logstash-input-multirss 0.1.1 → 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/lib/logstash/inputs/multirss.rb +54 -62
- data/logstash-input-multirss.gemspec +1 -1
- metadata +19 -21
- data/lib/logstash/inputs/multirss.rb.bk +0 -51
- data/lib/logstash/inputs/multirss.rb.bk2 +0 -117
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: cad07458c379cfcd9f3a7cbb9608f693a33efe5dfee0a2087387df491c135218
|
4
|
+
data.tar.gz: a5956c590a9e0d9667b278de7f690d3a55ce9eaf886919f2b355c9e12fff8675
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6611bda686c887dbaebba928718cd6521e4c2076e0c44feabdd1e13e89aef3aeb6a80cf8861dfba40b8b9a442f381262bc72023e6d3b3a14c86b94aadf3611ea
|
7
|
+
data.tar.gz: d73bfa18ec57247ff7b566f94e2d6e6a9e710bd09b5b5563034bb9cc74c46ddc2bc5c9f8e13f268ceb259913195922388f3efe2f0c952689e88cee932cb6a453
|
@@ -6,6 +6,7 @@ require "net/http"
|
|
6
6
|
require "uri"
|
7
7
|
require "mechanize"
|
8
8
|
require "rss"
|
9
|
+
require "nokogiri"
|
9
10
|
|
10
11
|
class LogStash::Inputs::Multirss < LogStash::Inputs::Base
|
11
12
|
config_name "multirss"
|
@@ -13,7 +14,10 @@ class LogStash::Inputs::Multirss < LogStash::Inputs::Base
|
|
13
14
|
default :codec, "plain"
|
14
15
|
|
15
16
|
# The rss array list to use in the pipe
|
16
|
-
config :
|
17
|
+
config :multi_feed, :validate => :array, :required => true
|
18
|
+
|
19
|
+
# The rss array list to use in the pipe
|
20
|
+
config :one_feed, :validate => :array, :default => []
|
17
21
|
|
18
22
|
#Set de interval for stoppable_sleep
|
19
23
|
config :interval, :validate => :number, :default => 200
|
@@ -24,9 +28,8 @@ class LogStash::Inputs::Multirss < LogStash::Inputs::Base
|
|
24
28
|
public
|
25
29
|
def register
|
26
30
|
@urls = []
|
27
|
-
@list_rss = @rss_list
|
28
31
|
@agent = Mechanize.new
|
29
|
-
|
32
|
+
@agent.agent.http.verify_mode = OpenSSL::SSL::VERIFY_NONE
|
30
33
|
end # def register
|
31
34
|
|
32
35
|
|
@@ -34,104 +37,93 @@ class LogStash::Inputs::Multirss < LogStash::Inputs::Base
|
|
34
37
|
# we can abort the loop if stop? becomes true
|
35
38
|
while !stop?
|
36
39
|
|
37
|
-
@
|
38
|
-
|
39
|
-
puts "Read parent: " + @actual_rss
|
40
|
+
@multi_feed.each do |rss|
|
41
|
+
puts "Read parent: " + rss
|
40
42
|
begin
|
41
|
-
page = @agent.get(
|
43
|
+
page = @agent.get(rss)
|
42
44
|
page.links.each do |link|
|
43
45
|
if link.href.chars.last(3).join == "xml" && not_include_blacklist(link)
|
44
46
|
@urls << link.href
|
45
47
|
end
|
46
48
|
end
|
47
49
|
rescue
|
48
|
-
puts "Fail to get " +
|
50
|
+
puts "Fail to get " + rss + " feed"
|
49
51
|
end
|
50
52
|
|
51
53
|
links = @urls.uniq
|
52
|
-
|
53
54
|
links.each do |link|
|
54
55
|
begin
|
55
|
-
|
56
|
-
response = @agente.get(link)
|
57
|
-
@agente.agent.http.verify_mode = OpenSSL::SSL::VERIFY_NONE
|
58
|
-
handle_response(response, queue)
|
56
|
+
response_link(link,queue)
|
59
57
|
puts "Read clidren: " + link
|
60
58
|
rescue
|
61
59
|
puts "Fail to get " + link
|
60
|
+
next
|
62
61
|
end
|
63
62
|
end
|
64
|
-
|
65
63
|
@urls.clear
|
