bulk_youtube 0.1.0
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/.gitignore +17 -0
- data/.rspec +2 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +42 -0
- data/Rakefile +7 -0
- data/bulk_youtube.gemspec +27 -0
- data/lib/bulk_youtube.rb +132 -0
- data/lib/bulk_youtube/globals.rb +15 -0
- data/lib/bulk_youtube/version.rb +3 -0
- data/spec/embedded_playlists_spec.rb +50 -0
- data/spec/full_page_playlist_spec.rb +47 -0
- data/spec/spec_helper.rb +11 -0
- metadata +143 -0
data/.gitignore
ADDED
data/.rspec
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Michael Zakany
|
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 +1,42 @@
|
|
1
|
+
# Youtube Bulk Video Downloader:
|
2
|
+
=======
|
3
|
+
```
|
4
|
+
Uses mechanize (2.7.2) and nokogiri (1.6.1)
|
5
|
+
|
6
|
+
Purpose: when you need to download multiple youtube files, say a course or tutorial i.e. to watch offline.
|
7
|
+
|
8
|
+
Note: change the @max_downloads to increase the amount of mp4s can send.
|
9
|
+
|
10
|
+
```
|
11
|
+
|
12
|
+
|
13
|
+
Variables:
|
14
|
+
==========
|
15
|
+
|
16
|
+
```
|
17
|
+
> search = 'https://www.youtube.com/playlist?list=PLV1-QgpUU7N2TVWS6gEVMqEfAFjAl-DV6'
|
18
|
+
> save = '/path/to/save'
|
19
|
+
> word = 'French'
|
20
|
+
```
|
21
|
+
|
22
|
+
Send mp4's to your local folder:
|
23
|
+
==========
|
24
|
+
|
25
|
+
|
26
|
+
```
|
27
|
+
Without keyword search:
|
28
|
+
> find = Scrape.new(search,save)
|
29
|
+
> find.grab_links.links #show the link objects as is
|
30
|
+
> find.grab_links.show #show a more concise version
|
31
|
+
> find.grab_links.you_convert #send links to folder
|
32
|
+
```
|
33
|
+
```
|
34
|
+
With keyword search:
|
35
|
+
> find = Scrape.new(search,save)
|
36
|
+
> find.grab_links('French').links
|
37
|
+
> find.grab_links('French').you_convert
|
38
|
+
```
|
39
|
+
```
|
40
|
+
Set to download more
|
41
|
+
> Scrape.new(search,save,10).grab_links.you_convert
|
42
|
+
```
|
data/Rakefile
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'bulk_youtube/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "bulk_youtube"
|
8
|
+
spec.version = BulkYoutube::VERSION
|
9
|
+
spec.authors = ["Michael C. Zakany"]
|
10
|
+
spec.email = ["mzakany@gmail.com"]
|
11
|
+
spec.description = %q{Download batches of youtube videos}
|
12
|
+
spec.summary = %q{Download Batches of youtube videos}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency "nokogiri"
|
22
|
+
spec.add_dependency "mechanize"
|
23
|
+
|
24
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
25
|
+
spec.add_development_dependency "rake"
|
26
|
+
spec.add_development_dependency "rspec"
|
27
|
+
end
|
data/lib/bulk_youtube.rb
ADDED
@@ -0,0 +1,132 @@
|
|
1
|
+
require "bulk_youtube/version"
|
2
|
+
require "bulk_youtube/globals"
|
3
|
+
require 'mechanize'
|
4
|
+
require 'nokogiri'
|
5
|
+
|
6
|
+
|
7
|
+
module BulkYoutube
