aranha-parsers 0.9.0 → 0.12.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/aranha/parsers/base.rb +7 -7
- data/lib/aranha/parsers/html/item_list.rb +5 -1
- data/lib/aranha/parsers/html/node/default/numeric_support.rb +70 -0
- data/lib/aranha/parsers/html/node/default/string_support.rb +77 -0
- data/lib/aranha/parsers/html/node/default.rb +2 -94
- data/lib/aranha/parsers/source_address/hash_http_base.rb +86 -0
- data/lib/aranha/parsers/source_address/hash_http_get.rb +3 -15
- data/lib/aranha/parsers/source_address/hash_http_post.rb +3 -35
- data/lib/aranha/parsers/source_address/http_get.rb +7 -16
- data/lib/aranha/parsers/version.rb +1 -1
- metadata +16 -13
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 955f0df6b2a59762cbdd597dd17ae6608a880ee74f4547449ad06bbef4cf9f09
|
4
|
+
data.tar.gz: 95e891f8db0aa252f3e385956e783c48e08e42e68b3e6666491356eb2e60618a
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e5e7266770218b0698edb3111db90d797a24bb3e0f5ee54d5728a5810a87559a22a3a9f3d368bb28fc83fda8c6cbc04c99cab44c50ee25ea76e7550ea4753249
|
7
|
+
data.tar.gz: 66873b24e21f3c3e43a4ae49b82997c6e401a4e500274e2fc76e4ba91b013eae1a4f6b8641880f94896f1dab40bf23c86b24e226c14c2b92afe024d2d18aa230
|
data/lib/aranha/parsers/base.rb
CHANGED
@@ -37,21 +37,21 @@ module Aranha
|
|
37
37
|
delegate :url, to: :source_address
|
38
38
|
|
39
39
|
def content
|
40
|
-
@content ||=
|
41
|
-
s = source_address.content
|
42
|
-
log_content(s)
|
43
|
-
s
|
44
|
-
end
|
40
|
+
@content ||= log_content(source_address_content)
|
45
41
|
end
|
46
42
|
|
43
|
+
# @return [String]
|
44
|
+
delegate :content, to: :source_address, prefix: true
|
45
|
+
|
47
46
|
private
|
48
47
|
|
48
|
+
# @return [String]
|
49
49
|
def log_content(content, suffix = '')
|
50
50
|
path = log_file(suffix)
|
51
51
|
|
52
|
-
|
52
|
+
File.open(path, 'wb') { |file| file.write(content) } if path
|
53
53
|
|
54
|
-
|
54
|
+
content
|
55
55
|
end
|
56
56
|
|
57
57
|
def log_file(suffix)
|
@@ -10,11 +10,15 @@ module Aranha
|
|
10
10
|
items_data
|
11
11
|
end
|
12
12
|
|
13
|
+
def item_data(item)
|
14
|
+
item
|
15
|
+
end
|
16
|
+
|
13
17
|
def items_data
|
14
18
|
count = 0
|
15
19
|
@data ||= nokogiri.xpath(items_xpath).map do |m|
|
16
20
|
count += 1
|
17
|
-
node_parser.parse(m)
|
21
|
+
item_data(node_parser.parse(m))
|
18
22
|
end
|
19
23
|
rescue StandardError => e
|
20
24
|
raise StandardError, "#{e.message} (Count: #{count})"
|
@@ -0,0 +1,70 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'aranha/parsers/html/node/base'
|
4
|
+
require 'eac_ruby_utils/core_ext'
|
5
|
+
|
6
|
+
module Aranha
|
7
|
+
module Parsers
|
8
|
+
module Html
|
9
|
+
module Node
|
10
|
+
class Default < ::Aranha::Parsers::Html::Node::Base
|
11
|
+
module NumericSupport
|
12
|
+
def integer_value(node, xpath)
|
13
|
+
r = string_value(node, xpath)
|
14
|
+
return nil if r.blank?
