autopagerize 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +65 -0
- data/Rakefile +1 -0
- data/autopagerize.gemspec +24 -0
- data/lib/autopagerize.rb +113 -0
- data/lib/autopagerize/version.rb +3 -0
- data/spec/autopagerize_spec.rb +56 -0
- data/spec/spec_helper.rb +14 -0
- metadata +138 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 uu59
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,65 @@
|
|
1
|
+
# Autopagerize gem
|
2
|
+
|
3
|
+
Autopagerize gem works as such extensions:
|
4
|
+
|
5
|
+
- [AutoPager Chrome](https://chrome.google.com/webstore/detail/autopager-chrome/mmgagnmbebdebebbcleklifnobamjonh?hl=ja)
|
6
|
+
- [AutoPagerize](https://chrome.google.com/webstore/detail/autopagerize/igiofjhpmpihnifddepnpngfjhkfenbp)
|
7
|
+
- [AutoPatchWork](https://chrome.google.com/webstore/detail/autopatchwork/aeolcjbaammbkgaiagooljfdepnjmkfd?hl=ja)
|
8
|
+
|
9
|
+
## Usage
|
10
|
+
|
11
|
+
You must download SITEINFO from <http://wedata.net/databases/AutoPagerize/items_all.json>
|
12
|
+
|
13
|
+
$ curl http://wedata.net/databases/AutoPagerize/items_all.json > siteinfo.json
|
14
|
+
|
15
|
+
require "rubygems"
|
16
|
+
require "multi_json"
|
17
|
+
require "autopagerize"
|
18
|
+
|
19
|
+
siteinfo = MultiJson.load(File.read("siteinfo.json"))
|
20
|
+
url = "http://www.google.com/search?q=test"
|
21
|
+
page = Autopagerize.new(url, siteinfo)
|
22
|
+
puts page.processed_html
|
23
|
+
|
24
|
+
## Advance Usage
|
25
|
+
|
26
|
+
require "rubygems"
|
27
|
+
require "multi_json"
|
28
|
+
require "autopagerize"
|
29
|
+
|
30
|
+
siteinfo = MultiJson.load(File.read("siteinfo.json"))
|
31
|
+
url = "http://apod.nasa.gov/apod/ap090903.html"
|
32
|
+
apod = Autopagerize.new(url, siteinfo, {
|
33
|
+
:maxpage => 30,
|
34
|
+
:headers => {
|
35
|
+
"User-Agent" => "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)",
|
36
|
+
},
|
37
|
+
})
|
38
|
+
apod.each do |page|
|
39
|
+
img = page.page_element.at_xpath('//a/img/..')
|
40
|
+
next unless img
|
41
|
+
puts URI.join(url, img.attributes["href"].to_s).to_s
|
42
|
+
end
|
43
|
+
|
44
|
+
## Installation
|
45
|
+
|
46
|
+
Add this line to your application's Gemfile:
|
47
|
+
|
48
|
+
gem 'autopagerize'
|
49
|
+
|
50
|
+
And then execute:
|
51
|
+
|
52
|
+
$ bundle
|
53
|
+
|
54
|
+
Or install it yourself as:
|
55
|
+
|
56
|
+
$ gem install autopagerize
|
57
|
+
|
58
|
+
|
59
|
+
## Contributing
|
60
|
+
|
61
|
+
1. Fork it
|
62
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
63
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
64
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
65
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'autopagerize/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "autopagerize"
|
8
|
+
gem.version = Autopagerize::VERSION
|
9
|
+
gem.authors = ["uu59"]
|
10
|
+
gem.email = ["k@uu59.org"]
|
11
|
+
gem.description = %q{Concat paginated web pages to single page}
|
12
|
+
gem.summary = %q{Concat paginated web pages to single page}
|
13
|
+
gem.homepage = ""
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
gem.add_dependency "addressable"
|
20
|
+
gem.add_dependency "httpclient"
|
21
|
+
gem.add_dependency "nokogiri"
|
22
|
+
gem.add_development_dependency "rspec"
|
23
|
+
gem.add_development_dependency "multi_json"
|
24
|
+
end
|
data/lib/autopagerize.rb
ADDED
@@ -0,0 +1,113 @@
|
|
1
|
+
#require "autopagerize/version"
|
2
|
+
require "addressable/uri"
|
3
|
+
require "nokogiri"
|
4
|
+
require "httpclient"
|
5
|
+
|
6
|
+
class Autopagerize
|
7
|
+
include Enumerable
|
8
|
+
|
9
|
+
attr_reader :url, :client, :siteinfo, :options
|
10
|
+
|
11
|
+
def initialize(url, siteinfo, options = {})
|
12
|
+
@url = url
|
13
|
+
@siteinfo = siteinfo
|
14
|
+
|
15
|
+
@options = {
|
16
|
+
:maxpage => 10,
|
17
|
+
:headers => {},
|
18
|
+
|
19
|
+
# for internal/test use
|
20
|
+
:current_page => 1,
|
21
|
+
:httpclient => nil,
|
22
|
+
:site => nil,
|
23
|
+
}.merge(options)
|
24
|
+
|
25
|
+
@site = @options[:site]
|
26
|
+
end
|
27
|
+
|
28
|
+
def nextlink
|
29
|
+
return nil unless site
|
30
|
+
node = document.at_xpath(site["data"]["nextLink"])
|
31
|
+
return nil unless node
|
32
|
+
Addressable::URI.join(url, node.attributes["href"].to_s).to_s
|
33
|
+
end
|
34
|
+
|
35
|
+
def next
|
36
|
+
return nil if options[:maxpage] <= options[:current_page]
|
37
|
+
return nil if nextlink.nil?
