nicovideo 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/README.txt +37 -0
- data/Rakefile +4 -0
- data/config/hoe.rb +71 -0
- data/config/requirements.rb +17 -0
- data/lib/nicovideo.rb +11 -0
- data/lib/nicovideo/base.rb +145 -0
- data/lib/nicovideo/comments.rb +9 -0
- data/lib/nicovideo/mechanize-ext.rb +20 -0
- data/lib/nicovideo/version.rb +9 -0
- data/lib/nicovideo/video.rb +14 -0
- data/sample/nv_download.rb +28 -0
- data/test/test_helper.rb +2 -0
- data/test/test_nicovideo.rb +11 -0
- metadata +68 -0
data/README.txt
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
= Nicovideo
|
2
|
+
|
3
|
+
Nicovideo is scraping NICONICO DOUGA utility for Ruby
|
4
|
+
(NICONICO DOUGA is Japanese Video Sharing Service)
|
5
|
+
|
6
|
+
- NICONICO DOUGA : http://www.nicovideo.jp/
|
7
|
+
|
8
|
+
== Installation
|
9
|
+
|
10
|
+
$ sudo gem install nicovideo
|
11
|
+
|
12
|
+
== Usage
|
13
|
+
|
14
|
+
See sample/nv_download.rb
|
15
|
+
|
16
|
+
== Author
|
17
|
+
|
18
|
+
- emergent ( http://d.hatena.ne.jp/emergent )
|
19
|
+
- thanks for many bloggers who wrote scraping scripts
|
20
|
+
|
21
|
+
== License
|
22
|
+
|
23
|
+
- 2-clause BSD License
|
24
|
+
|
25
|
+
|
26
|
+
|
27
|
+
|
28
|
+
|
29
|
+
|
30
|
+
|
31
|
+
|
32
|
+
|
33
|
+
|
34
|
+
|
35
|
+
|
36
|
+
|
37
|
+
|
data/Rakefile
ADDED
data/config/hoe.rb
ADDED
@@ -0,0 +1,71 @@
|
|
1
|
+
require 'nicovideo/version'
|
2
|
+
|
3
|
+
AUTHOR = 'emergent' # can also be an array of Authors
|
4
|
+
EMAIL = "emergent22 (at) livedoor.com"
|
5
|
+
DESCRIPTION = "utils for nicovideo"
|
6
|
+
GEM_NAME = 'nicovideo' # what ppl will type to install your gem
|
7
|
+
RUBYFORGE_PROJECT = 'nicovideo' # The unix name for your project
|
8
|
+
HOMEPATH = "http://#{RUBYFORGE_PROJECT}.rubyforge.org"
|
9
|
+
DOWNLOAD_PATH = "http://rubyforge.org/projects/#{RUBYFORGE_PROJECT}"
|
10
|
+
|
11
|
+
@config_file = "~/.rubyforge/user-config.yml"
|
12
|
+
@config = nil
|
13
|
+
RUBYFORGE_USERNAME = "unknown"
|
14
|
+
def rubyforge_username
|
15
|
+
unless @config
|
16
|
+
begin
|
17
|
+
@config = YAML.load(File.read(File.expand_path(@config_file)))
|
18
|
+
rescue
|
19
|
+
puts <<-EOS
|
20
|
+
ERROR: No rubyforge config file found: #{@config_file}
|
21
|
+
Run 'rubyforge setup' to prepare your env for access to Rubyforge
|
22
|
+
