myimdb 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE +20 -0
- data/README.rdoc +17 -0
- data/Rakefile +22 -0
- data/VERSION +1 -0
- data/bin/myimdb +34 -0
- data/bin/myimdb.bat +1 -0
- data/lib/myimdb.rb +7 -0
- data/lib/myimdb/scraper.rb +5 -0
- data/lib/myimdb/scraper/base.rb +45 -0
- data/lib/myimdb/scraper/imdb.rb +48 -0
- data/lib/myimdb/scraper/metacritic.rb +32 -0
- data/lib/myimdb/scraper/rotten_tomatoes.rb +32 -0
- data/lib/myimdb/scraper/string_extensions.rb +22 -0
- data/lib/myimdb/search.rb +2 -0
- data/lib/myimdb/search/google.rb +17 -0
- data/myimdb.gemspec +70 -0
- data/pkg/myimdb-0.0.0.gem +0 -0
- data/pkg/myimdb-0.1.0.gem +0 -0
- data/pkg/myimdb-0.2.0.gem +0 -0
- data/pkg/myimdb-0.3.0.gem +0 -0
- data/test/helper.rb +10 -0
- data/test/test_myimdb.rb +7 -0
- metadata +98 -0
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Gaurav Sharma
|
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 +1,17 @@
|
|
1
|
+
= myimdb
|
2
|
+
|
3
|
+
Utility gem for fetching movie details.
|
4
|
+
|
5
|
+
== Note on Patches/Pull Requests
|
6
|
+
|
7
|
+
* Fork the project.
|
8
|
+
* Make your feature addition or bug fix.
|
9
|
+
* Add tests for it. This is important so I don't break it in a
|
10
|
+
future version unintentionally.
|
11
|
+
* Commit, do not mess with rakefile, version, or history.
|
12
|
+
(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)
|
13
|
+
* Send me a pull request. Bonus points for topic branches.
|
14
|
+
|
15
|
+
== Copyright
|
16
|
+
|
17
|
+
Copyright (c) 2009 Gaurav Sharma. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "myimdb"
|
8
|
+
gem.summary = %Q{Utility gem for fetching movie details.}
|
9
|
+
gem.email = "gaurav@vinsol.com"
|
10
|
+
gem.homepage = "http://github.com/gauravs/myimdb"
|
11
|
+
gem.authors = ["Gaurav"]
|
12
|
+
gem.add_dependency 'httparty', '>= 0.4.5'
|
13
|
+
gem.add_dependency 'nokogiri', '>= 1.3.3'
|
14
|
+
gem.rubyforge_project = 'myimdb'
|
15
|
+
gem.files = FileList["**/*"]
|
16
|
+
end
|
17
|
+
Jeweler::RubyforgeTasks.new do |rubyforge|
|
18
|
+
rubyforge.doc_task = "rdoc"
|
19
|
+
end
|
20
|
+
rescue LoadError
|
21
|
+
puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
|
22
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.3.0
|
data/bin/myimdb
ADDED
@@ -0,0 +1,34 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# point this file to a folder and all the folder inside it will be renamed
|
4
|
+
require 'myimdb.rb'
|
5
|
+
|
6
|
+
unless ARGV[0]
|
7
|
+
p "Source directory required - exiting"
|
8
|
+
exit(0)
|
9
|
+
end
|
10
|
+
|
11
|
+
file_paths = Dir["#{ARGV[0]}/*"]
|
12
|
+
search_scope = "imdb.com"
|
13
|
+
|
14
|
+
file_paths.each do |path|
|
15
|
+
next if !File.directory?(path)
|
16
|
+
p "============================================"
|
17
|
+
name = File.basename(path)
|
18
|
+
if name.scan(/\[.*?\]/).size == 3
|
19
|
+
p "Skipping: #{name}"
|
20
|
+
else
|
21
|
+
p "Fetching details for: #{name}"
|
22
|
+
begin
|
23
|
+
search_result = Myimdb::Search::Google.search_text(name, search_scope)[0]
|
24
|
+
imdb = Myimdb::Scraper::Imdb.new(search_result["url"])
|
25
|
+
new_name = name.gsub(/\[\S+\]/, "").strip
|
26
|
+
new_name << " [#{imdb.year}] [#{imdb.rating},#{imdb.votes}] [#{imdb.directors.join(',')}]"
|
27
|
+
p "Renaming: #{name} to: #{new_name}"
|
28
|
+
new_path = File.join(File.dirname(path), new_name)
|
29
|
+
File.rename(path, new_path)
|
30
|
+
rescue
|
31
|
+
p "Unable to fetch details for: #{name}"
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
data/bin/myimdb.bat
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
@"ruby.exe" "%~dpn0" %*
|
data/lib/myimdb.rb
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
class UnformattedHtml < Exception; end
|
2
|
+
|
3
|
+
module HandleExceptions
|
4
|
+
def self.included(base)
|
5
|
+
base.send(:include, InstanceMethods)
|
6
|
+
base.send(:extend, ClassMethods)
|
7
|
+
end
|
8
|
+
|
9
|
+
module InstanceMethods
|
10
|
+
end
|
11
|
+
|
12
|
+
module ClassMethods
|
13
|
+
def handle_exceptions_for(*method_names)
|
14
|
+
method_names.each do |method_name|
|
15
|
+
alias_method("_#{method_name}", method_name)
|
16
|
+
define_method(method_name) do
|
17
|
+
begin
|
18
|
+
send("_#{method_name}")
|
19
|
+
rescue
|
20
|
+
raise UnformattedHtml.new("Unable to find tag: #{method_name}, probably you are parsing the wrong page.")
