vessel 0.1.1 → 0.2.0
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.
- checksums.yaml +4 -4
- data/README.md +2 -20
- data/lib/vessel/cargo.rb +20 -1
- data/lib/vessel/engine.rb +17 -7
- data/lib/vessel/request.rb +13 -5
- data/lib/vessel/scheduler.rb +19 -5
- data/lib/vessel/version.rb +1 -1
- metadata +7 -7
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 291c528925e5f6990b8223762c00a996cf8435325b52048c1c0338fc873d1a42
|
4
|
+
data.tar.gz: 5c845e2c6b19adea7742bbad3a031fe0ad5f09a3a0f8ceff248970cc2bb74fcb
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 77d65c60e1541c1ab1473b64bd7c451e3d57199fa19885bcf4e182d295321d0cdd36121cc673a9285a7113b482ec9143607d17a4017632d1d6826b5c5ad48b7e
|
7
|
+
data.tar.gz: 2a0e9bbe6de79e9ba6e7afed4d422de6b72639d91b508a921dd4bba2cf0b8e878a3de6846fca87de25e20047594b153efcf70ca3b91d373190bf976605e0bb2d
|
data/README.md
CHANGED
@@ -97,23 +97,5 @@ To be continued
|
|
97
97
|
|
98
98
|
## License
|
99
99
|
|
100
|
-
|
101
|
-
|
102
|
-
Permission is hereby granted, free of charge, to any person obtaining
|
103
|
-
a copy of this software and associated documentation files (the
|
104
|
-
"Software"), to deal in the Software without restriction, including
|
105
|
-
without limitation the rights to use, copy, modify, merge, publish,
|
106
|
-
distribute, sublicense, and/or sell copies of the Software, and to
|
107
|
-
permit persons to whom the Software is furnished to do so, subject to
|
108
|
-
the following conditions:
|
109
|
-
|
110
|
-
The above copyright notice and this permission notice shall be
|
111
|
-
included in all copies or substantial portions of the Software.
|
112
|
-
|
113
|
-
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
114
|
-
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
115
|
-
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
116
|
-
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
117
|
-
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
118
|
-
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
119
|
-
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
100
|
+
The gem is available as open source under the terms of the
|
101
|
+
[MIT License](https://opensource.org/licenses/MIT).
|
data/lib/vessel/cargo.rb
CHANGED
@@ -24,7 +24,7 @@ module Vessel
|
|
24
24
|
end
|
25
25
|
|
26
26
|
def start_urls(*urls)
|
27
|
-
settings[:start_urls] = urls
|
27
|
+
settings[:start_urls] = urls.flatten
|
28
28
|
end
|
29
29
|
|
30
30
|
def delay(value)
|
@@ -35,6 +35,10 @@ module Vessel
|
|
35
35
|
settings[:timeout] = value
|
36
36
|
end
|
37
37
|
|
38
|
+
def headers(value)
|
39
|
+
settings[:headers] = value
|
40
|
+
end
|
41
|
+
|
38
42
|
def threads(min: MIN_THREADS, max: MAX_THREADS)
|
39
43
|
settings[:min_threads] = min
|
40
44
|
settings[:max_threads] = max
|
@@ -44,6 +48,14 @@ module Vessel
|
|
44
48
|
settings[:middleware] = classes
|
45
49
|
end
|
46
50
|
|
51
|
+
def ferrum(**options)
|
52
|
+
settings[:ferrum] = options
|
53
|
+
end
|
54
|
+
|
55
|
+
def intercept(&block)
|
56
|
+
settings[:intercept] = block
|
57
|
+
end
|
58
|
+
|
47
59
|
def settings
|
48
60
|
@settings ||= {
|
49
61
|
delay: DELAY,
|
@@ -51,6 +63,9 @@ module Vessel
|
|
51
63
|
start_urls: START_URLS,
|
52
64
|
min_threads: MIN_THREADS,
|
53
65
|
max_threads: MAX_THREADS,
|
66
|
+
ferrum: Hash.new,
|
67
|
+
intercept: nil,
|
68
|
+
headers: nil,
|
54
69
|
domain: name&.split('::')&.last&.downcase
|
55
70
|
}
|
56
71
|
end
|
@@ -82,5 +97,9 @@ module Vessel
|
|
82
97
|
def absolute_url(relative)
|
83
98
|
Addressable::URI.join(page.current_url, relative).to_s
|
84
99
|
end
|
100
|
+
|
101
|
+
def current_url
|
102
|
+
Addressable::URI.parse(page.current_url)
|
103
|
+
end
|
85
104
|
end
|
86
105
|
end
|
data/lib/vessel/engine.rb
CHANGED
@@ -21,25 +21,35 @@ module Vessel
|
|
21
21
|
|
22
22
|
until @queue.closed?
|
23
23
|
message = @queue.pop
|
24
|
+
|
24
25
|
raise(message) if message.is_a?(Exception)
|
25
|
-
|
26
|
+
|
27
|
+
page, request = message
|
28
|
+
args = [request.method, request.data].compact
|
29
|
+
handle(page, args)
|
30
|
+
|
26
31
|
@queue.close if idle?