- See http://newgem.rubyforge.org/rubyforge.html for more details
|
23
|
+
EOS
|
24
|
+
exit
|
25
|
+
end
|
26
|
+
end
|
27
|
+
RUBYFORGE_USERNAME.replace @config["username"]
|
28
|
+
end
|
29
|
+
|
30
|
+
|
31
|
+
REV = nil
|
32
|
+
# UNCOMMENT IF REQUIRED:
|
33
|
+
# REV = `svn info`.each {|line| if line =~ /^Revision:/ then k,v = line.split(': '); break v.chomp; else next; end} rescue nil
|
34
|
+
VERS = Nicovideo::VERSION::STRING + (REV ? ".#{REV}" : "")
|
35
|
+
RDOC_OPTS = ['--quiet', '--title', 'nicovideo documentation',
|
36
|
+
"--opname", "index.html",
|
37
|
+
"--line-numbers",
|
38
|
+
"--main", "README",
|
39
|
+
"--inline-source"]
|
40
|
+
|
41
|
+
class Hoe
|
42
|
+
def extra_deps
|
43
|
+
@extra_deps.reject! { |x| Array(x).first == 'hoe' }
|
44
|
+
@extra_deps
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
# Generate all the Rake tasks
|
49
|
+
# Run 'rake -T' to see list of generated tasks (from gem root directory)
|
50
|
+
hoe = Hoe.new(GEM_NAME, VERS) do |p|
|
51
|
+
p.author = AUTHOR
|
52
|
+
p.description = DESCRIPTION
|
53
|
+
p.email = EMAIL
|
54
|
+
p.summary = DESCRIPTION
|
55
|
+
p.url = HOMEPATH
|
56
|
+
p.rubyforge_name = RUBYFORGE_PROJECT if RUBYFORGE_PROJECT
|
57
|
+
p.test_globs = ["test/**/test_*.rb"]
|
58
|
+
p.clean_globs |= ['**/.*.sw?', '*.gem', '.config', '**/.DS_Store'] #An array of file patterns to delete on clean.
|
59
|
+
|
60
|
+
# == Optional
|
61
|
+
p.changes = p.paragraphs_of("History.txt", 0..1).join("\\n\\n")
|
62
|
+
#p.extra_deps = [] # An array of rubygem dependencies [name, version], e.g. [ ['active_support', '>= 1.3.1'] ]
|
63
|
+
p.extra_deps = [
|
64
|
+
['mechanize', '>=0.6.0']
|
65
|
+
]
|
66
|
+
#p.spec_extras = {} # A hash of extra values to set in the gemspec.
|
67
|
+
end
|
68
|
+
|
69
|
+
CHANGES = hoe.paragraphs_of('History.txt', 0..1).join("\\n\\n")
|
70
|
+
PATH = (RUBYFORGE_PROJECT == GEM_NAME) ? RUBYFORGE_PROJECT : "#{RUBYFORGE_PROJECT}/#{GEM_NAME}"
|
71
|
+
hoe.remote_rdoc_dir = File.join(PATH.gsub(/^#{RUBYFORGE_PROJECT}\/?/,''), 'rdoc')
|
@@ -0,0 +1,17 @@
|
|
1
|
+
require 'fileutils'
|
2
|
+
include FileUtils
|
3
|
+
|
4
|
+
require 'rubygems'
|
5
|
+
%w[rake hoe newgem rubigen].each do |req_gem|
|
6
|
+
begin
|
7
|
+
require req_gem
|
8
|
+
rescue LoadError
|
9
|
+
puts "This Rakefile requires the '#{req_gem}' RubyGem."