|
38
|
+
@next ||= Autopagerize.new(nextlink, siteinfo, options.merge(:current_page => options[:current_page] + 1, :site => site))
|
39
|
+
end
|
40
|
+
|
41
|
+
def each
|
42
|
+
current = self
|
43
|
+
yield current
|
44
|
+
while current = current.next
|
45
|
+
yield current
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
def processed_document
|
50
|
+
@processed_document ||= begin
|
51
|
+
result = document.dup
|
52
|
+
|
53
|
+
# Insert rule:
|
54
|
+
# https://autopagerize.jottit.com/details_of_siteinfo_(ja)
|
55
|
+
before = site["data"]["insertBefore"]
|
56
|
+
if before.nil? || before.length == 0 || result.at_xpath(before).nil?
|
57
|
+
page = result.xpath(site["data"]["pageElement"]).last
|
58
|
+
point = Nokogiri::XML::Node.new("dummy_for_autopagerize", result.document)
|
59
|
+
page.after point
|
60
|
+
else
|
61
|
+
point = result.at_xpath(before)
|
62
|
+
end
|
63
|
+
|
64
|
+
@processed_page_elements = [self.page]
|
65
|
+
current = self
|
66
|
+
while current = current.next
|
67
|
+
point.before(current.page)
|
68
|
+
@processed_page_elements << current.page
|
69
|
+
end
|
70
|
+
point.remove
|
71
|
+
result
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
def processed_page_elements
|
76
|
+
processed_document
|
77
|
+
@processed_page_elements
|
78
|
+
end
|
79
|
+
|
80
|
+
def processed_html
|
81
|
+
processed_document.to_xml
|
82
|
+
end
|
83
|
+
|
84
|
+
def site
|
85
|
+
@site ||= siteinfo.find do |site|
|
86
|
+
/#{normalize_regex(site["data"]["url"])}/.match(url) && site["data"]["nextLink"] && document.at_xpath(site["data"]["nextLink"])
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
def client
|
91
|
+
options[:httpclient] ||= HTTPClient.new
|
92
|
+
end
|
93
|
+
|
94
|
+
def html
|
95
|
+
@html ||= client.get_content(url, nil, options[:headers])
|
96
|
+
end
|
97
|
+
|
98
|
+
def document
|
99
|
+
@document ||= Nokogiri::HTML.parse(html)
|
100
|
+
end
|
101
|
+
|
102
|
+
def page
|
103
|
+
document.xpath(site["data"]["pageElement"]).last
|
104
|
+
end
|
105
|
+
alias :page_element :page
|
106
|
+
|
107
|
+
private
|
108
|
+
def normalize_regex(re)
|
109
|
+
# to be quiet
|
110
|
+
# warning: nested repeat operator + and ? was replaced with '*': /^http:\/\/1stpower\.web\.fc2\.com\/comic(?:\d+)?/
|
111
|
+
re.gsub("+)?", "*)")
|
112
|
+
end
|
113
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
# -- coding: utf-8
|
2
|
+
|
3
|
+
require "spec_helper"
|
4
|
+
|
5
|
+
describe Autopagerize do
|
6
|
+
let(:siteinfo) do
|
7
|
+
json = MultiJson.dump [
|
8
|
+
{
|
9
|
+
:data => {
|
10
|
+
:url => "^http://foo/",
|
11
|
+
:nextLink => "nomatch",
|
12
|
+
},
|
13
|
+
},
|
14
|
+
{
|
15
|
+
:data => {
|
16
|
+
:url => "^http://bar/",
|
17
|
+
:pageElement => "//page",
|
18
|
+
:nextLink => "//a",
|
19
|
+
}
|
20
|
+
},
|
21
|
+
{
|
22
|
+
:data => {
|
23
|
+
:url => "^http://baz/",
|
24
|
+
:pageElement => "//foobar",
|
25
|
+
:nextLink => "//a",
|
26
|
+
}
|
27
|
+
},
|
28
|
+
]
|
29
|
+
MultiJson.load(json)
|
30
|
+
end
|
31
|
+
|
32
|
+
it "should autopagerize" do
|
33
|
+
first = <<-HTML
|
34
|
+
<!doctype html>
|
35
|
+
<page>first page</page>
|
36
|
+
<a href="next.html">next link</a>
|
37
|
+
HTML
|
38
|
+
|
39
|
+
second = <<-HTML
|
40
|
+
<!doctype html>
|
41
|
+
<page>next.html</page>
|
42
|
+
<a href="morenext.html">go to final page</a>
|
43
|
+
HTML
|
44
|
+
|
45
|
+
third = <<-HTML
|
46
|
+
<!doctype html>
|
47
|
+
<page>final page</page>
|
48
|
+
HTML
|
49
|
+
|
50
|
+
client = HTTPClient.new
|
51
|
+
client.test_loopback_response << first << second << third
|
52
|
+
a = Autopagerize.new("http://bar/", siteinfo, :httpclient => client)
|
53
|
+
a.nextlink.should == "http://bar/next.html"