66
64
|
|
67
65
|
end
|
68
66
|
|
67
|
+
@one_feed.each do |feed|
|
68
|
+
@urls << feed
|
69
|
+
end
|
70
|
+
links_o = @urls.uniq
|
71
|
+
links_o.each do |link|
|
72
|
+
begin
|
73
|
+
response_link(link,queue)
|
74
|
+
puts "Read clidren: " + link
|
75
|
+
rescue
|
76
|
+
puts "Fail to get " + link
|
77
|
+
next
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
@urls.clear
|
82
|
+
|
69
83
|
Stud.stoppable_sleep(@interval) { stop? }
|
70
84
|
end # loop
|
71
85
|
end # def run
|
72
86
|
|
73
87
|
|
74
88
|
def stop
|
75
|
-
|
76
|
-
# examples of common "stop" tasks:
|
77
|
-
# * close sockets (unblocking blocking reads/accets)
|
78
|
-
# * cleanup temporary files
|
79
|
-
# * terminate spawned threads
|
89
|
+
|
80
90
|
end
|
81
91
|
|
82
|
-
|
83
|
-
for i in 0..@blacklist.length-1
|
84
|
-
if link.href.include?(@blacklist[i])
|
85
|
-
return false
|
86
|
-
end
|
87
|
-
end
|
88
|
-
return true
|
89
|
-
end
|
90
|
-
|
91
|
-
|
92
|
-
def handle_response(response, queue)
|
93
|
-
body = response.body
|
92
|
+
def response_link(link, queue)
|
94
93
|
begin
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
puts "item have a enclosure field"
|
99
|
-
next
|
100
|
-
else
|
101
|
-
handle_rss_response(queue, item)
|
102
|
-
end
|
94
|
+
page = Nokogiri::XML(open(link))
|
95
|
+
page.search('item').each do |item|
|
96
|
+
link_rss_response(queue, item)
|
103
97
|
end
|
104
|
-
rescue RSS::MissingTagError => e
|
105
|
-
next
|
106
|
-
@logger.error("Invalid RSS feed", :exception => e)
|
107
|
-
rescue RSS::TooMuchTagError => ex
|
108
|
-
next
|
109
|
-
@logger.error("TooMuchTagError feed (have enclosure tag)", :exception => ex)
|
110
98
|
rescue => exc
|
111
|
-
|
99
|
+
puts "ERROR"
|
112
100
|
@logger.error("Uknown error while parsing the feed", :exception => exc)
|
113
101
|
end
|
114
102
|
end
|
115
103
|
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
|
121
|
-
event.
|
122
|
-
|
123
|
-
|
124
|
-
|
125
|
-
queue << event
|
104
|
+
def link_rss_response(queue, item)
|
105
|
+
event = LogStash::Event.new()
|
106
|
+
item.element_children.each do |x|
|
107
|
+
if x.inner_html.to_s.chars.first(9).join == "<![CDATA["
|
108
|
+
eve = LogStash::Event.new( x.name => x.inner_html.to_s[9..x.inner_html.to_s.length-4])
|
109
|
+
event.append( eve )
|
110
|
+
else
|
111
|
+
eve = LogStash::Event.new( x.name => x.inner_html.to_s )
|
112
|
+
event.append( eve )
|
126
113
|
end
|
114
|
+
end
|
115
|
+
decorate(event)
|
116
|
+
queue << event
|
127
117
|
end
|
128
118
|
|
129
|
-
def
|
130
|
-
|
119
|
+
def not_include_blacklist(link)
|
120
|
+
for i in 0..@blacklist.length-1
|
121
|
+
if link.href.include?(@blacklist[i])
|
122
|
+
return false
|
123
|
+
end
|
124
|
+
end
|
131
125
|
return true
|
132
|
-
|
133
|
-
|
134
|
-
end
|
135
|
-
end
|
126
|
+
end
|
127
|
+
|
136
128
|
|
137
129
|
end # class LogStash::Inputs::Crawler
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Gem::Specification.new do |s|
|
2
2
|
s.name = 'logstash-input-multirss'
|
3
|
-
s.version = '0.
