hlspider 0.1.0 → 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +5 -2
- data/lib/hlspider/playlist.rb +6 -24
- data/lib/hlspider/spider.rb +58 -26
- data/lib/hlspider/version.rb +1 -1
- data/lib/hlspider.rb +1 -1
- metadata +50 -56
data/README.md
CHANGED
@@ -3,7 +3,10 @@ HLSpider
|
|
3
3
|
ASYNC .m3u8 downloader. Downloads .m3u8 playlist files and confirms their segments are properly aligned.
|
4
4
|
|
5
5
|
Usage
|
6
|
-
-----
|
6
|
+
-----
|
7
|
+
hlspider crawl --playlists=http://site.tld/playlist1.m3u8 http://site.tld/playlist2.m3u8 http://site.tld/playlist3.m3u8
|
8
|
+
|
9
|
+
|
7
10
|
hlspider
|
8
11
|
|
9
12
|
Tasks:
|
@@ -17,7 +20,7 @@ Usage
|
|
17
20
|
Options:
|
18
21
|
--playlists=one two three
|
19
22
|
[--sleep=N] # Default: 5
|
20
|
-
[--log=LOG] #
|
23
|
+
[--log=LOG] # Disabled by default - Log provides some extra debug information
|
21
24
|
|
22
25
|
|
23
26
|
|
data/lib/hlspider/playlist.rb
CHANGED
@@ -1,27 +1,12 @@
|
|
1
1
|
module HLSpider
|
2
2
|
class Playlist
|
3
|
-
attr_accessor :file
|
3
|
+
attr_accessor :file, :source
|
4
4
|
attr_reader :playlists, :segments
|
5
5
|
|
6
|
-
def
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
playlists << {:title => f[:title], :playlist => playlist} if playlist.valid?
|
11
|
-
end
|
12
|
-
|
13
|
-
segments = []
|
14
|
-
playlists.each do |p|
|
15
|
-
segment = /(\d*.ts)/.match(p[:playlist].segments.first)[0].gsub(".ts", "")
|
16
|
-
segments << segment
|
17
|
-
end
|
18
|
-
|
19
|
-
return segments
|
20
|
-
end
|
21
|
-
|
22
|
-
def initialize(file)
|
23
|
-
@file = file
|
24
|
-
|
6
|
+
def initialize(file, source = '')
|
7
|
+
@file = file
|
8
|
+
@source = source
|
9
|
+
|
25
10
|
@valid = false
|
26
11
|
@variable_playlist = false
|
27
12
|
@segment_playlist = false
|
@@ -49,11 +34,8 @@ module HLSpider
|
|
49
34
|
end
|
50
35
|
|
51
36
|
private
|
52
|
-
include Line
|
53
|
-
|
54
37
|
def parse
|
55
38
|
@valid = true if /#EXTM3U/.match(@file)
|
56
|
-
|
57
39
|
if has_playlist?(@file) && !has_segment?(@file)
|
58
40
|
@variable_playlist = true
|
59
41
|
@file.each_line do |line|
|
@@ -70,7 +52,7 @@ module HLSpider
|
|
70
52
|
end
|
71
53
|
|
72
54
|
def has_segment?(str)
|
73
|
-
true if /.
|
55
|
+
true if /#EXT-X-MEDIA-SEQUENCE/.match(str)
|
74
56
|
end
|
75
57
|
|
76
58
|
def has_playlist?(str)
|
data/lib/hlspider/spider.rb
CHANGED
@@ -1,6 +1,8 @@
|
|
1
|
+
require 'rubygems'
|
1
2
|
require 'em-synchrony'
|
2
3
|
require 'em-synchrony/em-http'
|
3
4
|
require 'logger'
|
5
|
+
require_relative 'playlist'
|
4
6
|
|
5
7
|
module HLSpider
|
6
8
|
class Spider
|
@@ -10,43 +12,73 @@ module HLSpider
|
|
10
12
|
end
|
11
13
|
|
12
14
|
def crawl
|
15
|
+
playlists = dive(@playlists)
|
16
|
+
|
17
|
+
segments = []
|
18
|
+
playlists.each { |p| segments << p.segments.first }
|
19
|
+
|
20
|
+
puts Time.now
|
21
|
+
put_and_log "--- #{segments.inspect} ---"
|
22
|
+
segments.uniq!
