|
7
|
+
s.name = %q{pismo}
|
8
|
+
s.version = "0.2.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Peter Cooper"]
|
12
|
+
s.date = %q{2010-03-26}
|
13
|
+
s.default_executable = %q{pismo}
|
14
|
+
s.description = %q{Pismo extracts and retrieves content-related metadata from HTML pages - you can use the resulting data in an organized way, such as a summary/first paragraph, del.icio.us tags, first image used in the content block, etc.}
|
15
|
+
s.email = %q{git@peterc.org}
|
16
|
+
s.executables = ["pismo"]
|
17
|
+
s.extra_rdoc_files = [
|
18
|
+
"LICENSE",
|
19
|
+
"README.rdoc"
|
20
|
+
]
|
21
|
+
s.files = [
|
22
|
+
".document",
|
23
|
+
".gitignore",
|
24
|
+
"LICENSE",
|
25
|
+
"README.rdoc",
|
26
|
+
"Rakefile",
|
27
|
+
"VERSION",
|
28
|
+
"bin/pismo",
|
29
|
+
"lib/pismo.rb",
|
30
|
+
"lib/pismo/document.rb",
|
31
|
+
"lib/pismo/external_attributes.rb",
|
32
|
+
"lib/pismo/internal_attributes.rb",
|
33
|
+
"lib/pismo/readability.rb",
|
34
|
+
"lib/pismo/stopwords.txt",
|
35
|
+
"pismo.gemspec",
|
36
|
+
"test/corpus/bbcnews.html",
|
37
|
+
"test/corpus/briancray.html",
|
38
|
+
"test/corpus/cant_read.html",
|
39
|
+
"test/corpus/factor.html",
|
40
|
+
"test/corpus/huffington.html",
|
41
|
+
"test/corpus/metadata_expected.yaml",
|
42
|
+
"test/corpus/rubyinside.html",
|
43
|
+
"test/corpus/rww.html",
|
44
|
+
"test/corpus/spolsky.html",
|
45
|
+
"test/corpus/techcrunch.html",
|
46
|
+
"test/corpus/youtube.html",
|
47
|
+
"test/helper.rb",
|
48
|
+
"test/test_corpus.rb",
|
49
|
+
"test/test_pismo_document.rb",
|
50
|
+
"test/test_readability.rb"
|
51
|
+
]
|
52
|
+
s.homepage = %q{http://github.com/peterc/pismo}
|
53
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
54
|
+
s.require_paths = ["lib"]
|
55
|
+
s.rubygems_version = %q{1.3.5}
|
56
|
+
s.summary = %q{Extracts or retrieves content-related metadata from HTML pages}
|
57
|
+
s.test_files = [
|
58
|
+
"test/helper.rb",
|
59
|
+
"test/test_corpus.rb",
|
60
|
+
"test/test_pismo_document.rb",
|
61
|
+
"test/test_readability.rb"
|
62
|
+
]
|
63
|
+
|
64
|
+
if s.respond_to? :specification_version then
|
65
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
66
|
+
s.specification_version = 3
|
67
|
+
|
68
|
+
if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
|
69
|
+
s.add_development_dependency(%q<shoulda>, [">= 0"])
|
70
|
+
s.add_runtime_dependency(%q<nokogiri>, [">= 0"])
|
71
|
+
s.add_runtime_dependency(%q<loofah>, [">= 0"])
|
72
|
+
s.add_runtime_dependency(%q<httparty>, [">= 0"])
|
73
|
+
s.add_runtime_dependency(%q<fast-stemmer>, [">= 0"])
|
74
|
+
s.add_runtime_dependency(%q<chronic>, [">= 0"])
|
75
|
+
else
|
76
|
+
s.add_dependency(%q<shoulda>, [">= 0"])
|
77
|
+
s.add_dependency(%q<nokogiri>, [">= 0"])
|
78
|
+
s.add_dependency(%q<loofah>, [">= 0"])
|
79
|
+
s.add_dependency(%q<httparty>, [">= 0"])
|
80
|
+
s.add_dependency(%q<fast-stemmer>, [">= 0"])
|
81
|
+
s.add_dependency(%q<chronic>, [">= 0"])
|
82
|
+
end
|
83
|
+
else
|
84
|
+
s.add_dependency(%q<shoulda>, [">= 0"])
|
85
|
+
s.add_dependency(%q<nokogiri>, [">= 0"])
|
86
|
+
s.add_dependency(%q<loofah>, [">= 0"])
|
87
|
+
s.add_dependency(%q<httparty>, [">= 0"])
|
88
|
+
s.add_dependency(%q<fast-stemmer>, [">= 0"])
|
89
|
+
s.add_dependency(%q<chronic>, [">= 0"])
|
90
|
+
end
|
91
|
+
end
|
92
|
+
|