|
3
|
+
s.version = '1.0.0'
|
4
4
|
s.licenses = ['Apache-2.0']
|
5
5
|
s.summary = 'Simple multi rss plugin'
|
6
6
|
s.description = 'This plugin needs a list of links of different rss. Get all the links of the main feed pages and get all the content of each of the links.'
|
metadata
CHANGED
@@ -1,94 +1,94 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: logstash-input-multirss
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 1.0.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Felix R G
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2018-08-
|
11
|
+
date: 2018-08-14 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
|
-
name: logstash-core
|
15
14
|
requirement: !ruby/object:Gem::Requirement
|
16
15
|
requirements:
|
17
16
|
- - ">="
|
18
17
|
- !ruby/object:Gem::Version
|
19
18
|
version: '0'
|
20
|
-
|
19
|
+
name: logstash-core
|
21
20
|
prerelease: false
|
21
|
+
type: :runtime
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
26
|
version: '0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
|
-
name: logstash-codec-plain
|
29
28
|
requirement: !ruby/object:Gem::Requirement
|
30
29
|
requirements:
|
31
30
|
- - ">="
|
32
31
|
- !ruby/object:Gem::Version
|
33
32
|
version: '0'
|
34
|
-
|
33
|
+
name: logstash-codec-plain
|
35
34
|
prerelease: false
|
35
|
+
type: :runtime
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
38
|
- - ">="
|
39
39
|
- !ruby/object:Gem::Version
|
40
40
|
version: '0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
|
-
name: stud
|
43
42
|
requirement: !ruby/object:Gem::Requirement
|
44
43
|
requirements:
|
45
44
|
- - ">="
|
46
45
|
- !ruby/object:Gem::Version
|
47
46
|
version: 0.0.22
|
48
|
-
|
47
|
+
name: stud
|
49
48
|
prerelease: false
|
49
|
+
type: :runtime
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
52
|
- - ">="
|
53
53
|
- !ruby/object:Gem::Version
|
54
54
|
version: 0.0.22
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
|
-
name: logstash-devutils
|
57
56
|
requirement: !ruby/object:Gem::Requirement
|
58
57
|
requirements:
|
59
58
|
- - ">="
|
60
59
|
- !ruby/object:Gem::Version
|
61
60
|
version: 0.0.16
|
62
|
-
|
61
|
+
name: logstash-devutils
|
63
62
|
prerelease: false
|
63
|
+
type: :development
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
66
|
- - ">="
|
67
67
|
- !ruby/object:Gem::Version
|
68
68
|
version: 0.0.16
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
|
-
name: mechanize
|
71
70
|
requirement: !ruby/object:Gem::Requirement
|
72
71
|
requirements:
|
73
72
|
- - ">="
|
74
73
|
- !ruby/object:Gem::Version
|
75
74
|
version: '0'
|
76
|
-
|
75
|
+
name: mechanize
|
77
76
|
prerelease: false
|
77
|
+
type: :runtime
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
80
|
- - ">="
|
81
81
|
- !ruby/object:Gem::Version
|
82
82
|
version: '0'
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
|
-
name: nokogiri
|
85
84
|
requirement: !ruby/object:Gem::Requirement
|
86
85
|
requirements:
|
87
86
|
- - ">="
|
88
87
|
- !ruby/object:Gem::Version
|
89
88
|
version: '0'
|
90
|
-
|
89
|
+
name: nokogiri
|
91
90
|
prerelease: false
|
91
|
+
type: :runtime
|
92
92
|
version_requirements: !ruby/object:Gem::Requirement
|
93
93
|
requirements:
|
94
94
|
- - ">="
|
@@ -108,8 +108,6 @@ files:
|
|
108
108
|
- LICENSE
|
109
109
|
- README.md
|
110
110
|
- lib/logstash/inputs/multirss.rb
|
111
|
-
- lib/logstash/inputs/multirss.rb.bk
|
112
|
-
- lib/logstash/inputs/multirss.rb.bk2
|
113
111
|
- logstash-input-multirss.gemspec
|
114
112
|
- spec/inputs/multirss_spec.rb
|
115
113
|
homepage: https://github.com/felixramirezgarcia/logstash-input-multirss
|
@@ -118,7 +116,7 @@ licenses:
|
|
118
116
|
metadata:
|
119
117
|
logstash_plugin: 'true'
|
120
118
|
logstash_group: input
|
121
|
-
post_install_message:
|
119
|
+
post_install_message:
|
122
120
|
rdoc_options: []
|
123
121
|
require_paths:
|
124
122
|
- lib
|
@@ -133,9 +131,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
133
131
|
- !ruby/object:Gem::Version
|
134
132
|
version: '0'
|
135
133
|
requirements: []
|
136
|
-
rubyforge_project:
|
137
|
-
rubygems_version: 2.
