spidy 0.2.8 → 0.2.9
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/Gemfile.lock +1 -1
- data/lib/spidy/connector.rb +16 -4
- data/lib/spidy/connector/direct.rb +1 -1
- data/lib/spidy/connector/html.rb +1 -1
- data/lib/spidy/connector/json.rb +18 -2
- data/lib/spidy/connector/xml.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: 44d16509821e1779d821effb7c571d2a11cbb79166168943242628b2e53457ec
|
4
|
+
data.tar.gz: 5b52389a8042c9e69aaeead0d96b81553da2e5f5e51ad16696f87249e38067bd
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 3475b05ea1235b388960416a03ab96adb64608ce4046d1812b4d80f038a91b99343882e45413ee6a2f74e29626869aca8a48d34f8e57c64b480c8893efcda123
|
7
|
+
data.tar.gz: 7e4fd1abf5898a7a7273d4eaf53021e4c1898d995e8e0d23abfcbf80c3e1b45b2f059c95e48707577bae72a4f158d7cba7f9be097e7e8a277d89e683386c32d6
|
data/Gemfile.lock
CHANGED
data/lib/spidy/connector.rb
CHANGED
@@ -22,11 +22,19 @@ module Spidy::Connector
|
|
22
22
|
'Safari/537.36'
|
23
23
|
].join(' ')
|
24
24
|
|
25
|
+
#
|
26
|
+
# error output logger
|
27
|
+
#
|
28
|
+
DEFAULT_LOGGER = proc { |values| STDERR.puts(values.to_json) }
|
29
|
+
|
30
|
+
#
|
31
|
+
# static method
|
32
|
+
#
|
25
33
|
module StaticAccessor
|
26
34
|
extend ActiveSupport::Concern
|
27
35
|
class_methods do
|
28
|
-
def call(url, wait_time:
|
29
|
-
new(wait_time: wait_time, user_agent: user_agent).call(url, &block)
|
36
|
+
def call(url, wait_time: 5, logger: Spidy::Connector::DEFAULT_LOGGER, user_agent: Spidy::Connector::USER_AGENT, &block)
|
37
|
+
new(wait_time: wait_time, user_agent: user_agent, logger: logger).call(url, &block)
|
30
38
|
end
|
31
39
|
end
|
32
40
|
end
|
@@ -75,10 +83,14 @@ module Spidy::Connector
|
|
75
83
|
#
|
76
84
|
# get connection handller
|
77
85
|
#
|
78
|
-
def self.get(value, wait_time: nil, user_agent: nil, socks_proxy: nil)
|
86
|
+
def self.get(value, wait_time: nil, user_agent: nil, socks_proxy: nil, logger: nil)
|
79
87
|
return value if value.respond_to?(:call)
|
80
88
|
|
81
|
-
builder = Builder.new(const_get(value.to_s.classify).new(
|
89
|
+
builder = Builder.new(const_get(value.to_s.classify).new(
|
90
|
+
wait_time: wait_time || 5,
|
91
|
+
user_agent: user_agent || USER_AGENT,
|
92
|
+
logger: logger || DEFAULT_LOGGER,
|
93
|
+
), socks_proxy)
|
82
94
|
return builder.origin_connector if socks_proxy.nil? || builder.proxy_disabled?
|
83
95
|
|
84
96
|
builder.proxy_connector
|
data/lib/spidy/connector/html.rb
CHANGED
@@ -8,7 +8,7 @@ class Spidy::Connector::Html
|
|
8
8
|
|
9
9
|
def initialize(wait_time:, user_agent:, logger: nil)
|
10
10
|
@wait_time = wait_time
|
11
|
-
@logger = logger
|
11
|
+
@logger = logger
|
12
12
|
@agent = Mechanize.new
|
13
13
|
@user_agent = user_agent
|
14
14
|
@agent.user_agent = user_agent
|
data/lib/spidy/connector/json.rb
CHANGED
@@ -6,8 +6,12 @@
|
|
6
6
|
class Spidy::Connector::Json
|
7
7
|
include Spidy::Connector::StaticAccessor
|
8
8
|
|
9
|
-
|
9
|
+
attr_reader :logger
|
10
|
+
|
11
|
+
def initialize(wait_time: nil, user_agent: nil, logger: nil)
|
12
|
+
@wait_time = wait_time
|
10
13
|
@user_agent = user_agent
|
14
|
+
@logger = logger
|
11
15
|
end
|
12
16
|
|
13
17
|
def call(url, &block)
|
@@ -15,7 +19,19 @@ class Spidy::Connector::Json
|
|
15
19
|
connect(url, &block)
|
16
20
|
end
|
17
21
|
|
18
|
-
def connect(url)
|
22
|
+
def connect(url, retry_count: 5)
|
19
23
|
OpenURI.open_uri(url, "User-Agent" => @user_agent) { |body| yield JSON.parse(body.read, symbolize_names: true) }
|
24
|
+
rescue OpenURI::HTTPError => e
|
25
|
+
logger.call('retry.accessed': Time.current,
|
26
|
+
'retry.uri': url,
|
27
|
+
'retry.response_code': e.message,
|
28
|
+
'retry.rest_count': retry_count)
|
29
|
+
|
30
|
+
retry_count -= 1
|
31
|
+
if retry_count.positive?
|
32
|
+
sleep @wait_time
|
33
|
+
retry
|
34
|
+
end
|
35
|
+
raise e
|
20
36
|
end
|
21
37
|
end
|
data/lib/spidy/connector/xml.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: 0.2.
|
4
|
+
version: 0.2.9
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- aileron
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-09-
|
11
|
+
date: 2020-09-08 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|