ameblogazo 0.0.1 → 0.0.2
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/README.rdoc +13 -12
- data/ameblogazo.gemspec +4 -1
- data/bin/ameblogazo +22 -23
- data/lib/ameblogazo.rb +111 -102
- data/lib/ameblogazo/version.rb +1 -1
- data/spec/ameblogazo_spec.rb +47 -0
- data/spec/spec_helper.rb +22 -0
- metadata +43 -6
data/README.rdoc
CHANGED
@@ -1,34 +1,35 @@
|
|
1
1
|
= Ameblogazo
|
2
2
|
|
3
|
-
|
3
|
+
アメーバブログの画像をダウンロードするツールとライブラリ。
|
4
4
|
|
5
5
|
== Installing
|
6
6
|
|
7
7
|
gem install ameblogazo
|
8
8
|
|
9
|
-
dependencies:
|
9
|
+
dependencies: capybara, capybara-webkit, headless
|
10
10
|
|
11
|
-
|
11
|
+
require: qt-devel qt-webkit-devel > 4.7, Xvfb
|
12
12
|
|
13
|
-
|
14
|
-
ameblogazo -i ameba_id -d /tmp -c date
|
13
|
+
== Using
|
15
14
|
|
16
|
-
|
17
|
-
ameblogazo -i ameba_id -d /tmp -
|
15
|
+
画像を最新のものから指定枚数だけダウンロード
|
16
|
+
ameblogazo -i ameba_id -d /tmp -n 10
|
17
|
+
|
18
|
+
指定した場所に保存されている画像と同一のものが見つかるまでダウンロード
|
19
|
+
ameblogazo -i ameba_id -d /tmp
|
18
20
|
|
19
21
|
オプションの説明
|
20
22
|
-i アメーバIDを指定
|
21
23
|
-d 保存先ディレクトリを指定
|
22
24
|
-c カテゴライズ設定(title or date)。デフォルトは無効。titleは記事タイトル毎に分類。dateは日付で分類。
|
23
|
-
-n
|
24
|
-
-
|
25
|
+
-n 画像の枚数を指定
|
26
|
+
-s SeleniumDriverを使用
|
25
27
|
|
26
|
-
==
|
28
|
+
== Library
|
27
29
|
|
28
30
|
サンプル
|
29
31
|
require 'ameblogazo'
|
30
|
-
Ameblogazo.download(:ameba_id=>'ameba_id', :dir=>'/tmp', :
|
31
|
-
Ameblogazo.download_periodic(:ameba_id=>'ameba_id', :dir=>'/tmp', :categorize=>'date')
|
32
|
+
Ameblogazo.download(:ameba_id=>'ameba_id', :dir=>'/tmp', :num=>10, :selenium=>true)
|
32
33
|
|
33
34
|
== Copyright
|
34
35
|
|
data/ameblogazo.gemspec
CHANGED
@@ -21,5 +21,8 @@ Gem::Specification.new do |s|
|
|
21
21
|
# specify any dependencies here; for example:
|
22
22
|
# s.add_development_dependency "rspec"
|
23
23
|
# s.add_runtime_dependency "rest-client"
|
24
|
-
s.add_dependency('
|
24
|
+
s.add_dependency('capybara')
|
25
|
+
s.add_dependency('capybara-webkit')
|
26
|
+
s.add_dependency('headless')
|
27
|
+
s.add_development_dependency('rspec')
|
25
28
|
end
|
data/bin/ameblogazo
CHANGED
@@ -3,28 +3,27 @@
|
|
3
3
|
|
4
4
|
require "ameblogazo"
|
5
5
|
require "optparse"
|
6
|
+
require "headless"
|
6
7
|
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
rescue => ex
|
29
|
-
puts ex.message
|
8
|
+
Headless.ly do
|
9
|
+
opts = {}
|
10
|
+
op = OptionParser.new do |opt|
|
11
|
+
opt.on('-i ID', '--ameba-id=ID', 'アメーバIDを指定') {|v| opts[:ameba_id] = v}
|
12
|
+
opt.on('-d DIR', '--dir=DIR', '画像の保存先ディレクトリを指定') {|v| opts[:dir] = v}
|
13
|
+
opt.on('-c TYPE', '--categorize=TYPE', ['title', 'date'], 'カテゴライズ(title, date)を指定') {|v| opts[:categorize] = v}
|
14
|
+
opt.on('-n NUM', '--num=NUM', '画像の枚数を指定') {|v| opts[:num] = v}
|
15
|
+
opt.on('-s', '--selenium', 'selenium driverを使用') {|v| opts[:selenium] = true}
|
16
|
+
|
17
|
+
opt.parse!