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
module Myimdb
|
29
|
+
module Scraper
|
30
|
+
class Base
|
31
|
+
include HandleExceptions
|
32
|
+
def year
|
33
|
+
end
|
34
|
+
|
35
|
+
def tagline
|
36
|
+
end
|
37
|
+
|
38
|
+
def directors
|
39
|
+
end
|
40
|
+
|
41
|
+
def writers
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
@@ -0,0 +1,48 @@
|
|
1
|
+
module Myimdb
|
2
|
+
module Scraper
|
3
|
+
class Imdb < Scraper::Base
|
4
|
+
def initialize(url)
|
5
|
+
@url = url
|
6
|
+
end
|
7
|
+
|
8
|
+
def directors
|
9
|
+
document.css('.info h5:contains("Director") + .info-content a:not(.tn15more)').collect{ |a| a.text }
|
10
|
+
end
|
11
|
+
|
12
|
+
def writers
|
13
|
+
document.css('.info h5:contains("Writer") + .info-content a:not(.tn15more)').collect{ |a| a.text }
|
14
|
+
end
|
15
|
+
|
16
|
+
def rating
|
17
|
+
document.css(".general.rating b").inner_text.strip.split('/').first.to_f
|
18
|
+
end
|
19
|
+
|
20
|
+
def votes
|
21
|
+
document.css(".general.rating a").inner_text.strip.sub(',', '').to_i
|
22
|
+
end
|
23
|
+
|
24
|
+
def genres
|
25
|
+
document.css('.info h5:contains("Genre:") + .info-content a:not(.tn15more)').collect{ |a| a.text }
|
26
|
+
end
|
27
|
+
|
28
|
+
def tagline
|
29
|
+
document.css('.info h5:contains("Tagline:") + .info-content').children[0].text.strip
|
30
|
+
end
|
31
|
+
|
32
|
+
def plot
|
33
|
+
document.css('.info h5:contains("Plot:") + .info-content').children[0].text.strip
|
34
|
+
end
|
35
|
+
|
36
|
+
def year
|
37
|
+
document.css("div#tn15title a:first")[0].text.to_i
|
38
|
+
end
|
39
|
+
|
40
|
+
private
|
41
|
+
def document
|
42
|
+
@document ||= Nokogiri::HTML(open(@url))
|
43
|
+
end
|
44
|
+
|
45
|
+
handle_exceptions_for :directors, :writers, :rating, :votes, :genres, :tagline, :plot, :year
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
module Myimdb
|
2
|
+
module Scraper
|
3
|
+
class Metacritic < Scraper::Base
|
4
|
+
def initialize(url)
|
5
|
+
@url = url
|
6
|
+
end
|
7
|
+
|
8
|
+
def rating
|
9
|
+
document.css("#metascore").inner_text.strip.to_f/10
|
10
|
+
end
|
11
|
+
|
12
|
+
def votes
|
13
|
+
document.at("a[@href='#critics']").inner_text.strip.to_i
|
14
|
+
end
|
15
|
+
|
16
|
+
def genres
|
17
|
+
document.css("#productinfo p:first").text.gsub(/^\S+:/, '').split("|").map(&:strip_useless_chars)
|
18
|
+
end
|
19
|
+
|
20
|
+
def plot
|
21
|
+
document.css("#productsummary .summarytext").inner_text.strip
|
22
|
+
end
|
23
|
+
|
24
|
+
private
|
25
|
+
def document
|
26
|
+
@document ||= Nokogiri::HTML(open(@url))
|
27
|
+
end
|
28
|
+
|
29
|
+
handle_exceptions_for :rating, :votes, :genres, :plot
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
module Myimdb
|
2
|
+
module Scraper
|
3
|
+
class RottenTomatoes < Scraper::Base
|
4
|
+
def initialize(url)
|
5
|
+
@url = url
|
6
|
+
end
|
7
|
+
|
8
|
+
def rating
|
9
|
+
document.css("#tomatometer_data p:nth-child(4) span").inner_text.strip.to_i
|
10
|
+
end
|
11
|
+
|
12
|
+
def votes
|
13
|
+
document.css("#tomatometer_data p:nth-child(1) span").inner_text.strip.to_i
|
14
|
+
end
|
15
|
+
|
16
|
+
def genres
|
17
|
+