|
15
|
+
|
16
|
+
m = /\d+/.match(r)
|
17
|
+
raise "Integer not found in \"#{r}\"" unless m
|
18
|
+
|
19
|
+
m[0].to_i
|
20
|
+
end
|
21
|
+
|
22
|
+
def integer_optional_value(node, xpath)
|
23
|
+
r = string_value(node, xpath)
|
24
|
+
m = /\d+/.match(r)
|
25
|
+
m ? m[0].to_i : nil
|
26
|
+
end
|
27
|
+
|
28
|
+
def float_value(node, xpath)
|
29
|
+
parse_float(node, xpath, true)
|
30
|
+
end
|
31
|
+
|
32
|
+
def float_optional_value(node, xpath)
|
33
|
+
parse_float(node, xpath, false)
|
34
|
+
end
|
35
|
+
|
36
|
+
def us_decimal_value(node, xpath)
|
37
|
+
parse_us_decimal(node, xpath, true)
|
38
|
+
end
|
39
|
+
|
40
|
+
def us_decimal_optional_value(node, xpath)
|
41
|
+
parse_us_decimal(node, xpath, false)
|
42
|
+
end
|
43
|
+
|
44
|
+
private
|
45
|
+
|
46
|
+
def parse_float(node, xpath, required)
|
47
|
+
s = string_value(node, xpath)
|
48
|
+
m = /\d+(?:[\.\,](\d+))?/.match(s)
|
49
|
+
if m
|
50
|
+
m[0].delete('.').tr(',', '.').to_f
|
51
|
+
elsif required
|
52
|
+
raise "Float value not found in \"#{s}\""
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
def parse_us_decimal(node, xpath, required)
|
57
|
+
s = string_value(node, xpath)
|
58
|
+
m = /\d+(?:[\.\,](\d+))?/.match(s)
|
59
|
+
if m
|
60
|
+
m[0].delete(',').to_f
|
61
|
+
elsif required
|
62
|
+
raise "US decimal value not found in \"#{s}\""
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
@@ -0,0 +1,77 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'aranha/parsers/html/node/base'
|
4
|
+
require 'eac_ruby_utils/core_ext'
|
5
|
+
|
6
|
+
module Aranha
|
7
|
+
module Parsers
|
8
|
+
module Html
|
9
|
+
module Node
|
10
|
+
class Default < ::Aranha::Parsers::Html::Node::Base
|
11
|
+
module StringSupport
|
12
|
+
def quoted_value(node, xpath)
|
13
|
+
s = string_value(node, xpath)
|
14
|
+
return '' unless s
|
15
|
+
|
16
|
+
m = /\"([^\"]+)\"/.match(s)
|
17
|
+
return m[1] if m
|
18
|
+
|
19
|
+
''
|
20
|
+
end
|
21
|
+
|
22
|
+
def regxep(node, xpath, pattern)
|
23
|
+
s = string_value(node, xpath)
|
24
|
+
m = pattern.match(s)
|
25
|
+
return m if m
|
26
|
+
|
27
|
+
raise "Pattern \"#{pattern}\" not found in string \"#{s}\""
|
28
|
+
end
|
29
|
+
|
30
|
+
def string_value(node, xpath)
|
31
|
+
if node.at_xpath(xpath)
|
32
|
+
sanitize_string(node.at_xpath(xpath).text)
|
33
|
+
else
|
34
|
+
''
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
def string_recursive_value(node, xpath, required = true)
|
39
|
+
root = node.at_xpath(xpath)
|
40
|
+
if root.blank?
|
41
|
+
return nil unless required
|
42
|
+
|
43
|
+
raise "No node found (Xpath: #{xpath})"
|
44
|
+
end
|
45
|
+
result = string_recursive(root)
|
46
|
+
return result if result.present?
|
47
|
+
return nil unless required
|
48
|
+
|
49
|
+
raise "String blank (Xpath: #{xpath})"
|
50
|
+
end
|
51
|
+
|
52
|
+
def string_recursive_optional_value(node, xpath)
|
53
|
+
string_recursive_value(node, xpath, false)
|
54
|
+
end
|
55
|
+
|
56
|
+
private
|
57
|
+
|
58
|
+
def sanitize_string(obj)
|
59
|
+
obj.to_s.tr("\u00A0", ' ').strip
|
60
|
+
end
|
61
|
+
|
62
|
+
def string_recursive(node)
|
63
|
+
return sanitize_string(node.text) if node.is_a?(::Nokogiri::XML::Text)
|
64
|
+
|
65
|
+
s = ''
|
66
|
+
node.children.each do |child|
|
67
|
+
child_s = string_recursive(child)
|
68
|
+
s += ' ' + child_s if child_s.present?