|
138
|
-
signing_key:
|
134
|
+
rubyforge_project:
|
135
|
+
rubygems_version: 2.6.13
|
136
|
+
signing_key:
|
139
137
|
specification_version: 4
|
140
138
|
summary: Simple multi rss plugin
|
141
139
|
test_files:
|
@@ -1,51 +0,0 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
require "logstash/inputs/base"
|
3
|
-
require "logstash/namespace"
|
4
|
-
require "stud/interval"
|
5
|
-
require "socket" # for Socket.gethostname
|
6
|
-
|
7
|
-
# Generate a repeating message.
|
8
|
-
#
|
9
|
-
# This plugin is intented only as an example.
|
10
|
-
|
11
|
-
class LogStash::Inputs::Multirss < LogStash::Inputs::Base
|
12
|
-
config_name "multirss"
|
13
|
-
|
14
|
-
# If undefined, Logstash will complain, even if codec is unused.
|
15
|
-
default :codec, "plain"
|
16
|
-
|
17
|
-
# The message string to use in the event.
|
18
|
-
config :message, :validate => :string, :default => "Hello World!"
|
19
|
-
|
20
|
-
# Set how frequently messages should be sent.
|
21
|
-
#
|
22
|
-
# The default, `1`, means send a message every second.
|
23
|
-
config :interval, :validate => :number, :default => 1
|
24
|
-
|
25
|
-
public
|
26
|
-
def register
|
27
|
-
@host = Socket.gethostname
|
28
|
-
end # def register
|
29
|
-
|
30
|
-
def run(queue)
|
31
|
-
# we can abort the loop if stop? becomes true
|
32
|
-
while !stop?
|
33
|
-
event = LogStash::Event.new("message" => @message, "host" => @host)
|
34
|
-
decorate(event)
|
35
|
-
queue << event
|
36
|
-
# because the sleep interval can be big, when shutdown happens
|
37
|
-
# we want to be able to abort the sleep
|
38
|
-
# Stud.stoppable_sleep will frequently evaluate the given block
|
39
|
-
# and abort the sleep(@interval) if the return value is true
|
40
|
-
Stud.stoppable_sleep(@interval) { stop? }
|
41
|
-
end # loop
|
42
|
-
end # def run
|
43
|
-
|
44
|
-
def stop
|
45
|
-
# nothing to do in this case so it is not necessary to define stop
|
46
|
-
# examples of common "stop" tasks:
|
47
|
-
# * close sockets (unblocking blocking reads/accepts)
|
48
|
-
# * cleanup temporary files
|
49
|
-
# * terminate spawned threads
|
50
|
-
end
|
51
|
-
end # class LogStash::Inputs::Multirss
|
@@ -1,117 +0,0 @@
|
|
1
|
-
# encoding: utf-8
|
2
|
-
require "logstash/inputs/base"
|
3
|
-
require "logstash/namespace"
|
4
|
-
require "stud/interval"
|
5
|
-
require "net/http"
|
6
|
-
require "uri"
|
7
|
-
require "mechanize"
|
8
|
-
require "faraday"
|
9
|
-
require "rss"
|
10
|
-
|
11
|
-
class LogStash::Inputs::Crawler < LogStash::Inputs::Base
|
12
|
-
config_name "multirss"
|
13
|
-
|
14
|
-
# If undefined, Logstash will complain, even if codec is unused.
|
15
|
-
default :codec, "plain"