|
10
|
+
puts "Installation: gem install #{req_gem} -y"
|
11
|
+
exit
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
$:.unshift(File.join(File.dirname(__FILE__), %w[.. lib]))
|
16
|
+
|
17
|
+
require 'nicovideo'
|
data/lib/nicovideo.rb
ADDED
@@ -0,0 +1,11 @@
|
|
1
|
+
$:.unshift File.dirname(__FILE__)
|
2
|
+
|
3
|
+
require 'nicovideo/mechanize-ext'
|
4
|
+
require 'nicovideo/base'
|
5
|
+
require 'nicovideo/video'
|
6
|
+
require 'nicovideo/comments'
|
7
|
+
#require 'nicovideo/tags'
|
8
|
+
#require 'nicovideo/ichiba'
|
9
|
+
#require 'nicovideo/rank'
|
10
|
+
#require 'nicovideo/feed'
|
11
|
+
|
@@ -0,0 +1,145 @@
|
|
1
|
+
require 'cgi'
|
2
|
+
require 'kconv'
|
3
|
+
|
4
|
+
module Nicovideo
|
5
|
+
|
6
|
+
class NicovideoArgError < StandardError ; end
|
7
|
+
class NicovideoLoginError < StandardError ; end
|
8
|
+
class NicovideoNotFoundError < StandardError ; end
|
9
|
+
|
10
|
+
class Base
|
11
|
+
NV_DEBUG_LEVEL = 0
|
12
|
+
TITLE_NICONICO = 'ニコニコ動画\(RC\)‐'.toutf8
|
13
|
+
|
14
|
+
def initialize mail=nil, password=nil
|
15
|
+
@mail = mail
|
16
|
+
@password = password
|
17
|
+
@logged_in = false
|
18
|
+
@agent = WWW::Mechanize.new()
|
19
|
+
|
20
|
+
# for parameters current video
|
21
|
+
@video_id = nil
|
22
|
+
@params = nil
|
23
|
+
@page = nil
|
24
|
+
self
|
25
|
+
end
|
26
|
+
|
27
|
+
def login mail=nil, password=nil
|
28
|
+
if !@logged_in
|
29
|
+
@mail = mail unless @mail
|
30
|
+
@password = password unless @password
|
31
|
+
account = {'mail' => @mail, 'password' => @password }
|
32
|
+
|
33
|
+
begin
|
34
|
+
@page = @agent.post('https://secure.nicovideo.jp/secure/login?site=niconico', account)
|
35
|
+
puts_debug @page.title
|
36
|
+
@logged_in = true
|
37
|
+
rescue
|
38
|
+
@logged_in = false
|
39
|
+
raise NicovideoLoginError
|
40
|
+
end
|
41
|
+
end
|
42
|
+
self
|
43
|
+
end
|
44
|
+
|
45
|
+
def watch(video_id)
|
46
|
+
@video_id = video_id
|
47
|
+
if block_given?
|
48
|
+
yield self
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
def logged_in?() @logged_in end
|
53
|
+
def comments(num=500) self.get_comments(@video_id, num) end
|
54
|
+
def flv() self.get_flv @video_id end
|
55
|
+
def title() self.get_title @video_id end
|
56
|
+
def tags() self.get_tags @video_id end
|
57
|
+
|
58
|
+
def get_tags video_id
|
59
|
+
page = get_page(video_id)
|
60
|
+
div = page.parser.search("div#video_tags")
|
61
|
+
tags = div.to_html.scan(/<a href=\"tag\/[\w\%]+?\">(.+?)<\/a>/ou).inject([]) {|arr, v|
|
62
|
+
puts_debug v[0]
|
63
|
+
arr << v[0]
|
64
|
+
}
|
65
|
+
tags
|
66
|
+
end
|
67
|
+
|
68
|
+
def get_title video_id
|
69
|
+
page = get_page(video_id)
|
70
|
+
title = page.title
|
71
|
+
puts_info title.toutf8.sub(/^#{TITLE_NICONICO}/ou, '')
|
72
|
+
title.toutf8.sub(/^#{TITLE_NICONICO}/ou, '')
|
73
|
+
end
|
74
|
+
|
75
|
+
def get_video video_id=nil
|
76
|
+
puts_info 'getting video : id = ' + video_id
|
77
|
+
self.get_flv video_id
|
78
|
+
end
|
79
|
+
|
80
|
+
def get_flv video_id=nil
|
81
|
+
puts_info 'getting flv : id = ' + video_id if video_id
|
82
|
+
begin
|
83
|
+
params = get_params video_id
|
84
|
+
|
85
|
+
video_url = CGI.unescape(params['url'])
|
86
|
+
video_flv = @agent.get_file(video_url)
|
87
|
+
Video.new(video_id, video_flv)
|
88
|
+
end
|
89
|
+
end
|
90
|
+
|
91
|
+
def get_comments video_id, num=500
|
92
|
+
puts_info 'getting comment xml : id = ' + video_id
|
93
|
+
begin
|
94
|
+
params = get_params video_id
|
95
|
+
raise unless params['ms']
|
96
|
+
|
97
|
+
thread_id = params['thread_id']
|
98
|
+
body = %!<thread res_from="-#{num}" version="20061206" thread="#{thread_id}" />!
