digger 0.1.6 → 0.1.7
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/digger/index.rb +13 -12
- data/lib/digger/model.rb +17 -11
- data/lib/digger/page.rb +7 -8
- data/lib/digger/pattern.rb +71 -69
- data/lib/digger/version.rb +1 -1
- data/spec/index_spec.rb +12 -0
- data/spec/pattern_spec.rb +5 -5
- metadata +3 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 2f506fd615df8b9d732d6b67bedc72644df26dc3f5725cfe5dba10c1098bae0b
|
4
|
+
data.tar.gz: 0e9afcb19ba0be5ce4a90787d54c3b43d58100bac3ec45bf5ef93781a60b6eb1
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8608a2ee8e06ddd846772d40dc3e417560229729b7b736eda8a7f50977a7d2c6fc523f86fe64480b5172c5295137eae7c85f945f7ca310502c54c8b90dd75e8d
|
7
|
+
data.tar.gz: 59fef1a13adc8f983c16428ee4d08d6ccdecea09b7583452b6ca07689727c3d6a386f5a5b767a20d117c8c4bc9775a2a6b32fd4caff1c1a5e85ee2af82e39d1b
|
data/lib/digger/index.rb
CHANGED
@@ -8,33 +8,34 @@ module Digger
|
|
8
8
|
|
9
9
|
def urls
|
10
10
|
@urls ||= begin
|
11
|
-
args = self.args.map{|a|
|
12
|
-
args.shift.product(*args).map{|arg| pattern_applied_url(arg)}
|
11
|
+
args = self.args.map { |a| a.respond_to?(:each) ? a.to_a : [a] }
|
12
|
+
args.shift.product(*args).map { |arg| pattern_applied_url(arg) }
|
13
13
|
end
|
14
14
|
end
|
15
15
|
|
16
16
|
def pattern_applied_url(arg)
|
17
|
-
pattern.gsub('*').each_with_index{|_, i| arg[i]}
|
17
|
+
pattern.gsub('*').each_with_index { |_, i| arg[i] }
|
18
18
|
end
|
19
19
|
|
20
20
|
def self.batch(entities, cocurrence = 1, &block)
|
21
|
-
raise NoBlockError,
|
21
|
+
raise NoBlockError, 'No block given' unless block
|
22
22
|
|
23
23
|
if cocurrence > 1
|
24
|
-
results =
|
25
|
-
entities.each_slice(cocurrence) do |group|
|
24
|
+
results = Array.new(entities.size)
|
25
|
+
entities.each_slice(cocurrence).with_index do |group, idx1|
|
26
26
|
threads = []
|
27
|
-
group.
|
27
|
+
group.each_with_index do |entity, idx2|
|
28
|
+
index = idx1 * cocurrence + idx2
|
28
29
|
threads << Thread.new(entity) do |ent|
|
29
|
-
results[
|
30
|
+
results[index] = block.call(ent)
|
30
31
|
end
|
31
32
|
end
|
32
|
-
threads.each
|
33
|
+
threads.each(&:join)
|
33
34
|
end
|
34
|
-
|
35
|
+
results
|
35
36
|
else
|
36
|
-
entities.map{|ent| block.call(ent) }
|
37
|
+
entities.map { |ent| block.call(ent) }
|
37
38
|
end
|
38
39
|
end
|
39
40
|
end
|
40
|
-
end
|
41
|
+
end
|
data/lib/digger/model.rb
CHANGED
@@ -1,16 +1,19 @@
|
|
1
1
|
|
2
2
|
module Digger
|
3
3
|
class Model
|
4
|
-
@@digger_config = {
|
4
|
+
@@digger_config = {
|
5
|
+
'pattern' => {},
|
6
|
+
'index' => {}
|
7
|
+
}
|
5
8
|
|
6
9
|
class << self
|
7
10
|
# patterns
|
8
11
|
def pattern_config
|
9
|
-
@@digger_config['pattern'][
|
12
|
+
@@digger_config['pattern'][name] ||= {}
|
10
13
|
end
|
11
14
|
|
12
15
|
Pattern::TYPES.each do |method|
|
13
|
-
define_method method, ->(pairs, &block){
|
16
|
+
define_method method, -> (pairs, &block) {
|
14
17
|
pairs.each_pair do |key, value|