|
69
|
+
end
|
70
|
+
sanitize_string(s)
|
71
|
+
end
|
72
|
+
end
|
73
|
+
end
|
74
|
+
end
|
75
|
+
end
|
76
|
+
end
|
77
|
+
end
|
@@ -1,71 +1,14 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
3
|
require 'aranha/parsers/html/node/base'
|
4
|
+
require 'eac_ruby_utils/core_ext'
|
4
5
|
|
5
6
|
module Aranha
|
6
7
|
module Parsers
|
7
8
|
module Html
|
8
9
|
module Node
|
9
10
|
class Default < ::Aranha::Parsers::Html::Node::Base
|
10
|
-
|
11
|
-
if node.at_xpath(xpath)
|
12
|
-
sanitize_string(node.at_xpath(xpath).text)
|
13
|
-
else
|
14
|
-
''
|
15
|
-
end
|
16
|
-
end
|
17
|
-
|
18
|
-
def string_recursive_value(node, xpath, required = true)
|
19
|
-
root = node.at_xpath(xpath)
|
20
|
-
if root.blank?
|
21
|
-
return nil unless required
|
22
|
-
|
23
|
-
raise "No node found (Xpath: #{xpath})"
|
24
|
-
end
|
25
|
-
result = string_recursive(root)
|
26
|
-
return result if result.present?
|
27
|
-
return nil unless required
|
28
|
-
|
29
|
-
raise "String blank (Xpath: #{xpath})"
|
30
|
-
end
|
31
|
-
|
32
|
-
def string_recursive_optional_value(node, xpath)
|
33
|
-
string_recursive_value(node, xpath, false)
|
34
|
-
end
|
35
|
-
|
36
|
-
def quoted_value(node, xpath)
|
37
|
-
s = string_value(node, xpath)
|
38
|
-
return '' unless s
|
39
|
-
|
40
|
-
m = /\"([^\"]+)\"/.match(s)
|
41
|
-
return m[1] if m
|
42
|
-
|
43
|
-
''
|
44
|
-
end
|
45
|
-
|
46
|
-
def integer_value(node, xpath)
|
47
|
-
r = string_value(node, xpath)
|
48
|
-
return nil if r.blank?
|
49
|
-
|
50
|
-
m = /\d+/.match(r)
|
51
|
-
raise "Integer not found in \"#{r}\"" unless m
|
52
|
-
|
53
|
-
m[0].to_i
|
54
|
-
end
|
55
|
-
|
56
|
-
def integer_optional_value(node, xpath)
|
57
|
-
r = string_value(node, xpath)
|
58
|
-
m = /\d+/.match(r)
|
59
|
-
m ? m[0].to_i : nil
|
60
|
-
end
|
61
|
-
|
62
|
-
def float_value(node, xpath)
|
63
|
-
parse_float(node, xpath, true)
|
64
|
-
end
|
65
|
-
|
66
|
-
def float_optional_value(node, xpath)
|
67
|
-
parse_float(node, xpath, false)
|
68
|
-
end
|
11
|
+
require_sub __FILE__, include_modules: true
|
69
12
|
|
70
13
|
def array_value(node, xpath)
|
71
14
|
r = node.xpath(xpath).map { |n| n.text.strip }
|
@@ -84,41 +27,6 @@ module Aranha
|
|
84
27
|
m = /(\d+) m/.match(join_value(node, xpath))
|
85
28
|
m ? m[1].to_i : nil
|
86
29
|
end
|
87
|
-
|
88
|
-
def regxep(node, xpath, pattern)
|
89
|
-
s = string_value(node, xpath)
|
90
|
-
m = pattern.match(s)
|
91
|
-
return m if m
|
92
|
-
|
93
|
-
raise "Pattern \"#{pattern}\" not found in string \"#{s}\""
|
94
|
-
end
|
95
|
-
|
96
|
-
private
|
97
|
-
|
98
|
-
def parse_float(node, xpath, required)
|
99
|
-
s = string_value(node, xpath)
|
100
|
-
m = /\d+(?:[\.\,](\d+))?/.match(s)
|
101
|
-
if m
|
102
|
-
m[0].delete('.').tr(',', '.').to_f
|
103
|
-
elsif required
|
104
|
-
raise "Float value not found in \"#{s}\""
|
105
|
-
end
|
106
|
-
end
|
107
|
-
|
108
|
-
def sanitize_string(obj)
|
109
|
-
obj.to_s.tr("\u00A0", ' ').strip
|
110
|
-
end
|
111
|
-
|
112
|
-
def string_recursive(node)
|
113
|
-
return sanitize_string(node.text) if node.is_a?(::Nokogiri::XML::Text)
|
114
|
-
|
115
|
-
s = ''
|
116
|
-
node.children.each do |child|
|
117
|
-
child_s = string_recursive(child)
|
118
|
-
s += ' ' + child_s if child_s.present?