|
16
|
-
|
17
|
-
# The message string to use in the event.
|
18
|
-
config :urls, :validate => :array, :required => true
|
19
|
-
|
20
|
-
#Set de interval for stoppable_sleep
|
21
|
-
config :interval, :validate => :number, :default => 86400
|
22
|
-
|
23
|
-
#Domains to exclude
|
24
|
-
config :blacklist, :validate => :array , :default => ['http://fusion.google.com/','yahoo.com','live.com','netvibes.com']
|
25
|
-
|
26
|
-
public
|
27
|
-
def register
|
28
|
-
@urls = []
|
29
|
-
puts "**********************************************************"
|
30
|
-
puts "STARTING MULTI-RSS"
|
31
|
-
puts "*******************************************************"
|
32
|
-
@agent = Mechanize.new
|
33
|
-
@agent.agent.http.verify_mode = OpenSSL::SSL::VERIFY_NONE
|
34
|
-
end # def register
|
35
|
-
|
36
|
-
|
37
|
-
def run(queue)
|
38
|
-
# we can abort the loop if stop? becomes true
|
39
|
-
while !stop?
|
40
|
-
puts "********************ENTRA1"
|
41
|
-
@urls.each do |url|
|
42
|
-
page = @agent.get(@url)
|
43
|
-
page.links.each do |link|
|
44
|
-
if link.href.chars.last(3).join == "xml" && valid_link?(link)
|
45
|
-
puts "*******************************************************"
|
46
|
-
puts link.href
|
47
|
-
@new_urls << link.href
|
48
|
-
end
|
49
|
-
end
|
50
|
-
|
51
|
-
links = @new_urls.uniq
|
52
|
-
|
53
|
-
links.each do |link|
|
54
|
-
puts "********************ENTRA2"
|
55
|
-
response = @agent.get(link)
|
56
|
-
handle_response(response, queue)
|
57
|
-
end
|
58
|
-
|
59
|
-
end #urls.each
|
60
|
-
Stud.stoppable_sleep(@interval) { stop? }
|
61
|
-
end # loop
|
62
|
-
end # def run
|
63
|
-
|
64
|
-
|
65
|
-
def stop
|
66
|
-
# nothing to do in this case so it is not necessary to define stop
|
67
|
-
# examples of common "stop" tasks:
|
68
|
-
# * close sockets (unblocking blocking reads/accets)
|
69
|
-
# * cleanup temporary files
|
70
|
-
# * terminate spawned threads
|
71
|
-
end
|
72
|
-
|
73
|
-
def valid_link?(link)
|
74
|
-
puts "********************ENTRA3"
|
75
|
-
@blacklist.each do |black_link|
|
76
|
-
if link.href.include?(black_link)
|
77
|
-
return false
|
78
|
-
end
|
79
|
-
end
|
80
|
-
return true
|
81
|
-
end
|
82
|
-
|
83
|
-
|
84
|
-
def handle_response(response, queue)
|
85
|
-
puts "********************ENTRA4"
|
86
|
-
body = response.body
|
87
|
-
begin
|
88
|
-
feed = RSS::Parser.parse(body)
|
89
|
-
feed.items.each do |item|
|
90
|
-
# Put each item into an event
|
91
|
-
@logger.debug("Item", :item => item.author)
|
92
|
-
handle_rss_response(queue, item)
|
93
|
-
end
|
94
|
-
rescue RSS::MissingTagError => e
|
95
|
-
@logger.error("Invalid RSS feed", :exception => e)
|
96
|
-
rescue => e
|
97
|
-
@logger.error("Uknown error while parsing the feed", :exception => e)
|
98
|
-
end
|
99
|
-
end
|
100
|
-
|
101
|
-
|
102
|
-
def handle_rss_response(queue, item)
|
103
|
-
puts "********************ENTRA5"
|
104
|
-
@codec.decode(item.description) do |event|
|
105
|
-
event.set("Feed", @url)
|
106
|
-
event.set("published", item.pubDate)
|
107
|
-
event.set("title", item.title)
|
108
|
-
event.set("link", item.link)
|
109
|
-
event.set("author", item.author)
|
110
|
-
decorate(event)
|
111
|
-
queue << event
|
112
|
-
end
|
113
|
-
end
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
end # class LogStash::Inputs::Crawler
|