|
18
|
+
end
|
19
|
+
if opts.empty?
|
20
|
+
puts op
|
21
|
+
exit
|
22
|
+
end
|
23
|
+
|
24
|
+
begin
|
25
|
+
Ameblogazo.download(opts)
|
26
|
+
rescue => ex
|
27
|
+
puts ex.message
|
28
|
+
end
|
30
29
|
end
|
data/lib/ameblogazo.rb
CHANGED
@@ -1,14 +1,34 @@
|
|
1
1
|
# coding: utf-8
|
2
2
|
require "ameblogazo/version"
|
3
3
|
require 'open-uri'
|
4
|
-
require 'nokogiri'
|
5
4
|
require 'fileutils'
|
5
|
+
require 'capybara'
|
6
|
+
require 'capybara/dsl'
|
7
|
+
require 'capybara-webkit'
|
6
8
|
|
7
9
|
module Ameblogazo
|
8
10
|
class Gazo
|
9
11
|
class GazoException < StandardError
|
10
12
|
end
|
11
13
|
|
14
|
+
class Driver
|
15
|
+
include Capybara::DSL
|
16
|
+
end
|
17
|
+
|
18
|
+
class WebkitDriver < Driver
|
19
|
+
def initialize()
|
20
|
+
Capybara.default_driver = :webkit
|
21
|
+
Capybara.javascript_driver = :webkit
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
class SeleniumDriver < Driver
|
26
|
+
def initialize()
|
27
|
+
Capybara.default_driver = :selenium
|
28
|
+
Capybara.javascript_driver = :selenium
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
12
32
|
# オプションチェック
|
13
33
|
def _check_options(options)
|
14
34
|
if options.nil? or !options.is_a?(Hash)
|
@@ -28,6 +48,15 @@ module Ameblogazo
|
|
28
48
|
options
|
29
49
|
end
|
30
50
|
|
51
|
+
# driver初期化
|
52
|
+
def _init_driver(selenium)
|
53
|
+
if selenium
|
54
|
+
@driver = SeleniumDriver.new
|
55
|
+
else
|
56
|
+
@driver = WebkitDriver.new
|
57
|
+
end
|
58
|
+
end
|
59
|
+
|
31
60
|
# 一番最初の画像のURLを取得する
|
32
61
|
def _find_image_url(ameba_id)
|
33
62
|
puts "検索中..."
|
@@ -43,6 +72,12 @@ module Ameblogazo
|
|
43
72
|
end
|
44
73
|
doc = Nokogiri::HTML(html)
|
45
74
|
|
75
|
+
# 有効なameba_idか確認
|
76
|
+
sorry = doc.xpath("//body[@class='sorry']")
|
77
|
+
unless sorry.empty?
|
78
|
+
raise GazoException, "存在しないIDです"
|
79
|
+
end
|
80
|
+
|
46
81
|
a = doc.xpath("//a")
|
47
82
|
a.each do |node|
|
48
83
|
if /http:\/\/ameblo.jp\/#{ameba_id}\/image-\d{11}-\d{11}.html/ =~ node[:href]
|
@@ -59,155 +94,129 @@ module Ameblogazo
|
|
59
94
|
end
|
60
95
|
image_url
|
61
96
|
end
|
62
|
-
|
63
|
-
#
|
64
|
-
def
|
97
|
+
|
98
|
+
# ダウンロード対象のURLや保存先を取得
|
99
|
+
def _get_info(dir, categorize)
|
100
|
+
img = @driver.find(:xpath, '//img[@id="imgItem"]')
|
101
|
+
download_url = img[:src]
|
102
|
+
filename = File.basename(download_url)
|
103
|
+
title = @driver.find("#entryLink").text
|
104
|
+
date = download_url[/\d{8}/]
|
105
|
+
|
65
106
|
# カテゴリー分け(タイトルとか日付)
|
66
107
|
if categorize == "title"
|
67
|
-
title = img[:alt]
|
68
108
|
dir = "#{dir}/#{title}"
|
69
109
|
elsif categorize == "date"
|
70
|
-
if
|
71
|
-
date = $1
|
110
|
+
if date
|
72
111
|
dir = "#{dir}/#{date}"
|
73
112
|
else
|
74
|
-
|
113
|
+
puts "うまく日付がとれなかったのでカテゴライズせずに保存します"
|
75
114
|
end
|
76
115
|
end
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
116
|
+
|
117
|
+
# ディレクトリが存在しなければ作成する
|
118
|
+
unless File.directory?(dir)
|
119
|
+
print "ディレクトリを作成します #{dir}\n"
|
120
|
+
FileUtils.mkdir_p(dir)
|
121
|
+
end
|
122
|
+
download_file = "#{dir}/#{filename}"
|
123
|
+
{:url=>download_url, :file=>download_file, :title=>title, :date=>date}
|
84
124
|
end
|
85
|
-
|
86
|
-
# ダウンロード対象のURLや保存先を取得
|
87
|
-
def _download_info(doc, dir, categorize)
|
88
|
-
img = doc.xpath('//img[@id="centerImg"]')
|
89
|
-
unless img.empty?