|
15
18
|
pattern_config[key] = Pattern.new(type: method, value: value, block: block)
|
16
19
|
end
|
@@ -18,21 +21,22 @@ module Digger
|
|
18
21
|
end
|
19
22
|
|
20
23
|
def validate_presence(*keys)
|
21
|
-
|
22
|
-
raise "Pattern keys #{(keys - keys_all).join(', ')} should be present" unless
|
24
|
+
is_all = pattern_config.keys.all? { |k| keys.include?(k) }
|
25
|
+
raise "Pattern keys #{(keys - keys_all).join(', ')} should be present" unless is_all
|
23
26
|
end
|
24
27
|
|
25
28
|
def validate_includeness(*keys)
|
26
|
-
|
29
|
+
is_all = pattern_config.keys.all? { |k| keys.include?(k) }
|
30
|
+
raise "Pattern keys #{(pattern_config.keys - keys).join(', ')} should not be included" if is_all
|
27
31
|
end
|
28
32
|
|
29
33
|
# index page
|
30
34
|
def index_config
|
31
|
-
@@digger_config['index'][
|
35
|
+
@@digger_config['index'][name]
|
32
36
|
end
|
33
37
|
|
34
38
|
def index_page(pattern, *args)
|
35
|
-
|
39
|
+
@@digger_config['index'][name] = Index.new(pattern, args)
|
36
40
|
end
|
37
41
|
|
38
42
|
def index_page?
|
@@ -55,13 +59,15 @@ module Digger
|
|
55
59
|
end
|
56
60
|
|
57
61
|
def dig_urls(urls, cocurrence = 1, opts = {})
|
58
|
-
Index.batch(urls, cocurrence){|url| dig_url(url, opts) }
|
62
|
+
Index.batch(urls, cocurrence) { |url| dig_url(url, opts) }
|
59
63
|
end
|
60
64
|
|
61
65
|
def dig(cocurrence = 1)
|
62
66
|
if self.class.index_page?
|
63
|
-
self.class.index_config.process(cocurrence)
|
67
|
+
self.class.index_config.process(cocurrence) do |url|
|
68
|
+
dig_url(url)
|
69
|
+
end
|
64
70
|
end
|
65
71
|
end
|
66
72
|
end
|
67
|
-
end
|
73
|
+
end
|
data/lib/digger/page.rb
CHANGED
@@ -28,16 +28,12 @@ module Digger
|
|
28
28
|
# OpenStruct it holds users defined data
|
29
29
|
attr_accessor :user_data
|
30
30
|
|
31
|
-
attr_accessor :aliases
|
32
|
-
|
33
|
-
attr_accessor :domain_aliases
|
31
|
+
attr_accessor :aliases, :domain_aliases, :fetched_at
|
34
32
|
|
35
33
|
# Whether the current page should be stored
|
36
34
|
# Default: true
|
37
35
|
attr_accessor :storable
|
38
36
|
|
39
|
-
attr_accessor :fetched_at
|
40
|
-
|
41
37
|
#
|
42
38
|
# Create a new page
|
43
39
|
#
|
@@ -61,7 +57,7 @@ module Digger
|
|
61
57
|
end
|
62
58
|
|
63
59
|
def title
|
64
|
-
doc
|
60
|
+
doc&.title
|
65
61
|
end
|
66
62
|
|
67
63
|
#
|
@@ -75,6 +71,7 @@ module Digger
|
|
75
71
|
doc.search('//a[@href]').each do |a|
|
76
72
|
u = a['href']
|
77
73
|
next if u.nil? || u.empty?
|
74
|
+
|
78
75
|
abs = to_absolute(u) rescue next
|
79
76
|
@links << abs if abs && in_domain?(abs)
|
80
77
|
end
|
@@ -101,7 +98,7 @@ module Digger
|
|
101
98
|
end
|
102
99
|
|
103
100
|
def jsonp
|
104
|
-
@jsonp ||= JSON.parse body.match(/^[
|
101
|
+
@jsonp ||= JSON.parse body.match(/^[^(]+?\((.+)\)[^)]*$/)[1]
|
105
102
|
end
|
106
103
|
|
107
104
|
#
|
@@ -163,7 +160,7 @@ module Digger
|
|
163
160
|
# returns +false+ otherwise.
|
164
161
|
#
|
165
162
|
def not_found?