|
54
|
+
a.to_enum.to_a.length.should == 3
|
55
|
+
end
|
56
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
# -- coding: utf-8
|
2
|
+
|
3
|
+
require "rubygems"
|
4
|
+
require "bundler/setup"
|
5
|
+
Bundler.require :default, :test, :development
|
6
|
+
require "rspec-expectations"
|
7
|
+
require "rspec/matchers/built_in/be"
|
8
|
+
|
9
|
+
Dir["./spec/support/**/*.rb"].each{|file| require file }
|
10
|
+
|
11
|
+
require File.expand_path("../../lib/autopagerize.rb", __FILE__)
|
12
|
+
|
13
|
+
RSpec.configure do |config|
|
14
|
+
end
|
metadata
ADDED
@@ -0,0 +1,138 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: autopagerize
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- uu59
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-11-11 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: addressable
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: '0'
|
22
|
+
type: :runtime
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: '0'
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: httpclient
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: '0'
|
38
|
+
type: :runtime
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: '0'
|
46
|
+
- !ruby/object:Gem::Dependency
|
47
|
+
name: nokogiri
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ! '>='
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '0'
|
54
|
+
type: :runtime
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ! '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: rspec
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
none: false
|
66
|
+
requirements:
|
67
|
+
- - ! '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
type: :development
|
71
|
+
prerelease: false
|
72
|
+
version_requirements: !ruby/object:Gem::Requirement
|
73
|
+
none: false
|
74
|
+
requirements:
|
75
|
+
- - ! '>='
|
76
|
+
- !ruby/object:Gem::Version
|
77
|
+
version: '0'
|
78
|
+
- !ruby/object:Gem::Dependency
|
79
|
+
name: multi_json
|
80
|
+
requirement: !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ! '>='
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '0'
|
86
|
+
type: :development
|
87
|
+
prerelease: false
|
88
|
+
version_requirements: !ruby/object:Gem::Requirement
|
89
|
+
none: false
|
90
|
+
requirements:
|
91
|
+
- - ! '>='
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '0'
|
94
|
+
description: Concat paginated web pages to single page
|
95
|
+
email:
|
96
|
+
- k@uu59.org
|
97
|
+
executables: []
|
98
|
+
extensions: []
|
99
|
+
extra_rdoc_files: []
|
100
|
+
files:
|
101
|
+
- .gitignore
|
102
|
+
- Gemfile
|
103
|
+
- LICENSE.txt
|
104
|
+
- README.md
|
105
|
+
- Rakefile
|
106
|
+
- autopagerize.gemspec
|
107
|
+
- lib/autopagerize.rb
|
108
|
+
- lib/autopagerize/version.rb
|
109
|
+
- spec/autopagerize_spec.rb
|
110
|
+
- spec/spec_helper.rb
|
111
|
+
homepage: ''
|
112
|
+
licenses: []
|
113
|
+
post_install_message:
|
114
|
+
rdoc_options: []
|
115
|
+
require_paths:
|
116
|
+
- lib
|
117
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
118
|
+
none: false
|
119
|
+
requirements:
|
120
|
+
- - ! '>='
|
121
|
+
- !ruby/object:Gem::Version
|
122
|
+
version: '0'
|
123
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
124
|
+
none: false
|
125
|
+
requirements:
|
126
|
+
- - ! '>='
|
127
|
+
- !ruby/object:Gem::Version
|
128
|
+
version: '0'
|
129
|
+
requirements: []
|
130
|
+
rubyforge_project:
|
131
|
+
rubygems_version: 1.8.23
|
132
|
+
signing_key:
|
133
|
+
specification_version: 3
|
134
|
+
summary: Concat paginated web pages to single page
|
135
|
+
test_files:
|
136
|
+
- spec/autopagerize_spec.rb
|
137
|
+
- spec/spec_helper.rb
|
138
|
+
has_rdoc:
|