|
90
|
-
download_url = img[0][:src]
|
91
|
-
filename = File.basename(download_url)
|
92
|
-
|
93
|
-
# カテゴリー分け(タイトルとか日付)
|
94
|
-
dir = _categorize(dir, categorize, img[0])
|
95
125
|
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
FileUtils.mkdir_p(dir)
|
100
|
-
end
|
101
|
-
download_file = "#{dir}/#{filename}"
|
102
|
-
return {:url=>download_url, :file=>download_file}
|
103
|
-
end
|
104
|
-
return {}
|
126
|
+
# 次にダウンロードするべき画像を開く
|
127
|
+
def _next_page()
|
128
|
+
@driver.find("#nextNavi").click
|
105
129
|
end
|
106
|
-
|
107
|
-
#
|
108
|
-
def
|
130
|
+
|
131
|
+
# 画像をダウンロードして保存
|
132
|
+
def _save_img(url, file)
|
109
133
|
open(url) do |doc|
|
110
134
|
open(file, 'w') do |fp|
|
111
135
|
fp.print doc.read
|
112
136
|
end
|
113
137
|
end
|
114
138
|
filename = File.basename(file)
|
115
|
-
|
139
|
+
puts "#{filename} を保存しました"
|
116
140
|
end
|
117
141
|
|
118
|
-
#
|
119
|
-
def _download_next_url(doc)
|
120
|
-
a = doc.xpath('//a[@id="imgLink"]')
|
121
|
-
unless a.empty?
|
122
|
-
image_url = a[0][:href] # 次の画像URL
|
123
|
-
end
|
124
|
-
end
|
125
|
-
|
126
|
-
# 指定URLの物を保存する
|
127
|
-
def _download(url, dir, categorize)
|
128
|
-
doc = _download_doc(url)
|
129
|
-
info = _download_info(doc, dir, categorize)
|
130
|
-
|
131
|
-
if File.exists?(info[:file])
|
132
|
-
print "もうダウロード済みみたいです\n"
|
133
|
-
else
|
134
|
-
_download_img(info[:url], info[:file])
|
135
|
-
end
|
136
|
-
_download_next_url(doc)
|
137
|
-
end
|
138
|
-
|
139
|
-
# ダウンロード済みの画像をみつけたら止める
|
140
|
-
def _download_periodic(url, dir, categorize)
|
141
|
-
doc = _download_doc(url)
|
142
|
-
info = _download_info(doc, dir, categorize)
|
143
|
-
|
144
|
-
if File.exists?(info[:file])
|
145
|
-
print "ダウロード済みの見つけたので終了します\n"
|
146
|
-
return nil
|
147
|
-
else
|
148
|
-
_download_img(info[:url], info[:file])
|
149
|
-
end
|
150
|
-
_download_next_url(doc)
|
151
|
-
end
|
152
|
-
|
153
|
-
# 画像を取得する
|
142
|
+
# 画像を保存する
|
154
143
|
# :ameba_id => アメーバID
|
155
144
|
# :dir => 保存先ディレクトリ
|
156
145
|
# :categorize => タイトル毎などに分類する(デフォルト無効)[nil, "title", "date"]
|
157
146
|
# :num => 取得する枚数(新しいものから順番に)[数値]
|
158
|
-
def
|
147
|
+
def fetch(options)
|
159
148
|
options = _check_options(options)
|
160
149
|
ameba_id = options[:ameba_id]
|
161
150
|
categorize = options[:categorize]
|
162
151
|
dir = options[:dir]
|
163
152
|
num = options[:num]
|
164
153
|
|
165
|
-
|
154
|
+
# driver初期化
|
155
|
+
_init_driver(options[:selenium])
|
166
156
|
|
167
|
-
|
168
|
-
|
169
|
-
|
170
|
-
|
171
|
-
|
172
|
-
|
173
|
-
|
174
|
-
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
|
157
|
+
# 画像ページに移動
|
158
|
+
@driver.visit(_find_image_url(ameba_id))
|
159
|
+
|
160
|
+
# 最初にみつけた画像から次の画像へと順番にたどってく
|
161
|
+
info_list = []
|
162
|
+
loop.with_index do |_, i|
|
163
|
+
break if i == num # 指定枚数で終了
|
164
|
+
info = _get_info(dir, categorize)
|
165
|
+
break if !info_list[0].nil? and info_list[0][:file] == info[:file]
|
166
|
+
info_list.push(info)
|
167
|
+
|
168
|
+
if File.exists?(info[:file])
|
169
|
+
if num
|
170
|
+
puts "既にダウンロードされている画像です"
|
171
|
+
else
|
172
|
+
puts "ダウンロード済みの画像が見つかったので終了します"
|
173
|
+
break
|
174
|
+
end
|
175
|
+