|
99
|
+
post_url = CGI.unescape(params['ms'])
|
100
|
+
comment_xml = @agent.post_data(post_url, body).body
|
101
|
+
puts_debug comment_xml
|
102
|
+
Comments.new(video_id, comment_xml)
|
103
|
+
end
|
104
|
+
end
|
105
|
+
|
106
|
+
private
|
107
|
+
def get_params video_id=nil
|
108
|
+
self.login unless @logged_in
|
109
|
+
|
110
|
+
begin
|
111
|
+
if !((video_id == @video_id) && @params)
|
112
|
+
puts_info 'getting params : id = ' + video_id
|
113
|
+
@video_id = video_id
|
114
|
+
page = get_page video_id
|
115
|
+
content = @agent.get_file('http://www.nicovideo.jp/api/getflv?v=' + video_id)
|
116
|
+
puts_debug content
|
117
|
+
@params = content.scan(/([^&]+)=([^&]*)/).inject({}){|h, v| h[v[0]] = v[1]; h}
|
118
|
+
else
|
119
|
+
puts_info 'params are already in cache : id = ' + video_id
|
120
|
+
end
|
121
|
+
@params
|
122
|
+
rescue
|
123
|
+
raise NicovideoNotFoundError
|
124
|
+
end
|
125
|
+
end
|
126
|
+
|
127
|
+
def get_page video_id
|
128
|
+
puts_info 'getting HTML page : id = ' + video_id
|
129
|
+
@agent.get('http://www.nicovideo.jp/watch/' + video_id)
|
130
|
+
end
|
131
|
+
|
132
|
+
def puts_error str ; puts str if (NV_DEBUG_LEVEL >= 1) ; end
|
133
|
+
def puts_info str ; puts str if (NV_DEBUG_LEVEL >= 2) ; end
|
134
|
+
def puts_debug str ; puts str if (NV_DEBUG_LEVEL >= 3) ; end
|
135
|
+
|
136
|
+
end
|
137
|
+
|
138
|
+
def Nicovideo.new(mail, password)
|
139
|
+
Base.new(mail, password)
|
140
|
+
end
|
141
|
+
|
142
|
+
def Nicovideo.login(mail, password)
|
143
|
+
Base.new(mail, password).login
|
144
|
+
end
|
145
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
# file: mechanize-ext.rb
|
2
|
+
require 'mechanize'
|
3
|
+
|
4
|
+
module WWW
|
5
|
+
class Mechanize
|
6
|
+
self.class_eval {
|
7
|
+
def post_data(url, data='', enctype=nil)
|
8
|
+
cur_page = current_page || Page.new( nil, {'content-type'=>'text/html'})
|
9
|
+
request_data = data
|
10
|
+
abs_url = to_absolute_uri(url, cur_page)
|
11
|
+
request = fetch_request(abs_url, :post)
|
12
|
+
request.add_field('Content-Length', request_data.size.to_s)
|
13
|
+
|
14
|
+
page = fetch_page(abs_url, request, cur_page, [request_data])
|
15
|
+
add_to_history(page)
|
16
|
+
page
|
17
|
+
end
|
18
|
+
}
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'nicovideo'
|
3
|
+
require 'yaml'
|
4
|
+
|
5
|
+
video_ids = ARGV
|
6
|
+
|
7
|
+
# set account
|
8
|
+
account = YAML.load_file(ENV['HOME'] + '/.nicovideo/account.yml')
|
9
|
+
mail = account['mail']
|
10
|
+
password = account['password']
|
11
|
+
|
12
|
+