|
27
32
|
end
|
33
|
+
|
34
|
+
ensure
|
35
|
+
scheduler.stop
|
28
36
|
end
|
29
37
|
|
30
|
-
def handle(page,
|
38
|
+
def handle(page, args)
|
31
39
|
crawler = @crawler_class.new(page)
|
32
|
-
crawler.send(
|
33
|
-
if
|
34
|
-
scheduler.post(*
|
40
|
+
crawler.send(*args) do |*result|
|
41
|
+
if result.flatten.all? { |i| i.is_a?(Request) }
|
42
|
+
scheduler.post(*result.flatten)
|
35
43
|
else
|
36
|
-
@middleware&.call(*
|
44
|
+
@middleware&.call(*result)
|
37
45
|
end
|
38
46
|
end
|
39
47
|
ensure
|
40
|
-
page.close
|
48
|
+
page.close if page
|
41
49
|
end
|
42
50
|
|
51
|
+
private
|
52
|
+
|
43
53
|
def start_requests
|
44
54
|
Request.build(*settings[:start_urls])
|
45
55
|
end
|
data/lib/vessel/request.rb
CHANGED
@@ -4,16 +4,24 @@ require "addressable/uri"
|
|
4
4
|
|
5
5
|
module Vessel
|
6
6
|
class Request
|
7
|
-
attr_reader :url, :uri, :method
|
7
|
+
attr_reader :url, :uri, :method, :data
|
8
8
|
|
9
9
|
def self.build(*urls)
|
10
|
-
urls.map { |url| new(url: url) }
|
10
|
+
urls.empty? ? [new] : urls.map { |url| new(url: url) }
|
11
11
|
end
|
12
12
|
|
13
|
-
def initialize(url
|
14
|
-
|
15
|
-
|
13
|
+
def initialize(url: nil, method: :parse, data: nil)
|
14
|
+
if url
|
15
|
+
@url = url.to_s
|
16
|
+
@uri = Addressable::URI.parse(@url)
|
17
|
+
end
|
18
|
+
|
16
19
|
@method = method
|
20
|
+
@data = data.freeze if data
|
21
|
+
end
|
22
|
+
|
23
|
+
def stub?
|
24
|
+
!url
|
17
25
|
end
|
18
26
|
end
|
19
27
|
end
|
data/lib/vessel/scheduler.rb
CHANGED
@@ -6,18 +6,23 @@ require "concurrent-ruby"
|
|
6
6
|
module Vessel
|
7
7
|
class Scheduler
|
8
8
|
extend Forwardable
|
9
|
-
delegate %i[scheduled_task_count completed_task_count queue_length] =>
|
9
|
+
delegate %i[scheduled_task_count completed_task_count queue_length] => :pool
|
10
10
|
|
11
|
-
attr_reader :browser, :queue, :delay
|
11
|
+
attr_reader :browser, :queue, :delay, :headers
|
12
12
|
|
13
13
|
def initialize(queue, settings)
|
14
14
|
@queue = queue
|
15
|
-
@min_threads, @max_threads, @delay =
|
16
|
-
settings.values_at(:min_threads, :max_threads, :delay)
|
15
|
+
@min_threads, @max_threads, @delay, @headers =
|
16
|
+
settings.values_at(:min_threads, :max_threads, :delay, :headers)
|
17
17
|
|
18
|
-
options =
|
18
|
+
options = settings[:ferrum]
|
19
19
|
options.merge!(timeout: settings[:timeout]) if settings[:timeout]
|
20
20
|
@browser = Ferrum::Browser.new(**options)
|
21
|
+
|
22
|
+
if settings[:intercept]
|
23
|
+
@browser.network.intercept
|
24
|
+
@browser.on(:request, &settings[:intercept])
|
25
|
+
end
|
21
26
|
end
|
22
27
|
|
23
28
|
def post(*requests)
|
@@ -28,6 +33,12 @@ module Vessel
|
|
28
33
|
end
|
29
34
|
end
|
30
35
|
|
36
|
+
def stop
|
37
|
+
pool.shutdown
|
38
|
+
pool.kill unless pool.wait_for_termination(30)
|
39
|
+
browser.quit
|
40
|
+
end
|
41
|
+
|
31
42
|
private
|
32
43
|
|
33
44
|
def pool
|
@@ -39,7 +50,10 @@ module Vessel
|
|
39
50
|
end
|
40
51
|
|
41
52
|
def goto(request)
|
53
|
+
return [nil, request] if request.stub?
|
54
|
+
|
42
55
|
page = browser.create_page
|
56
|
+
page.headers.set(headers) if headers
|
43
57
|
# Delay is set between requests when we don't want to bombard server with
|
44
58
|
# requests so it requires crawler to be single threaded. Otherwise doesn't
|
45
59
|
# make sense.
|
data/lib/vessel/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: vessel
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Dmitry Vorotilin
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2021-03-09 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: ferrum
|
@@ -16,28 +16,28 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '0.
|
19
|
+
version: '0.8'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - ">="
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '0.
|
26
|
+
version: '0.8'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: thor
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
31
|
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '0
|
33
|
+
version: '1.0'
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
38
|
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version: '0
|
40
|
+
version: '1.0'
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: bundler
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
@@ -117,7 +117,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
117
117
|
- !ruby/object:Gem::Version
|
118
118
|
version: '0'
|
119
119
|
requirements: []
|
120
|
-
rubygems_version: 3.
|
120
|
+
rubygems_version: 3.1.4
|
121
121
|
signing_key:
|
122
122
|
specification_version: 4
|
123
123
|
summary: High-level web crawling framework
|