|
166
|
-
|
163
|
+
@code == 404
|
167
164
|
end
|
168
165
|
|
169
166
|
#
|
@@ -177,6 +174,7 @@ module Digger
|
|
177
174
|
end unless @base
|
178
175
|
|
179
176
|
return nil if @base && @base.to_s.empty?
|
177
|
+
|
180
178
|
@base
|
181
179
|
end
|
182
180
|
|
@@ -245,6 +243,7 @@ module Digger
|
|
245
243
|
|
246
244
|
def expired?(ttl)
|
247
245
|
return false if fetched_at.nil?
|
246
|
+
|
248
247
|
(Time.now.to_i - ttl) > fetched_at
|
249
248
|
end
|
250
249
|
|
data/lib/digger/pattern.rb
CHANGED
@@ -1,111 +1,113 @@
|
|
1
1
|
require 'nokogiri'
|
2
2
|
|
3
3
|
module Digger
|
4
|
+
# Extractor patterns definition
|
4
5
|
class Pattern
|
5
6
|
attr_accessor :type, :value, :block
|
6
7
|
|
7
8
|
def initialize(hash = {})
|
8
|
-
hash.each_pair{|key, value| send("#{key}=", value) if %w
|
9
|
+
hash.each_pair { |key, value| send("#{key}=", value) if %w[type value block].include?(key.to_s)}
|
9
10
|
end
|
10
11
|
|
11
|
-
def safe_block
|
12
|
-
block &&
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
nil
|
12
|
+
def safe_block(&default_block)
|
13
|
+
if block.nil? || (block.is_a?(String) && block.strip.empty?)
|
14
|
+
default_block
|
15
|
+
elsif block.respond_to?(:call)
|
16
|
+
block
|
17
|
+
else
|
18
|
+
proc {
|
19
|
+
$SAFE = 2
|
20
|
+
eval block
|
21
|
+
}.call
|
22
22
|
end
|
23
23
|
end
|
24
24
|
|
25
25
|
def self.wrap(hash)
|
26
|
-
|
26
|
+
hash.transform_values { |value| value.is_a?(Pattern) ? value : Pattern.new(value) }
|
27
27
|
end
|
28
28
|
|
29
29
|
MATCH_MAX = 3
|
30
30
|
|
31
|
-
TYPES_REGEXP = 0.upto(MATCH_MAX).map{|i| "match_#{i}"} + %w
|
32
|
-
TYPES_CSS = %w
|
33
|
-
TYPES_JSON = %w
|
34
|
-
|
31
|
+
TYPES_REGEXP = 0.upto(MATCH_MAX).map { |i| "match_#{i}" } + %w[match_many]
|
32
|
+
TYPES_CSS = %w[css_one css_many].freeze
|
33
|
+
TYPES_JSON = %w[json jsonp].freeze
|
34
|
+
|
35
35
|
TYPES = TYPES_REGEXP + TYPES_CSS + TYPES_JSON
|
36
36
|
|
37
|
-
def match_page(page
|
38
|
-
|
37
|
+
def match_page(page)
|
38
|
+
return unless page.success?
|
39
39
|
if TYPES_REGEXP.include?(type) # regular expression
|
40
|
-
|
41
|
-
# content is String
|
42
|
-
if type == 'match_many'
|
43
|
-
match = page.body.gsub(value).to_a
|
44
|
-
else
|
45
|
-
index = TYPES_REGEXP.index(type)
|
46
|
-
matches = page.body.match(value)
|
47
|
-
match = matches.nil? ? nil : matches[index]
|
48
|
-
end
|
40
|
+
regexp_match(page.body)
|
49
41
|
elsif TYPES_CSS.include?(type) # css expression
|
50
|
-
|
51
|
-
# content is Nokogiri::HTML::Document
|
52
|
-
if type == 'css_one'
|
53
|
-
match = page.doc.css(value).first
|
54
|
-
else
|
55
|
-
match = page.doc.css(value)
|
56
|
-
end
|
42
|
+
css_match(page.doc)
|
57
43
|
elsif TYPES_JSON.include?(type)
|
58
|
-
|
59
|
-
|
44
|
+
json_match(page)
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
def json_match(page)
|
49
|
+
block = safe_block { |j| j }
|
50
|
+
json = page.send(type)
|
51
|
+
keys = json_index_keys(value)
|
52
|
+
match = json_fetch(json, keys)
|
53
|
+
block.call(match)
|
54
|
+
end
|
55
|
+
|
56
|
+
def css_match(doc)
|
57
|
+
block = safe_block { |node| node.content.strip }
|
58
|
+
# content is Nokogiri::HTML::Document
|
59
|
+
contents = doc.css(value)
|
60
|
+
if type == 'css_many'
|
61
|
+
contents.map { |node| block.call(node) }.uniq
|
62
|
+
else
|
63
|
+
block.call(contents.first)
|
60
64
|
end
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
+
end
|
66
|
+
|
67
|
+
def regexp_match(body)
|
68
|
+
block = safe_block(&:strip)
|
69
|
+
# content is String
|
70
|
+
if type == 'match_many'
|
71
|
+
body.gsub(value).to_a.map { |node| block.call(node) }.uniq
|
65
72
|
else
|
66
|
-
|
73
|
+
index = TYPES_REGEXP.index(type)
|
74
|
+
matches = body.match(value)
|
75
|
+
block.call(matches[index]) unless matches.nil?