|
119
|
-
end
|
120
|
-
sanitize_string(s)
|
121
|
-
end
|
122
30
|
end
|
123
31
|
end
|
124
32
|
end
|
@@ -0,0 +1,86 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'aranha/parsers/source_address/fetch_content_error'
|
4
|
+
require 'aranha/parsers/source_address/hash_http_base'
|
5
|
+
require 'eac_ruby_utils/core_ext'
|
6
|
+
require 'faraday_middleware'
|
7
|
+
require 'yaml'
|
8
|
+
|
9
|
+
module Aranha
|
10
|
+
module Parsers
|
11
|
+
class SourceAddress
|
12
|
+
class HashHttpBase
|
13
|
+
class << self
|
14
|
+
def http_method
|
15
|
+
const_get 'HTTP_METHOD'
|
16
|
+
end
|
17
|
+
|
18
|
+
def valid_source?(source)
|
19
|
+
source.is_a?(::Hash) &&
|
20
|
+
source.with_indifferent_access[:method].to_s.downcase.strip == http_method.to_s
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
DEFAULT_BODY = ''
|
25
|
+
DEFAULT_FOLLOW_REDIRECT = true
|
26
|
+
DEFAULT_HEADERS = {}.freeze
|
27
|
+
DEFAULT_PARAMS = {}.freeze
|
28
|
+
|
29
|
+
common_constructor :source do
|
30
|
+
self.source = source.with_indifferent_access
|
31
|
+
end
|
32
|
+
compare_by :source
|
33
|
+
|
34
|
+
def body
|
35
|
+
param(:body, DEFAULT_BODY)
|
36
|
+
end
|
37
|
+
|
38
|
+
def follow_redirect?
|
39
|
+
param(:follow_redirect, DEFAULT_FOLLOW_REDIRECT)
|
40
|
+
end
|
41
|
+
|
42
|
+
def headers
|
43
|
+
param(:headers, DEFAULT_HEADERS)
|
44
|
+
end
|
45
|
+
|
46
|
+
def url
|
47
|
+
source.fetch(:url)
|
48
|
+
end
|
49
|
+
|
50
|
+
def serialize
|
51
|
+
source.to_yaml
|
52
|
+
end
|
53
|
+
|
54
|
+
# @return [Faraday]
|
55
|
+
def faraday_connection
|
56
|
+
::Faraday.new do |f|
|
57
|
+
f.response :follow_redirects if follow_redirect?
