spidy 0.0.4 → 0.0.5
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/exe/spidy +15 -14
- data/lib/spidy/connector/html.rb +22 -7
- data/lib/spidy/definition.rb +18 -12
- data/lib/spidy/shell.rb +1 -1
- data/lib/spidy/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 41b1f40d3ae33eeac273d40a57b956be37971bbb940280c1ca5c9faf0371fbeb
|
4
|
+
data.tar.gz: e55d03b8703142255caf2eb74b927f4dcfdc58b02a96bb51fcb2f1fa0e9e4167
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 9577e5315da4a33a4becb1a9c3d41788729fa5dcc8d1a8f1fe774a36a9c34503c7d4f35ee9c20efb99148ac8fe59d9ed69c47e8da20d4590a153b743cc1ea7d4
|
7
|
+
data.tar.gz: ff454254636e05f6df17d8b35d591ad32ffb6de66bd654a2ed34006eb73a87fa9e948539a0b954ae8bf82d30860966066f3947bc34559e783f617c90fa187715
|
data/exe/spidy
CHANGED
@@ -2,22 +2,23 @@
|
|
2
2
|
# frozen_string_literal: true
|
3
3
|
|
4
4
|
require 'spidy'
|
5
|
+
require 'pry'
|
5
6
|
|
6
|
-
if ARGV[
|
7
|
-
|
8
|
-
|
7
|
+
if ARGV[1].blank?
|
8
|
+
case ARGV[0]
|
9
|
+
when 'version' then STDOUT.puts(Spidy::VERSION)
|
10
|
+
when 'console' then Spidy.console
|
9
11
|
else
|
10
|
-
|
12
|
+
STDOUT.puts 'usage: spidy [version console]'
|
11
13
|
end
|
12
|
-
return
|
13
|
-
end
|
14
|
-
|
15
|
-
shell = Spidy.open(ARGV[1]).shell
|
16
|
-
|
17
|
-
case ARGV[0]&.to_sym
|
18
|
-
when :shell then shell.function
|
19
|
-
when :call then shell.call(ARGV[2])
|
20
|
-
when :each then shell.each(ARGV[2])
|
21
14
|
else
|
22
|
-
|
15
|
+
spidy = Spidy.open(ARGV[1])
|
16
|
+
case ARGV[0]
|
17
|
+
when 'console' then spidy.console
|
18
|
+
when 'shell' then spidy.shell.function
|
19
|
+
when 'call' then spidy.shell.call(ARGV[2])
|
20
|
+
when 'each' then spidy.shell.each(ARGV[2])
|
21
|
+
else
|
22
|
+
STDOUT.puts 'usage: spidy [call each shell] [file]'
|
23
|
+
end
|
23
24
|
end
|
data/lib/spidy/connector/html.rb
CHANGED
@@ -13,13 +13,28 @@ module Spidy::Connector::Html
|
|
13
13
|
'Safari/537.36'
|
14
14
|
].join(' ')
|
15
15
|
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
16
|
+
@agent = Mechanize.new
|
17
|
+
@agent.user_agent = USER_AGENT
|
18
|
+
|
19
|
+
class << self
|
20
|
+
def call(url, encoding: nil, &yielder)
|
21
|
+
if encoding
|
22
|
+
@agent.default_encoding = encoding
|
23
|
+
@agent.force_default_encoding = true
|
24
|
+
end
|
25
|
+
get(url, yielder)
|
26
|
+
end
|
27
|
+
|
28
|
+
def get(url, yielder)
|
29
|
+
@agent.get(url, &yielder)
|
30
|
+
rescue Mechanize::ResponseCodeError => e
|
31
|
+
case e.response_code
|
32
|
+
when '429'
|
33
|
+
sleep 2
|
34
|
+
@agent.get(url, &yielder)
|
35
|
+
else
|
36
|
+
raise e
|
37
|
+
end
|
21
38
|
end
|
22
|
-
agent.user_agent = USER_AGENT
|
23
|
-
agent.get(url, &yielder)
|
24
39
|
end
|
25
40
|
end
|
data/lib/spidy/definition.rb
CHANGED
@@ -8,23 +8,29 @@ class Spidy::Definition
|
|
8
8
|
class_attribute :spiders, default: {}
|
9
9
|
|
10
10
|
class << self
|
11
|
-
def
|
11
|
+
def spider(name = :default, connector: nil, as: nil)
|
12
12
|
connector = Spidy::Connector.get(as || connector) || connector
|
13
|
-
|
14
|
-
|
15
|
-
connection_yielder = lambda do |resource|
|
16
|
-
binder.call(resource, define_block) do |object|
|
17
|
-
yielder.call(object)
|
18
|
-
end
|
19
|
-
end
|
20
|
-
connector.call(url, &connection_yielder)
|
13
|
+
spiders[name] = proc do |url, &yielder|
|
14
|
+
yield(yielder, connector, url)
|
21
15
|
end
|
22
16
|
end
|
23
17
|
|
24
|
-
def
|
18
|
+
def define(name = :default, connector: nil, binder: nil, as: nil, &define_block)
|
25
19
|
connector = Spidy::Connector.get(as || connector) || connector
|
26
|
-
|
27
|
-
|
20
|
+
binder = Spidy::Binder.get(as || binder) || binder
|
21
|
+
namespace[name] = define_proc(connector, binder, define_block)
|
22
|
+
end
|
23
|
+
|
24
|
+
private
|
25
|
+
|
26
|
+
def define_proc(connector, binder, define_block)
|
27
|
+
proc do |url, &yielder|
|
28
|
+
fail 'invalid argument [Required url / block]' if url.blank? || yielder.nil?
|
29
|
+
|
30
|
+
connection_yielder = lambda do |resource|
|
31
|
+
binder.call(resource, define_block) { |object| yielder.call(object) }
|
32
|
+
end
|
33
|
+
connector.call(url, &connection_yielder)
|
28
34
|
end
|
29
35
|
end
|
30
36
|
end
|
data/lib/spidy/shell.rb
CHANGED
data/lib/spidy/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: spidy
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- aileron
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-09-
|
11
|
+
date: 2019-09-19 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|