html_page_title 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.rdoc +40 -0
- data/Rakefile +55 -0
- data/VERSION +1 -0
- data/html_page_title.gemspec +60 -0
- data/lib/html_page_title.rb +78 -0
- data/test/helper.rb +10 -0
- data/test/test_html_page_title.rb +63 -0
- metadata +125 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2010 Christoph Olszowka
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,40 @@
|
|
1
|
+
= HtmlPageTitle
|
2
|
+
|
3
|
+
gem install html_page_title
|
4
|
+
|
5
|
+
A simple class for finding the title of a given http url by fetching the
|
6
|
+
given url, following all eventual redirects and finally parsing it through
|
7
|
+
hpricot.
|
8
|
+
|
9
|
+
You can either use the shorthand form or initialize the instance properly:
|
10
|
+
* HtmlPageTitle('http://github.com')
|
11
|
+
* HtmlPageTitle.new('http://github.com')
|
12
|
+
|
13
|
+
Those calls are equivalent, except for one subtle difference:
|
14
|
+
The shorthand form will swallow SocketErrors and return nil (i.e. this will
|
15
|
+
happen for invalid urls), while the regular instantiation via new will
|
16
|
+
throw that error.
|
17
|
+
|
18
|
+
You can either get the title, the heading (which will be the content of the
|
19
|
+
first h1 tag in the body) or the label, which will be (in the following order
|
20
|
+
by availability) either the heading, or the title, or the target url after
|
21
|
+
redirecting.
|
22
|
+
Note that if the title or the heading can not be found (e.g. a non-HTML
|
23
|
+
document), both methods will return nil, so the label method is the only one
|
24
|
+
that will always return some kind of string
|
25
|
+
|
26
|
+
You can also have a look at the unit test to find out about the behaviour!
|
27
|
+
|
28
|
+
== Note on Patches/Pull Requests
|
29
|
+
|
30
|
+
* Fork the project.
|
31
|
+
* Make your feature addition or bug fix.
|
32
|
+
* Add tests for it. This is important so I don't break it in a
|
33
|
+
future version unintentionally.
|
34
|
+
* Commit, do not mess with rakefile, version, or history.
|
35
|
+
(if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
|
36
|
+
* Send me a pull request. Bonus points for topic branches.
|
37
|
+
|
38
|
+
== Copyright
|
39
|
+
|
40
|
+
Copyright (c) 2010 Christoph Olszowka. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,55 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "html_page_title"
|
8
|
+
gem.summary = %Q{Retrieve the page title for a given url (including redirects)}
|
9
|
+
gem.description = %Q{Retrieve the page title for a given url using redirect_follower and hpricot ruby gems}
|
10
|
+
gem.email = "'christoph at olszowka.de'"
|
11
|
+
gem.homepage = "http://github.com/colszowka/html_page_title"
|
12
|
+
gem.authors = ["Christoph Olszowka"]
|
13
|
+
gem.add_dependency "redirect_follower", ">= 0.1.1"
|
14
|
+
gem.add_dependency "hpricot", ">= 0.8.2"
|
15
|
+
gem.add_development_dependency "shoulda", ">= 2.11.1"
|
16
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
17
|
+
end
|
18
|
+
Jeweler::GemcutterTasks.new
|
19
|
+
rescue LoadError
|
20
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
21
|
+
end
|
22
|
+