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def faraday_request
|
62
|
+
faraday_connection.send(self.class.http_method, url) do |req|
|
63
|
+
headers.if_present { |v| req.headers = v }
|
64
|
+
body.if_present { |v| req.body = v }
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
def content
|
69
|
+
req = faraday_request
|
70
|
+
return req.body if req.status == 200
|
71
|
+
|
72
|
+
raise ::Aranha::Parsers::SourceAddress::FetchContentError,
|
73
|
+
"Get #{url} returned #{req.status.to_i}"
|
74
|
+
end
|
75
|
+
|
76
|
+
def param(key, default_value)
|
77
|
+
source[key] || params[key] || default_value
|
78
|
+
end
|
79
|
+
|
80
|
+
def params
|
81
|
+
source[:params].if_present(DEFAULT_PARAMS)
|
82
|
+
end
|
83
|
+
end
|
84
|
+
end
|
85
|
+
end
|
86
|
+
end
|
@@ -1,24 +1,12 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
require 'aranha/parsers/source_address/
|
3
|
+
require 'aranha/parsers/source_address/hash_http_base'
|
4
4
|
|
5
5
|
module Aranha
|
6
6
|
module Parsers
|
7
7
|
class SourceAddress
|
8
|
-
class HashHttpGet < ::Aranha::Parsers::SourceAddress::
|
9
|
-
|
10
|
-
def valid_source?(source)
|
11
|
-
source.is_a?(::Hash) &&
|
12
|
-
source.with_indifferent_access[:method].to_s.downcase.strip == 'get'
|
13
|
-
end
|
14
|
-
end
|
15
|
-
|
16
|
-
def content
|
17
|
-
HTTPClient.new.get_content(
|
18
|
-
source[:url],
|
19
|
-
source[:params]
|
20
|
-
)
|
21
|
-
end
|
8
|
+
class HashHttpGet < ::Aranha::Parsers::SourceAddress::HashHttpBase
|
9
|
+
HTTP_METHOD = :get
|
22
10
|
end
|
23
11
|
end
|
24
12
|
end
|
@@ -1,44 +1,12 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
require '
|
4
|
-
require 'httpclient'
|
5
|
-
require 'yaml'
|
3
|
+
require 'aranha/parsers/source_address/hash_http_base'
|
6
4
|
|
7
5
|
module Aranha
|
8
6
|
module Parsers
|
9
7
|
class SourceAddress
|
10
|
-
class HashHttpPost
|
11
|
-
|
12
|
-
def valid_source?(source)
|
13
|
-
source.is_a?(::Hash) &&
|
14
|
-
source.with_indifferent_access[:method].to_s.downcase.strip == 'post'
|
15
|
-
end
|
16
|
-
end
|
17
|
-
|
18
|
-
attr_reader :source
|
19
|
-
|
20
|
-
def initialize(source)
|
21
|
-
@source = source.with_indifferent_access
|
22
|
-
end
|
23
|
-
|
24
|
-
def ==(other)
|
25
|
-
self.class == other.class && source == other.source
|
26
|
-
end
|
27
|
-
|
28
|
-
def url
|
29
|
-
source.fetch(:url)
|
30
|
-
end
|
31
|
-
|
32
|
-
def serialize
|
33
|
-
source.to_yaml
|
34
|
-
end
|
35
|
-
|
36
|
-
def content
|
37
|
-
HTTPClient.new.post_content(
|
38
|
-
source[:url],
|
39
|
-
source[:params].merge(follow_redirect: true)
|
40
|
-
)
|
41
|
-
end
|
8
|
+
class HashHttpPost < ::Aranha::Parsers::SourceAddress::HashHttpBase
|
9
|
+
HTTP_METHOD = :post
|
42
10
|
end
|
43
11
|
end
|
44
12
|
end
|
@@ -3,6 +3,7 @@
|
|
3
3
|
require 'addressable'
|
4
4
|
require 'curb'
|
5
5
|
require 'aranha/parsers/source_address/fetch_content_error'
|
6
|
+
require 'faraday_middleware'
|
6
7
|
|
7
8
|
module Aranha
|
8
9
|
module Parsers
|
@@ -38,10 +39,12 @@ module Aranha
|
|
38
39
|
end
|
39
40
|
|
40
41
|
def content
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
42
|
+
conn = ::Faraday.new do |f|
|
43
|
+
f.request :retry # retry transient failures
|
44
|
+
f.response :follow_redirects # follow redirects
|
45
|
+
end
|
46
|
+
c = conn.get(url)
|
47
|
+
return c.body if c.status == 200
|
45
48
|
|
46
49
|
raise ::Aranha::Parsers::SourceAddress::FetchContentError,
|
47
50
|
"Get #{url} returned #{c.status.to_i}"
|
@@ -50,18 +53,6 @@ module Aranha
|
|
50
53
|
def serialize
|
51
54
|
url
|
52
55
|
end
|
53
|
-
|
54
|
-
private
|
55
|
-
|
56
|
-
def curl_perform(curl)
|
57
|
-
unless curl.perform
|
58
|
-
raise(::Aranha::Parsers::SourceAddress::FetchContentError,
|
59
|
-
"Curl perform failed (URL: #{url})")
|
60
|
-
end
|
61
|
-
@final_url = curl.url
|
62
|
-
rescue Curl::Err::CurlError => e
|
63
|
-
raise ::Aranha::Parsers::SourceAddress::FetchContentError, "CURL error: #{e.class.name}"
|
64
|
-
end
|
65
56
|
end
|
66
57
|
end
|
67
58
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: aranha-parsers
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.12.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Esquilo Azul Company
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2022-05-15 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: activesupport
|
@@ -58,34 +58,34 @@ dependencies:
|
|
58
58
|
requirements:
|
59
59
|
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version: '0.