|
23
|
+
|
24
|
+
if segments.size > 1 && ((segments[0].to_i - segments[1].to_i).abs > 1)
|
25
|
+
p "Segments are off - #{@time}"
|
26
|
+
log "**********"
|
27
|
+
log segments.inspect
|
28
|
+
log "**********"
|
29
|
+
elsif segments.size == 1
|
30
|
+
p "All Good. at #{segments[0]}"
|
31
|
+
log "^^^^^^^^^^^"
|
32
|
+
log segments.inspect
|
33
|
+
log "^^^^^^^^^^^"
|
34
|
+
else
|
35
|
+
p "No segements found - #{@time}"
|
36
|
+
log "~~~~~~~~~~~"
|
37
|
+
log "No segments!"
|
38
|
+
log "~~~~~~~~~~~"
|
39
|
+
end
|
40
|
+
end
|
41
|
+
|
42
|
+
private
|
43
|
+
|
44
|
+
def async_download(urls = [])
|
45
|
+
res = nil
|
46
|
+
|
13
47
|
EM.synchrony do
|
14
48
|
multi = EventMachine::Synchrony::Multi.new
|
15
|
-
|
49
|
+
|
50
|
+
urls.each_with_index do |p,i|
|
16
51
|
log p
|
17
|
-
puts "Downloading: #{p}"
|
18
52
|
multi.add :"#{i}", EventMachine::HttpRequest.new(p).aget
|
19
53
|
@time = Time.now
|
20
54
|
end
|
21
|
-
|
55
|
+
|
22
56
|
res = multi.perform
|
57
|
+
|
58
|
+
EventMachine.stop
|
59
|
+
end
|
23
60
|
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
61
|
+
return res
|
62
|
+
end
|
63
|
+
|
64
|
+
def dive(urls = [])
|
65
|
+
playlists = []
|
66
|
+
|
67
|
+
res = async_download(urls)
|
68
|
+
res.requests.each do |req|
|
69
|
+
p = Playlist.new(req.response, req.req.uri.to_s)
|
32
70
|
|
33
|
-
if
|
34
|
-
p
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
p "All Good. at #{segments[0]}"
|
40
|
-
log "^^^^^^^^^^^"
|
41
|
-
log segments.inspect
|
42
|
-
log "^^^^^^^^^^^"
|
71
|
+
if p.valid?
|
72
|
+
if p.variable_playlist?
|
73
|
+
playlists = dive(p.playlists)
|
74
|
+
else
|
75
|
+
playlists << p
|
76
|
+
end
|
43
77
|
end
|
44
|
-
|
45
|
-
EventMachine.stop
|
46
78
|
end
|
47
|
-
|
48
|
-
|
49
|
-
|
79
|
+
|
80
|
+
return playlists
|
81
|
+
end
|
50
82
|
|
51
83
|
def log(str)
|
52
84
|
#eval "@log.#{type} \"#{str}\"" if @log
|
data/lib/hlspider/version.rb
CHANGED
data/lib/hlspider.rb
CHANGED
metadata
CHANGED
@@ -1,72 +1,70 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: hlspider
|
3
|
-
version: !ruby/object:Gem::Version
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.2
|
4
5
|
prerelease:
|
5
|
-
version: 0.1.0
|
6
6
|
platform: ruby
|
7
|
-
authors:
|
7
|
+
authors:
|
8
8
|
- Brooke McKim
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
|
13
|
-
date: 2011-05-27 00:00:00 -04:00
|
12
|
+
date: 2011-08-18 00:00:00.000000000 -04:00
|
14
13
|
default_executable:
|
15
|
-
dependencies:
|
16
|
-
- !ruby/object:Gem::Dependency
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
17
16
|
name: thor
|
18
|
-
|
19
|
-
requirement: &id001 !ruby/object:Gem::Requirement
|
17
|
+
requirement: &2152994560 !ruby/object:Gem::Requirement
|
20
18
|
none: false
|
21
|
-
requirements:
|
22
|
-
- -
|
23
|
-
- !ruby/object:Gem::Version
|
19
|
+
requirements:
|
20
|
+
- - ! '>='
|
21
|
+
- !ruby/object:Gem::Version
|
24
22
|
version: 0.14.0
|
25
23
|
type: :runtime
|
26
|
-
version_requirements: *id001
|
27
|
-
- !ruby/object:Gem::Dependency
|
28
|
-
name: em-synchrony
|
29
24
|
prerelease: false
|
30
|
-
|
25
|
+
version_requirements: *2152994560
|
26
|
+