|
23
|
+
require 'rake/testtask'
|
24
|
+
Rake::TestTask.new(:test) do |test|
|
25
|
+
test.libs << 'lib' << 'test'
|
26
|
+
test.pattern = 'test/**/test_*.rb'
|
27
|
+
test.verbose = true
|
28
|
+
end
|
29
|
+
|
30
|
+
begin
|
31
|
+
require 'rcov/rcovtask'
|
32
|
+
Rcov::RcovTask.new do |test|
|
33
|
+
test.libs << 'test'
|
34
|
+
test.pattern = 'test/**/test_*.rb'
|
35
|
+
test.verbose = true
|
36
|
+
end
|
37
|
+
rescue LoadError
|
38
|
+
task :rcov do
|
39
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
task :test => :check_dependencies
|
44
|
+
|
45
|
+
task :default => :test
|
46
|
+
|
47
|
+
require 'rake/rdoctask'
|
48
|
+
Rake::RDocTask.new do |rdoc|
|
49
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
50
|
+
|
51
|
+
rdoc.rdoc_dir = 'rdoc'
|
52
|
+
rdoc.title = "html_page_title #{version}"
|
53
|
+
rdoc.rdoc_files.include('README*')
|
54
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
55
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
@@ -0,0 +1,60 @@
|
|
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{html_page_title}
|
8
|
+
s.version = "0.1.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Christoph Olszowka"]
|
12
|
+
s.date = %q{2010-07-15}
|
13
|
+
s.description = %q{Retrieve the page title for a given url using redirect_follower and hpricot ruby gems}
|
14
|
+
s.email = %q{'christoph at olszowka.de'}
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE",
|
17
|
+
"README.rdoc"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
".document",
|
21
|
+
".gitignore",
|
22
|
+
"LICENSE",
|
23
|
+
"README.rdoc",
|
24
|
+
"Rakefile",
|
25
|
+
"VERSION",
|
26
|
+
"html_page_title.gemspec",
|
27
|
+
"lib/html_page_title.rb",
|
28
|
+
"test/helper.rb",
|
29
|
+
"test/test_html_page_title.rb"
|
30
|
+
]
|
31
|
+
s.homepage = %q{http://github.com/colszowka/html_page_title}
|
32
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
33
|
+
s.require_paths = ["lib"]
|
34
|
+
s.rubygems_version = %q{1.3.7}
|
35
|
+
s.summary = %q{Retrieve the page title for a given url (including redirects)}
|
36
|
+
s.test_files = [
|
37
|
+
"test/helper.rb",
|
38
|
+
"test/test_html_page_title.rb"
|
39
|
+
]
|
40
|
+
|
41
|
+
if s.respond_to? :specification_version then
|
42
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
43
|
+
s.specification_version = 3
|
44
|
+
|
45
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
46
|
+
s.add_runtime_dependency(%q<redirect_follower>, [">= 0.1.1"])
|
47
|
+
s.add_runtime_dependency(%q<hpricot>, [">= 0.8.2"])
|
48
|
+
s.add_development_dependency(%q<shoulda>, [">= 2.11.1"])
|
49
|
+
else
|
50
|
+
s.add_dependency(%q<redirect_follower>, [">= 0.1.1"])
|
51
|
+
s.add_dependency(%q<hpricot>, [">= 0.8.2"])
|
52
|
+
s.add_dependency(%q<shoulda>, [">= 2.11.1"])
|
53
|
+
end
|
54
|
+
else
|
55
|
+
s.add_dependency(%q<redirect_follower>, [">= 0.1.1"])
|
56
|
+
s.add_dependency(%q<hpricot>, [">= 0.8.2"])
|
57
|
+
s.add_dependency(%q<shoulda>, [">= 2.11.1"])
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
@@ -0,0 +1,78 @@
|
|
1
|
+
require 'redirect_follower'
|
2
|
+
require 'hpricot'
|
3
|
+
def HtmlPageTitle(url)
|
4
|
+
HtmlPageTitle.new(url)