|
8
|
+
class Scrape
|
9
|
+
include Globals
|
10
|
+
|
11
|
+
attr_accessor :search_path, :save_destination, :max_retries
|
12
|
+
|
13
|
+
def initialize(search_path=nil, save_destination=nil, max_downloads=2, max_retries=10)
|
14
|
+
@search_path = search_path
|
15
|
+
@save_destination = save_destination
|
16
|
+
@max_downloads = max_downloads
|
17
|
+
@max_retries = max_retries
|
18
|
+
end
|
19
|
+
|
20
|
+
|
21
|
+
# def you_convert
|
22
|
+
# retry_count = 0
|
23
|
+
# begin
|
24
|
+
# send_files(@link_arr)
|
25
|
+
# rescue Net::HTTP::Persistent::Error => e
|
26
|
+
# raise unless e.message =~ /too man connection resets/
|
27
|
+
# if retry_count > @max_retries
|
28
|
+
# puts "**** WARN: Mechanize retried connection reset #{@max_retries} times"
|
29
|
+
# raise
|
30
|
+
# end
|
31
|
+
# retry_count +=1
|
32
|
+
# Mechanize::HTTP::Agent.http.shutdown
|
33
|
+
# retry
|
34
|
+
# end
|
35
|
+
# end
|
36
|
+
|
37
|
+
def you_convert
|
38
|
+
begin
|
39
|
+
send_files(@link_arr)
|
40
|
+
rescue StandardError
|
41
|
+
false
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
def grab_links(word=nil)
|
46
|
+
gather(word)
|
47
|
+
end
|
48
|
+
|
49
|
+
def show
|
50
|
+
arr = []
|
51
|
+
@link_arr.each do |link|
|
52
|
+
REPLACE.each do |r|
|
53
|
+
link.text.gsub!(r[0], r[1])
|
54
|
+
end
|
55
|
+
arr << link
|
56
|
+
end
|
57
|
+
arr
|
58
|
+
end
|
59
|
+
|
60
|
+
def links
|
61
|
+
@link_arr
|
62
|
+
end
|
63
|
+
|
64
|
+
|
65
|
+
|
66
|
+
|
67
|
+
|
68
|
+
|
69
|
+
|
70
|
+
private
|
71
|
+
|
72
|
+
def noko(path)
|
73
|
+
Nokogiri::HTML(path)
|
74
|
+
end
|
75
|
+
|
76
|
+
def mec_get(path)
|
77
|
+
Mechanize.new.get(path)
|
78
|
+
end
|
79
|
+
|
80
|
+
# returns itself
|
81
|
+
def gather(word)
|
82
|
+
@link_arr = []
|
83
|
+
path = mec_get(@search_path)
|
84
|
+
count = 0
|
85
|
+
|
86
|
+
if word.nil?
|
87
|
+
|
88
|
+
path.links.each do |link|
|
89
|
+
break if count > @max_downloads
|
90
|
+
youtube = link.click.uri.to_s
|
91
|
+
|
92
|
+
# next if link.text.include?('Play')
|
93
|
+
|
94
|
+
if youtube.include?('watch?v=')
|
95
|
+
@link_arr << link
|
96
|
+
count += 1
|
97
|
+
end
|
98
|
+
end
|
99
|
+
|
100
|
+
else
|
101
|
+
|
102
|
+
path.links_with(:text => /#{word}/).each do |link|
|
103
|
+
|
104
|
+
break if count > @max_downloads
|
105
|
+
|
106
|
+
# next if link.text.include?('Play')
|
107
|
+
|
108
|
+
if link.text.include?(word) && link.click.uri.to_s.include?('watch?v=')
|
109
|
+
@link_arr << link
|
110
|
+
count += 1
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
114
|
+
self
|
115
|
+
end
|
116
|
+
|
117
|
+
# requires an array
|
118
|
+
def send_files(links)
|
119
|
+
you_convert = 'http://www.youtubeinmp4.com/'
|
120
|
+
links.each_with_index do |link, i|
|
121
|
+
clicked_link = link.click.uri.to_s
|
122
|
+
form = mec_get(you_convert).forms[0]
|
123
|
+
next if link.nil?