- !ruby/object:Gem::Dependency
|
27
|
+
name: em-synchrony
|
28
|
+
requirement: &2152993020 !ruby/object:Gem::Requirement
|
31
29
|
none: false
|
32
|
-
requirements:
|
33
|
-
- -
|
34
|
-
- !ruby/object:Gem::Version
|
30
|
+
requirements:
|
31
|
+
- - ! '>='
|
32
|
+
- !ruby/object:Gem::Version
|
35
33
|
version: 0.3.0.beta.1
|
36
34
|
type: :runtime
|
37
|
-
version_requirements: *id002
|
38
|
-
- !ruby/object:Gem::Dependency
|
39
|
-
name: eventmachine
|
40
35
|
prerelease: false
|
41
|
-
|
36
|
+
version_requirements: *2152993020
|
37
|
+
- !ruby/object:Gem::Dependency
|
38
|
+
name: eventmachine
|
39
|
+
requirement: &2152983760 !ruby/object:Gem::Requirement
|
42
40
|
none: false
|
43
|
-
requirements:
|
44
|
-
- -
|
45
|
-
- !ruby/object:Gem::Version
|
41
|
+
requirements:
|
42
|
+
- - ! '>='
|
43
|
+
- !ruby/object:Gem::Version
|
46
44
|
version: 1.0.0.beta.3
|
47
45
|
type: :runtime
|
48
|
-
version_requirements: *id003
|
49
|
-
- !ruby/object:Gem::Dependency
|
50
|
-
name: em-http-request
|
51
46
|
prerelease: false
|
52
|
-
|
47
|
+
version_requirements: *2152983760
|
48
|
+
- !ruby/object:Gem::Dependency
|
49
|
+
name: em-http-request
|
50
|
+
requirement: &2152981200 !ruby/object:Gem::Requirement
|
53
51
|
none: false
|
54
|
-
requirements:
|
55
|
-
- -
|
56
|
-
- !ruby/object:Gem::Version
|
52
|
+
requirements:
|
53
|
+
- - ! '>='
|
54
|
+
- !ruby/object:Gem::Version
|
57
55
|
version: 1.0.0.beta.3
|
58
56
|
type: :runtime
|
59
|
-
|
60
|
-
|
61
|
-
|
57
|
+
prerelease: false
|
58
|
+
version_requirements: *2152981200
|
59
|
+
description: Downloads .m3u8 playlist files and confirms their segments are properly
|
60
|
+
aligned.
|
61
|
+
email:
|
62
62
|
- bmckim@telvue.com
|
63
|
-
executables:
|
63
|
+
executables:
|
64
64
|
- hlspider
|
65
65
|
extensions: []
|
66
|
-
|
67
66
|
extra_rdoc_files: []
|
68
|
-
|
69
|
-
files:
|
67
|
+
files:
|
70
68
|
- .gitignore
|
71
69
|
- Gemfile
|
72
70
|
- README.md
|
@@ -81,30 +79,26 @@ files:
|
|
81
79
|
has_rdoc: true
|
82
80
|
homepage: http://github.com/telvue/hlspider
|
83
81
|
licenses: []
|
84
|
-
|
85
82
|
post_install_message:
|
86
83
|
rdoc_options: []
|
87
|
-
|
88
|
-
require_paths:
|
84
|
+
require_paths:
|
89
85
|
- lib
|
90
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
86
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
91
87
|
none: false
|
92
|
-
requirements:
|
93
|
-
- -
|
94
|
-
- !ruby/object:Gem::Version
|
95
|
-
version:
|
96
|
-
required_rubygems_version: !ruby/object:Gem::Requirement
|
88
|
+
requirements:
|
89
|
+
- - ! '>='
|
90
|
+
- !ruby/object:Gem::Version
|
91
|
+
version: '0'
|
92
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
97
93
|
none: false
|
98
|
-
requirements:
|
99
|
-
- -
|
100
|
-
- !ruby/object:Gem::Version
|
101
|
-
version:
|
94
|
+
requirements:
|
95
|
+
- - ! '>='
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '0'
|
102
98
|
requirements: []
|
103
|
-
|
104
99
|
rubyforge_project: hlspider
|
105
100
|
rubygems_version: 1.6.2
|
106
101
|
signing_key:
|
107
102
|
specification_version: 3
|
108
103
|
summary: ASYNC .m3u8 downloader
|
109
104
|
test_files: []
|
110
|
-
|