|
5
|
+
rescue SocketError => err
|
6
|
+
nil
|
7
|
+
end
|
8
|
+
|
9
|
+
#
|
10
|
+
# A simple class for finding the title of a given http url by fetching the
|
11
|
+
# given url, following all eventual redirects and finally parsing it through
|
12
|
+
# hpricot.
|
13
|
+
#
|
14
|
+
# You can either use the shorthand form or initialize the instance properly:
|
15
|
+
# * HtmlPageTitle('http://github.com')
|
16
|
+
# * HtmlPageTitle.new('http://github.com')
|
17
|
+
#
|
18
|
+
# Those calls are equivalent, except for one subtle difference:
|
19
|
+
# The shorthand form will swallow SocketErrors and return nil (i.e. this will
|
20
|
+
# happen for invalid urls), while the regular instantiation via new will
|
21
|
+
# throw that error.
|
22
|
+
#
|
23
|
+
# You can either get the title, the heading (which will be the content of the
|
24
|
+
# first h1 tag in the body) or the label, which will be (in the following order
|
25
|
+
# by availability) either the heading, or the title, or the target url after
|
26
|
+
# redirecting.
|
27
|
+
# Note that if the title or the heading can not be found (e.g. a non-HTML
|
28
|
+
# document), both methods will return nil, so the label method is the only one
|
29
|
+
# that will always return some kind of string
|
30
|
+
#
|
31
|
+
class HtmlPageTitle
|
32
|
+
attr_reader :original_url
|
33
|
+
def initialize(original_url)
|
34
|
+
@original_url = original_url
|
35
|
+
title # retrieve data so exceptions can be thrown
|
36
|
+
end
|
37
|
+
|
38
|
+
def document
|
39
|
+
@document ||= Hpricot(redirect.body)
|
40
|
+
end
|
41
|
+
|
42
|
+
def title
|
43
|
+
return @title if @title
|
44
|
+
if title_tag = document.at('head title')
|
45
|
+
@title = title_tag.inner_html.strip.chomp
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
# Retrieves the first h1 tag in the page and returns it's content
|
50
|
+
def heading
|
51
|
+
return @heading if @heading
|
52
|
+
if heading_tag = document.at('body h1')
|
53
|
+
@heading = heading_tag.inner_html.strip.chomp
|
54
|
+
end
|
55
|
+
end
|
56
|
+
|
57
|
+
# Returns either the heading, or the title, or the url in this order
|
58
|
+
# by availability
|
59
|
+
def label
|
60
|
+
heading or title or url
|
61
|
+
end
|
62
|
+
|
63
|
+
# Returns the redirect follower instance used for resolving
|
64
|
+
# this instances url
|
65
|
+
def redirect
|
66
|
+
@redirect = RedirectFollower.new(original_url)
|
67
|
+
end
|
68
|
+
|
69
|
+
# Returns the target url after all redirects
|
70
|
+
def url
|
71
|
+
redirect.url
|
72
|
+
end
|
73
|
+
|
74
|
+
# Returns the body of the document at the (redirected?) target
|
75
|
+
def body
|
76
|
+
redirect.body
|
77
|
+
end
|
78
|
+
end
|
data/test/helper.rb
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
class TestHtmlPageTitle < Test::Unit::TestCase
|
4
|
+
def test_quick_access
|
5
|
+
instance = HtmlPageTitle('http://www.spiegel.de')
|
6
|
+
assert_equal "SPIEGEL ONLINE - Nachrichten", instance.title
|
7
|
+
assert_equal 'http://www.spiegel.de', instance.url
|
8
|
+
assert_equal 'SPIEGEL ONLINE', instance.heading
|
9
|
+
assert_equal instance.heading, instance.label
|
10
|
+
end
|
11
|
+
|
12
|
+
def test_access_with_instantiation
|
13
|
+
instance = HtmlPageTitle.new('http://www.spiegel.de')
|
14
|
+
assert_equal "SPIEGEL ONLINE - Nachrichten", instance.title
|
15
|
+
assert_equal 'http://www.spiegel.de', instance.url
|
16
|
+
assert_equal 'SPIEGEL ONLINE', instance.heading
|
17
|
+
assert_equal instance.heading, instance.label
|
18
|
+
|
19
|
+
assert instance.body.kind_of?(String)
|
20
|
+
assert_equal instance.redirect.url, instance.url
|
21
|
+
assert_equal RedirectFollower, instance.redirect.class
|
22
|
+
assert_equal Hpricot::Doc, instance.document.class
|
23
|
+
end
|
24
|
+
|
25
|
+
def test_with_redirect
|
26
|
+
instance = HtmlPageTitle.new('http://is.gd/bNZYZ')
|
27
|
+
assert_equal "TASCHEN Books: Byrne, Six Books of Euclid", instance.title
|
28
|
+
assert_equal 'http://www.taschen.com/pages/en/catalogue/classics/all/06724/facts.byrne_six_books_of_euclid.htm', instance.url
|
29
|
+
assert_equal 'Byrne, Six Books of Euclid', instance.heading
|
30
|
+
assert_equal instance.heading, instance.label
|
31
|
+
|
32
|
+
assert instance.body.kind_of?(String)
|
33
|
+