|
124
|
+
puts "printing link #{i}"
|
125
|
+
form.field_with(:class => 'c3').value = clicked_link
|
126
|
+
path = "#{@save_destination}/#{i}.mp4"
|
127
|
+
form.submit.links[1].click.save_as(path)
|
128
|
+
puts "link #{1} successful"
|
129
|
+
end
|
130
|
+
end
|
131
|
+
end
|
132
|
+
end
|
@@ -0,0 +1,50 @@
|
|
1
|
+
# this file tests many different types of youtube urls and playlists
|
2
|
+
require 'spec_helper'
|
3
|
+
|
4
|
+
describe 'Playlist' do
|
5
|
+
before do
|
6
|
+
@temples = 'https://www.youtube.com/watch?v=mLPvEfB8F2I&list=UU3I2GFN_F8WudD_2jUZbojA'
|
7
|
+
@of_monsters = 'https://www.youtube.com/watch?v=8Dw8qdmT_aY&list=TLF8Mb1J2-C51c-0bwT31CLxHjPDNIDemE'
|
8
|
+
@shovels_rope = 'https://www.youtube.com/watch?v=SFzWiUeooEY&list=PLB88CA03885F74F2B'
|
9
|
+
@save_to = '/Users/mzakany/Desktop/folder'
|
10
|
+
end
|
11
|
+
|
12
|
+
context 'Grab the links with no parameters' do
|
13
|
+
|
14
|
+
it 'should get temples' do
|
15
|
+
# theres a ton of links so I commented out
|
16
|
+
found_links = BulkYoutube::Scrape.new(@temples, @save_to)
|
17
|
+
# found_links.grab_links.count
|
18
|
+
end
|
19
|
+
|
20
|
+
it 'should get of_monsters' do
|
21
|
+
found_links = BulkYoutube::Scrape.new(@of_monsters,@save_to)
|
22
|
+
# found_links.grab_links.count
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
context 'Grab the links with word search' do
|
27
|
+
it 'should get Monsters' do
|
28
|
+
found_links = BulkYoutube::Scrape.new(@of_monsters,@save_to)
|
29
|
+
# found_links.grab_links('Monsters').show
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
context 'Send files to folder' do
|
34
|
+
before do
|
35
|
+
@run = BulkYoutube::Scrape.new(@of_monsters, @save_to)
|
36
|
+
end
|
37
|
+
|
38
|
+
it 'should send no parameter to folder' do
|
39
|
+
# links = @run.grab_links.links
|
40
|
+
# @run.you_convert(links)
|
41
|
+
end
|
42
|
+
|
43
|
+
it 'should send with word search to folder' do
|
44
|
+
# links = @run.grab_links('Monsters')
|
45
|
+
# @run.you_convert(links)
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
|
50
|
+
end
|
@@ -0,0 +1,47 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
|
4
|
+
describe 'Full Page Playlist' do
|
5
|
+
before do
|
6
|
+
@EEVlog = 'https://www.youtube.com/playlist?list=PL55857F4F6F2D36B1'
|
7
|
+
@french = 'https://www.youtube.com/playlist?list=PLV1-QgpUU7N2TVWS6gEVMqEfAFjAl-DV6'
|
8
|
+
@save_to = '/Users/mzakany/Desktop/folder'
|
9
|
+
|
10
|
+
@found = BulkYoutube::Scrape.new(@EEVlog, @save_to)
|
11
|
+
@found_french = BulkYoutube::Scrape.new(@french, @save_to)
|
12
|
+
end
|
13
|
+
|
14
|
+
context 'Grab Links with no parameters' do
|
15
|
+
it 'should get eevlog links' do
|
16
|
+
# @found.grab_links.class
|
17
|
+
# expect(@found_french.grab_links).to be_an_instance_of Array
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
context 'Grab with word search' do
|
22
|
+
it 'should get with word search ' do
|
23
|
+
# expect(@found.grab_links('EEVblog')).to be_an_instance_of Array
|
24
|
+
# @found_french.grab_links('French').show
|
25
|
+
end
|
26
|
+
|
27
|
+
it 'should grab this page' do
|
28
|
+
path = 'https://www.youtube.com/watch?v=z5pJvhd3lFQ'
|
29
|
+
save = '/Users/mzakany/Desktop/folder'
|
30
|
+