# you must login to Nicovideo
|
13
|
+
nv = Nicovideo.new(mail, password).login
|
14
|
+
|
15
|
+
# get videos and comments
|
16
|
+
video_ids.each {|video_id|
|
17
|
+
|
18
|
+
nv.watch(video_id) {|v|
|
19
|
+
puts 'title = ' + v.title
|
20
|
+
puts 'tags = ' + v.tags.join(' ')
|
21
|
+
puts 'getting comments xml'
|
22
|
+
File.open("#{video_id}.xml", "wb") {|f| f.write v.comments(100).to_xml }
|
23
|
+
puts 'getting flv file'
|
24
|
+
File.open("#{video_id}.flv", "wb") {|f| f.write v.flv }
|
25
|
+
}
|
26
|
+
|
27
|
+
sleep 3
|
28
|
+
}
|
data/test/test_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,68 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
rubygems_version: 0.9.4
|
3
|
+
specification_version: 1
|
4
|
+
name: nicovideo
|
5
|
+
version: !ruby/object:Gem::Version
|
6
|
+
version: 0.0.1
|
7
|
+
date: 2008-01-06 00:00:00 +09:00
|
8
|
+
summary: utils for nicovideo
|
9
|
+
require_paths:
|
10
|
+
- lib
|
11
|
+
email: emergent22 (at) livedoor.com
|
12
|
+
homepage: http://nicovideo.rubyforge.org
|
13
|
+
rubyforge_project: nicovideo
|
14
|
+
description: utils for nicovideo
|
15
|
+
autorequire:
|
16
|
+
default_executable:
|
17
|
+
bindir: bin
|
18
|
+
has_rdoc: true
|
19
|
+
required_ruby_version: !ruby/object:Gem::Version::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">"
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 0.0.0
|
24
|
+
version:
|
25
|
+
platform: ruby
|
26
|
+
signing_key:
|
27
|
+
cert_chain:
|
28
|
+
post_install_message:
|
29
|
+
authors:
|
30
|
+
- emergent
|
31
|
+
files:
|
32
|
+
- README.txt
|
33
|
+
- Rakefile
|
34
|
+
- config/hoe.rb
|
35
|
+
- config/requirements.rb
|
36
|
+
- lib/nicovideo.rb
|
37
|
+
- lib/nicovideo/version.rb
|
38
|
+
- lib/nicovideo/mechanize-ext.rb
|
39
|
+
- lib/nicovideo/base.rb
|
40
|
+
- lib/nicovideo/video.rb
|
41
|
+
- lib/nicovideo/comments.rb
|
42
|
+
- test/test_helper.rb
|
43
|
+
- test/test_nicovideo.rb
|
44
|
+
- sample/nv_download.rb
|
45
|
+
test_files:
|
46
|
+
- test/test_nicovideo.rb
|
47
|
+
- test/test_helper.rb
|
48
|
+
rdoc_options:
|
49
|
+
- --main
|
50
|
+
- README.txt
|
51
|
+
extra_rdoc_files:
|
52
|
+
- README.txt
|
53
|
+
executables: []
|
54
|
+
|
55
|
+
extensions: []
|
56
|
+
|
57
|
+
requirements: []
|
58
|
+
|
59
|
+
dependencies:
|
60
|
+
- !ruby/object:Gem::Dependency
|
61
|
+
name: mechanize
|
62
|
+
version_requirement:
|
63
|
+
version_requirements: !ruby/object:Gem::Version::Requirement
|
64
|
+
requirements:
|
65
|
+
- - ">="
|
66
|
+
- !ruby/object:Gem::Version
|
67
|
+
version: 0.6.0
|
68
|
+
version:
|