assert_equal instance.redirect.url, instance.url
|
34
|
+
assert_equal RedirectFollower, instance.redirect.class
|
35
|
+
assert_equal Hpricot::Doc, instance.document.class
|
36
|
+
end
|
37
|
+
|
38
|
+
def test_quick_access_with_invalid_urls
|
39
|
+
assert_nil HtmlPageTitle('http://www.thisdoesnotexistforrealsure.de')
|
40
|
+
assert_nil HtmlPageTitle('http://www.notldisntniceeh')
|
41
|
+
end
|
42
|
+
|
43
|
+
def test_regular_access_with_invalid_urls
|
44
|
+
assert_raise SocketError do
|
45
|
+
HtmlPageTitle.new('http://www.thisdoesnotexistforsure.de')
|
46
|
+
end
|
47
|
+
assert_raise SocketError do
|
48
|
+
HtmlPageTitle.new('http://www.thisdoesnotexistforsur')
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
def test_non_html_url
|
53
|
+
instance = HtmlPageTitle.new('http://gist.github.com/raw/93965/64e0b8445d0c3481f755fe65fd79297fcf6da909/x')
|
54
|
+
assert_nil instance.title
|
55
|
+
assert_nil instance.heading
|
56
|
+
assert_equal 'http://gist.github.com/raw/93965/64e0b8445d0c3481f755fe65fd79297fcf6da909/x', instance.label
|
57
|
+
end
|
58
|
+
|
59
|
+
def test_url_without_h1
|
60
|
+
instance = HtmlPageTitle('http://gembundler.com/v1.0/index.html')
|
61
|
+
assert_equal instance.title, instance.label
|
62
|
+
end
|
63
|
+
end
|
metadata
ADDED
@@ -0,0 +1,125 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: html_page_title
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 27
|
5
|
+
prerelease: false
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
- 0
|
10
|
+
version: 0.1.0
|
11
|
+
platform: ruby
|
12
|
+
authors:
|
13
|
+
- Christoph Olszowka
|
14
|
+
autorequire:
|
15
|
+
bindir: bin
|
16
|
+
cert_chain: []
|
17
|
+
|
18
|
+
date: 2010-07-15 00:00:00 +02:00
|
19
|
+
default_executable:
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
name: redirect_follower
|
23
|
+
prerelease: false
|
24
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 25
|
30
|
+
segments:
|
31
|
+
- 0
|
32
|
+
- 1
|
33
|
+
- 1
|
34
|
+
version: 0.1.1
|
35
|
+
type: :runtime
|
36
|
+
version_requirements: *id001
|
37
|
+
- !ruby/object:Gem::Dependency
|
38
|
+
name: hpricot
|
39
|
+
prerelease: false
|
40
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ">="
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
hash: 59
|
46
|
+
segments:
|
47
|
+
- 0
|
48
|
+
- 8
|
49
|
+
- 2
|
50
|
+
version: 0.8.2
|
51
|
+
type: :runtime
|
52
|
+
version_requirements: *id002
|
53
|
+
- !ruby/object:Gem::Dependency
|
54
|
+
name: shoulda
|
55
|
+
prerelease: false
|
56
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
hash: 33
|
62
|
+
segments:
|
63
|
+
- 2
|
64
|
+
- 11
|
65
|
+
- 1
|
66
|
+
version: 2.11.1
|
67
|
+
type: :development
|
68
|
+
version_requirements: *id003
|
69
|
+
description: Retrieve the page title for a given url using redirect_follower and hpricot ruby gems
|
70
|
+
email: "'christoph at olszowka.de'"
|
71
|
+
executables: []
|
72
|
+
|
73
|
+
extensions: []
|
74
|
+
|
75
|
+
extra_rdoc_files:
|
76
|
+
- LICENSE
|
77
|
+
- README.rdoc
|
78
|
+
files:
|
79
|
+
- .document
|
80
|
+
- .gitignore
|
81
|
+
- LICENSE
|
82
|
+
- README.rdoc
|
83
|
+
- Rakefile
|
84
|
+
- VERSION
|
85
|
+
- html_page_title.gemspec
|
86
|
+
- lib/html_page_title.rb
|
87
|
+
- test/helper.rb
|
88
|
+
- test/test_html_page_title.rb
|
89
|
+
has_rdoc: true
|
90
|
+
homepage: http://github.com/colszowka/html_page_title
|
91
|
+
licenses: []
|
92
|
+
|
93
|
+
post_install_message:
|
94
|
+
rdoc_options:
|
95
|
+
- --charset=UTF-8
|
96
|
+
require_paths:
|
97
|
+
- lib
|
98
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
99
|
+
none: false
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
hash: 3
|
104
|
+
segments:
|
105
|
+
- 0
|
106
|
+
version: "0"
|
107
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
108
|
+
none: false
|
109
|
+
requirements:
|
110
|
+
- - ">="
|
111
|
+
- !ruby/object:Gem::Version
|
112
|
+
hash: 3
|
113
|
+
segments:
|
114
|
+
- 0
|
115
|
+
version: "0"
|
116
|
+
requirements: []
|
117
|
+
|
118
|
+
rubyforge_project:
|
119
|
+
rubygems_version: 1.3.7
|
120
|
+
signing_key:
|
121
|
+
specification_version: 3
|
122
|
+
summary: Retrieve the page title for a given url (including redirects)
|
123
|
+
test_files:
|
124
|
+
- test/helper.rb
|
125
|
+
- test/test_html_page_title.rb
|