|
61
|
+
version: '0.92'
|
62
|
+
- - ">="
|
63
|
+
- !ruby/object:Gem::Version
|
64
|
+
version: 0.92.1
|
62
65
|
type: :runtime
|
63
66
|
prerelease: false
|
64
67
|
version_requirements: !ruby/object:Gem::Requirement
|
65
68
|
requirements:
|
66
69
|
- - "~>"
|
67
70
|
- !ruby/object:Gem::Version
|
68
|
-
version: '0.
|
71
|
+
version: '0.92'
|
72
|
+
- - ">="
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: 0.92.1
|
69
75
|
- !ruby/object:Gem::Dependency
|
70
|
-
name:
|
76
|
+
name: faraday_middleware
|
71
77
|
requirement: !ruby/object:Gem::Requirement
|
72
78
|
requirements:
|
73
|
-
- - "~>"
|
74
|
-
- !ruby/object:Gem::Version
|
75
|
-
version: '2.8'
|
76
79
|
- - ">="
|
77
80
|
- !ruby/object:Gem::Version
|
78
|
-
version:
|
81
|
+
version: '0'
|
79
82
|
type: :runtime
|
80
83
|
prerelease: false
|
81
84
|
version_requirements: !ruby/object:Gem::Requirement
|
82
85
|
requirements:
|
83
|
-
- - "~>"
|
84
|
-
- !ruby/object:Gem::Version
|
85
|
-
version: '2.8'
|
86
86
|
- - ">="
|
87
87
|
- !ruby/object:Gem::Version
|
88
|
-
version:
|
88
|
+
version: '0'
|
89
89
|
- !ruby/object:Gem::Dependency
|
90
90
|
name: nokogiri
|
91
91
|
requirement: !ruby/object:Gem::Requirement
|
@@ -156,6 +156,8 @@ files:
|
|
156
156
|
- lib/aranha/parsers/html/node.rb
|
157
157
|
- lib/aranha/parsers/html/node/base.rb
|
158
158
|
- lib/aranha/parsers/html/node/default.rb
|
159
|
+
- lib/aranha/parsers/html/node/default/numeric_support.rb
|
160
|
+
- lib/aranha/parsers/html/node/default/string_support.rb
|
159
161
|
- lib/aranha/parsers/invalid_state_exception.rb
|
160
162
|
- lib/aranha/parsers/json.rb
|
161
163
|
- lib/aranha/parsers/json/base.rb
|
@@ -167,6 +169,7 @@ files:
|
|
167
169
|
- lib/aranha/parsers/source_address.rb
|
168
170
|
- lib/aranha/parsers/source_address/fetch_content_error.rb
|
169
171
|
- lib/aranha/parsers/source_address/file.rb
|
172
|
+
- lib/aranha/parsers/source_address/hash_http_base.rb
|
170
173
|
- lib/aranha/parsers/source_address/hash_http_get.rb
|
171
174
|
- lib/aranha/parsers/source_address/hash_http_post.rb
|
172
175
|
- lib/aranha/parsers/source_address/http_get.rb
|