document.css("#movie_stats .fl:first p:last .content a").inner_text.scraper_unescape_html.to_a
|
18
|
+
end
|
19
|
+
|
20
|
+
def plot
|
21
|
+
document.css("#movie_synopsis_all").inner_text.strip
|
22
|
+
end
|
23
|
+
|
24
|
+
private
|
25
|
+
def document
|
26
|
+
@document ||= Nokogiri::HTML(open(@url))
|
27
|
+
end
|
28
|
+
|
29
|
+
handle_exceptions_for :rating, :votes, :genres, :plot
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
require 'cgi'
|
2
|
+
require 'iconv'
|
3
|
+
|
4
|
+
module Myimdb
|
5
|
+
module Scraper
|
6
|
+
module StringExtensions
|
7
|
+
def scraper_unescape_html
|
8
|
+
Iconv.conv("UTF-8", 'ISO-8859-1', CGI::unescapeHTML(self))
|
9
|
+
end
|
10
|
+
|
11
|
+
def scraper_strip_tags
|
12
|
+
gsub(/<\/?[^>]*>/, "")
|
13
|
+
end
|
14
|
+
|
15
|
+
def strip_useless_chars
|
16
|
+
gsub(/[^a-zA-z0-9\|\-_\(\)@$\/\\]/, '')
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
String.send :include, Myimdb::Scraper::StringExtensions
|
@@ -0,0 +1,17 @@
|
|
1
|
+
module Myimdb
|
2
|
+
module Search
|
3
|
+
class Google
|
4
|
+
include HTTParty
|
5
|
+
|
6
|
+
format :json
|
7
|
+
headers 'Content-Type' => 'application/json'
|
8
|
+
base_uri 'ajax.googleapis.com'
|
9
|
+
|
10
|
+
def self.search_text( text, restrict_to=nil )
|
11
|
+
text = "site:#{restrict_to} #{text}" if restrict_to
|
12
|
+
response = get( '/ajax/services/search/web', :query=> {:v=> '1.0', :q=> text} )
|
13
|
+
response['responseData'] and response['responseData']['results']
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
data/myimdb.gemspec
ADDED
@@ -0,0 +1,70 @@
|
|
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{myimdb}
|
8
|
+
s.version = "0.3.0"
|
9
|
+
|
10
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
11
|
+
s.authors = ["Gaurav"]
|
12
|
+
s.date = %q{2009-12-28}
|
13
|
+
s.email = %q{gaurav@vinsol.com}
|
14
|
+
s.executables = ["myimdb", "myimdb.bat"]
|
15
|
+
s.extra_rdoc_files = [
|
16
|
+
"LICENSE",
|
17
|
+
"README.rdoc"
|
18
|
+
]
|
19
|
+
s.files = [
|
20
|
+
"LICENSE",
|
21
|
+
"README.rdoc",
|
22
|
+
"Rakefile",
|
23
|
+
"VERSION",
|
24
|
+
"bin/myimdb",
|
25
|
+
"bin/myimdb.bat",
|
26
|
+
"lib/myimdb.rb",
|
27
|
+
"lib/myimdb/scraper.rb",
|
28
|
+
"lib/myimdb/scraper/base.rb",
|
29
|
+
"lib/myimdb/scraper/imdb.rb",
|
30
|
+
"lib/myimdb/scraper/metacritic.rb",
|
31
|
+
"lib/myimdb/scraper/rotten_tomatoes.rb",
|
32
|
+
"lib/myimdb/scraper/string_extensions.rb",
|
33
|
+
"lib/myimdb/search.rb",
|
34
|
+
"lib/myimdb/search/google.rb",
|
35
|
+
"myimdb.gemspec",
|
36
|
+
"pkg/myimdb-0.0.0.gem",
|
37
|
+
"pkg/myimdb-0.1.0.gem",
|
38
|
+
"pkg/myimdb-0.2.0.gem",
|
39
|
+
"pkg/myimdb-0.3.0.gem",
|
40
|
+
"test/helper.rb",
|
41
|
+
"test/test_myimdb.rb"
|
42
|
+
]
|
43
|
+
s.homepage = %q{http://github.com/gauravs/myimdb}
|
44
|
+
s.rdoc_options = ["--charset=UTF-8"]
|
45
|
+
s.require_paths = ["lib"]
|
46
|
+
s.rubyforge_project = %q{myimdb}
|
47
|
+
s.rubygems_version = %q{1.3.5}
|
48
|
+
s.summary = %q{Utility gem for fetching movie details.}
|
49
|
+
s.test_files = [
|
50
|
+
"test/helper.rb",
|
51
|
+
"test/test_myimdb.rb"
|
52
|
+
]
|
53
|
+
|
54
|
+
if s.respond_to? :specification_version then