found = BulkYoutube::Scrape.new(path,save)
|
31
|
+
puts found.grab_links.show
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
context 'Send to folder' do
|
36
|
+
|
37
|
+
before do
|
38
|
+
@run_french = BulkYoutube::Scrape.new(@french, @save_to)
|
39
|
+
end
|
40
|
+
|
41
|
+
it 'should do no parameters' do
|
42
|
+
# @run_french.grab_links('French').you_convert
|
43
|
+
end
|
44
|
+
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,11 @@
|
|
1
|
+
require 'bulk_youtube'
|
2
|
+
require 'bulk_youtube/globals'
|
3
|
+
|
4
|
+
RSpec.configure do |config|
|
5
|
+
config.expect_with :rspec do |expectations|
|
6
|
+
expectations.include_chain_clauses_in_custom_matcher_descriptions = true
|
7
|
+
end
|
8
|
+
config.mock_with :rspec do |mocks|
|
9
|
+
mocks.verify_partial_doubles = true
|
10
|
+
end
|
11
|
+
end
|
metadata
ADDED
@@ -0,0 +1,143 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: bulk_youtube
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Michael C. Zakany
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2014-10-15 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: nokogiri
|
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: mechanize
|
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: bundler
|
48
|
+
requirement: !ruby/object:Gem::Requirement
|
49
|
+
none: false
|
50
|
+
requirements:
|
51
|
+
- - ~>
|
52
|
+
- !ruby/object:Gem::Version
|
53
|
+
version: '1.3'
|
54
|
+
type: :development
|
55
|
+
prerelease: false
|
56
|
+
version_requirements: !ruby/object:Gem::Requirement
|
57
|
+
none: false
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '1.3'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: rake
|
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: rspec
|
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: Download batches of youtube videos
|
95
|
+
email:
|
96
|
+
- mzakany@gmail.com
|
97
|
+
executables: []
|
98
|
+
extensions: []
|
99
|
+
extra_rdoc_files: []
|
100
|
+
files:
|
101
|
+
- .gitignore
|
102
|
+
- .rspec
|
103
|
+
- Gemfile
|
104
|
+
- LICENSE.txt
|
105
|
+
- README.md
|
106
|
+
- Rakefile
|
107
|
+
- bulk_youtube.gemspec
|
108
|
+
- lib/bulk_youtube.rb
|
109
|
+
- lib/bulk_youtube/globals.rb
|
110
|
+
- lib/bulk_youtube/version.rb
|
111
|
+
- spec/embedded_playlists_spec.rb
|
112
|
+
- spec/full_page_playlist_spec.rb
|
113
|
+
- spec/spec_helper.rb
|
114
|
+
homepage: ''
|
115
|
+
licenses:
|
116
|
+
- MIT
|
117
|
+
post_install_message:
|
118
|
+
rdoc_options: []
|
119
|
+
require_paths:
|
120
|
+
- lib
|
121
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
122
|
+
none: false
|
123
|
+
requirements:
|
124
|
+
- - ! '>='
|
125
|
+
- !ruby/object:Gem::Version
|
126
|
+
version: '0'
|
127
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
128
|
+
none: false
|
129
|
+
requirements:
|
130
|
+
- - ! '>='
|
131
|
+
- !ruby/object:Gem::Version
|
132
|
+
version: '0'
|
133
|
+
requirements: []
|
134
|
+
rubyforge_project:
|
135
|
+
rubygems_version: 1.8.23
|
136
|
+
signing_key:
|
137
|
+
specification_version: 3
|
138
|
+
summary: Download Batches of youtube videos
|
139
|
+
test_files:
|
140
|
+
- spec/embedded_playlists_spec.rb
|
141
|
+
- spec/full_page_playlist_spec.rb
|
142
|
+
- spec/spec_helper.rb
|
143
|
+
has_rdoc:
|