else
|
176
|
+
_save_img(info[:url], info[:file])
|
180
177
|
end
|
178
|
+
_next_page
|
179
|
+
sleep(0.5)
|
181
180
|
end
|
182
181
|
end
|
183
182
|
|
184
|
-
#
|
185
|
-
|
186
|
-
def get_periodic(options)
|
183
|
+
# 画像の情報を取得する
|
184
|
+
def info(options)
|
187
185
|
options = _check_options(options)
|
188
186
|
ameba_id = options[:ameba_id]
|
189
187
|
categorize = options[:categorize]
|
190
188
|
dir = options[:dir]
|
189
|
+
num = options[:num]
|
190
|
+
|
191
|
+
# driver初期化
|
192
|
+
_init_driver(options[:selenium])
|
193
|
+
|
194
|
+
# 画像ページに移動
|
195
|
+
@driver.visit(_find_image_url(ameba_id))
|
191
196
|
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
|
196
|
-
|
197
|
-
|
197
|
+
# 最初にみつけた画像から次の画像へと順番にたどってく
|
198
|
+
info_list = []
|
199
|
+
loop.with_index do |a, i|
|
200
|
+
break if i == num # 指定枚数で終了
|
201
|
+
info = _get_info(dir, categorize)
|
202
|
+
break if !info_list[0].nil? and info_list[0][:file] == info[:file]
|
203
|
+
info_list.push(info)
|
204
|
+
_next_page
|
205
|
+
sleep(0.5)
|
198
206
|
end
|
207
|
+
info_list
|
199
208
|
end
|
200
209
|
end
|
201
210
|
|
202
211
|
def download(options)
|
203
212
|
gazo = Gazo.new
|
204
|
-
gazo.
|
213
|
+
gazo.fetch(options)
|
205
214
|
end
|
206
215
|
|
207
|
-
def
|
216
|
+
def info(options)
|
208
217
|
gazo = Gazo.new
|
209
|
-
gazo.
|
218
|
+
gazo.info(options)
|
210
219
|
end
|
211
220
|
|
212
|
-
module_function :download, :
|
221
|
+
module_function :download, :info
|
213
222
|
end
|
data/lib/ameblogazo/version.rb
CHANGED
@@ -0,0 +1,47 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
require 'spec_helper'
|
3
|
+
|
4
|
+
describe Ameblogazo::Gazo do
|
5
|
+
before(:all) do
|
6
|
+
@gazo = Ameblogazo::Gazo.new
|
7
|
+
end
|
8
|
+
|
9
|
+
describe "オプションをチェックするとき" do
|
10
|
+
it "nilだったら例外を投げること" do
|
11
|
+
expect{ @gazo._check_options(nil) }.to raise_error(Ameblogazo::Gazo::GazoException)
|
12
|
+
end
|
13
|
+
it "ディレクトリが指定されていなかったら例外を投げること" do
|
14
|
+
options = {}
|
15
|
+
expect{ @gazo._check_options(options) }.to raise_error(Ameblogazo::Gazo::GazoException)
|
16
|
+
end
|
17
|
+
it "枚数指定の値が数値以外だったら例外を投げること" do
|
18
|
+
options = {:dir=>'/tmp', :num=>'abc'}
|
19
|
+
expect{ @gazo._check_options(options) }.to raise_error(Ameblogazo::Gazo::GazoException)
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
describe "最初の画像のURLを取得するとき" do
|
24
|
+
it "無効なIDが渡されたら例外を投げること" do
|
25
|
+
expect{ @gazo._find_image_url("ameblogazotest") }.to raise_error(Ameblogazo::Gazo::GazoException)
|
26
|
+
end
|
27
|
+
|
28
|
+
it "返ってくる値がnilではないこと" do
|
29
|
+
@gazo._find_image_url("staff").nil?.should == false
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
describe "画像をダウンロードするとき" do
|
34
|
+
before(:all) do
|
35
|
+
url = @gazo._find_image_url("staff")
|
36
|
+
@gazo.instance_eval{@driver.visit(url)}
|
37
|
+
end
|
38
|
+
|
39
|
+
it "ダウンロードURLや保存先が取得できること" do
|
40
|
+
@gazo._get_info("/tmp", "title").empty?.should == false
|
41
|
+
end
|
42
|
+
|
43
|
+
it "次の画像に移動できること" do
|
44
|
+
@gazo._next_page
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# This file was generated by the `rspec --init` command. Conventionally, all