|
55
|
+
current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
|
56
|
+
s.specification_version = 3
|
57
|
+
|
58
|
+
if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
|
59
|
+
s.add_runtime_dependency(%q<httparty>, [">= 0.4.5"])
|
60
|
+
s.add_runtime_dependency(%q<nokogiri>, [">= 1.3.3"])
|
61
|
+
else
|
62
|
+
s.add_dependency(%q<httparty>, [">= 0.4.5"])
|
63
|
+
s.add_dependency(%q<nokogiri>, [">= 1.3.3"])
|
64
|
+
end
|
65
|
+
else
|
66
|
+
s.add_dependency(%q<httparty>, [">= 0.4.5"])
|
67
|
+
s.add_dependency(%q<nokogiri>, [">= 1.3.3"])
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
data/test/helper.rb
ADDED
data/test/test_myimdb.rb
ADDED
metadata
ADDED
@@ -0,0 +1,98 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: myimdb
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.3.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Gaurav
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-12-28 00:00:00 +05:30
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: httparty
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 0.4.5
|
24
|
+
version:
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: nokogiri
|
27
|
+
type: :runtime
|
28
|
+
version_requirement:
|
29
|
+
version_requirements: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 1.3.3
|
34
|
+
version:
|
35
|
+
description:
|
36
|
+
email: gaurav@vinsol.com
|
37
|
+
executables:
|
38
|
+
- myimdb
|
39
|
+
- myimdb.bat
|
40
|
+
extensions: []
|
41
|
+
|
42
|
+
extra_rdoc_files:
|
43
|
+
- LICENSE
|
44
|
+
- README.rdoc
|
45
|
+
files:
|
46
|
+
- LICENSE
|
47
|
+
- README.rdoc
|
48
|
+
- Rakefile
|
49
|
+
- VERSION
|
50
|
+
- bin/myimdb
|
51
|
+
- bin/myimdb.bat
|
52
|
+
- lib/myimdb.rb
|
53
|
+
- lib/myimdb/scraper.rb
|
54
|
+
- lib/myimdb/scraper/base.rb
|
55
|
+
- lib/myimdb/scraper/imdb.rb
|
56
|
+
- lib/myimdb/scraper/metacritic.rb
|
57
|
+
- lib/myimdb/scraper/rotten_tomatoes.rb
|
58
|
+
- lib/myimdb/scraper/string_extensions.rb
|
59
|
+
- lib/myimdb/search.rb
|
60
|
+
- lib/myimdb/search/google.rb
|
61
|
+
- myimdb.gemspec
|
62
|
+
- pkg/myimdb-0.0.0.gem
|
63
|
+
- pkg/myimdb-0.1.0.gem
|
64
|
+
- pkg/myimdb-0.2.0.gem
|
65
|
+
- pkg/myimdb-0.3.0.gem
|
66
|
+
- test/helper.rb
|
67
|
+
- test/test_myimdb.rb
|
68
|
+
has_rdoc: true
|
69
|
+
homepage: http://github.com/gauravs/myimdb
|
70
|
+
licenses: []
|
71
|
+
|
72
|
+
post_install_message:
|
73
|
+
rdoc_options:
|
74
|
+
- --charset=UTF-8
|
75
|
+
require_paths:
|
76
|
+
- lib
|
77
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
78
|
+
requirements:
|
79
|
+
- - ">="
|
80
|
+
- !ruby/object:Gem::Version
|
81
|
+
version: "0"
|
82
|
+
version:
|
83
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
84
|
+
requirements:
|
85
|
+
- - ">="
|
86
|
+
- !ruby/object:Gem::Version
|
87
|
+
version: "0"
|
88
|
+
version:
|
89
|
+
requirements: []
|
90
|
+
|
91
|
+
rubyforge_project: myimdb
|
92
|
+
rubygems_version: 1.3.5
|
93
|
+
signing_key:
|
94
|
+
specification_version: 3
|
95
|
+
summary: Utility gem for fetching movie details.
|
96
|
+
test_files:
|
97
|
+
- test/helper.rb
|
98
|
+
- test/test_myimdb.rb
|