|
2
|
+
# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
|
3
|
+
# Require this file using `require "spec_helper"` to ensure that it is only
|
4
|
+
# loaded once.
|
5
|
+
#
|
6
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
7
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
8
|
+
require 'rspec'
|
9
|
+
require 'ameblogazo'
|
10
|
+
|
11
|
+
# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
|
12
|
+
RSpec.configure do |config|
|
13
|
+
config.treat_symbols_as_metadata_keys_with_true_values = true
|
14
|
+
config.run_all_when_everything_filtered = true
|
15
|
+
config.filter_run :focus
|
16
|
+
|
17
|
+
# Run specs in random order to surface order dependencies. If you find an
|
18
|
+
# order dependency and want to debug it, you can fix the order by providing
|
19
|
+
# the seed, which is printed after each run.
|
20
|
+
# --seed 1234
|
21
|
+
config.order = 'random'
|
22
|
+
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: ameblogazo
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.2
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,11 +9,11 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-
|
12
|
+
date: 2012-12-09 00:00:00.000000000Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
|
-
name:
|
16
|
-
requirement: &
|
15
|
+
name: capybara
|
16
|
+
requirement: &69325480 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ! '>='
|
@@ -21,7 +21,40 @@ dependencies:
|
|
21
21
|
version: '0'
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *69325480
|
25
|
+
- !ruby/object:Gem::Dependency
|
26
|
+
name: capybara-webkit
|
27
|
+
requirement: &69325180 !ruby/object:Gem::Requirement
|
28
|
+
none: false
|
29
|
+
requirements:
|
30
|
+
- - ! '>='
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '0'
|
33
|
+
type: :runtime
|
34
|
+
prerelease: false
|
35
|
+
version_requirements: *69325180
|
36
|
+
- !ruby/object:Gem::Dependency
|
37
|
+
name: headless
|
38
|
+
requirement: &69324970 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ! '>='
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: '0'
|
44
|
+
type: :runtime
|
45
|
+
prerelease: false
|
46
|
+
version_requirements: *69324970
|
47
|
+
- !ruby/object:Gem::Dependency
|
48
|
+
name: rspec
|
49
|
+
requirement: &69324760 !ruby/object:Gem::Requirement
|
50
|
+
none: false
|
51
|
+
requirements:
|
52
|
+
- - ! '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
type: :development
|
56
|
+
prerelease: false
|
57
|
+
version_requirements: *69324760
|
25
58
|
description: get ameba blog images
|
26
59
|
email:
|
27
60
|
- labs.ninxit@gmail.com
|
@@ -38,6 +71,8 @@ files:
|
|
38
71
|
- bin/ameblogazo
|
39
72
|
- lib/ameblogazo.rb
|
40
73
|
- lib/ameblogazo/version.rb
|
74
|
+
- spec/ameblogazo_spec.rb
|
75
|
+
- spec/spec_helper.rb
|
41
76
|
homepage: ''
|
42
77
|
licenses: []
|
43
78
|
post_install_message:
|
@@ -62,4 +97,6 @@ rubygems_version: 1.8.10
|
|
62
97
|
signing_key:
|
63
98
|
specification_version: 3
|
64
99
|
summary: get ameba blog images
|
65
|
-
test_files:
|
100
|
+
test_files:
|
101
|
+
- spec/ameblogazo_spec.rb
|
102
|
+
- spec/spec_helper.rb
|