|
67
76
|
end
|
68
|
-
rescue
|
69
|
-
nil
|
70
77
|
end
|
71
78
|
|
72
79
|
def json_fetch(json, keys)
|
73
|
-
if keys.
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
json_fetch(json, parts)
|
79
|
-
elsif keys.is_a? Array
|
80
|
-
if keys.length == 0
|
81
|
-
json
|
82
|
-
else
|
83
|
-
pt = keys.shift
|
84
|
-
json_fetch(json[pt[:index] || pt[:key]], keys)
|
85
|
-
end
|
80
|
+
if keys.empty?
|
81
|
+
json
|
82
|
+
else
|
83
|
+
pt = keys.shift
|
84
|
+
json_fetch(json[pt[:index] || pt[:key]], keys)
|
86
85
|
end
|
87
86
|
end
|
88
87
|
|
88
|
+
def json_index_keys(keys)
|
89
|
+
keys.to_s.match(/^\$\S*$/)[0].scan(/(\.(\w+)|\[(\d+)\])/).map do |p|
|
90
|
+
p[1].nil? ? { index: p[2].to_i } : { key: p[1] }
|
91
|
+
end
|
92
|
+
end
|
93
|
+
|
94
|
+
private :json_index_keys, :json_fetch
|
95
|
+
|
96
|
+
# Nokogiri node methods
|
89
97
|
class Nokogiri::XML::Node
|
90
|
-
%w
|
91
|
-
define_method "inner_#{name}" do |css, &block|
|
92
|
-
callback = ->(node)
|
93
|
-
if node
|
94
|
-
(block || ->(n){n.text.strip}).call(node)
|
95
|
-
else
|
96
|
-
nil
|
97
|
-
end
|
98
|
-
end
|
98
|
+
%w[one many].each do |name|
|
99
|
+
define_method "inner_#{name}" do |css, &block|
|
100
|
+
callback = ->(node) { (block || ->(n) { n.text.strip }).call(node) if node }
|
99
101
|
if name == 'one' # inner_one
|
100
102
|
callback.call(self.css(css).first)
|
101
103
|
else # inner_many
|
102
|
-
self.css(css).map{|node| callback.call(node)}
|
104
|
+
self.css(css).map { |node| callback.call(node) }
|
103
105
|
end
|
104
106
|
end
|
105
107
|
end
|
106
108
|
def source
|
107
109
|
to_xml
|
108
110
|
end
|
109
|
-
end
|
111
|
+
end
|
110
112
|
end
|
111
|
-
end
|
113
|
+
end
|
data/lib/digger/version.rb
CHANGED
data/spec/index_spec.rb
ADDED
@@ -0,0 +1,12 @@
|
|
1
|
+
require 'digger'
|
2
|
+
|
3
|
+
describe Digger::Index do
|
4
|
+
it 'batch digger' do
|
5
|
+
list = [1, 2, 3, 4, 5, 6, 7, 8]
|
6
|
+
pt = Digger::Index.batch(list, 3) do |num|
|
7
|
+
sleep(rand(1..3))
|
8
|
+
"##{num}"
|
9
|
+
end
|
10
|
+
expect(pt.join).to eq(list.map { |num| "##{num}" }.join)
|
11
|
+
end
|
12
|
+
end
|
data/spec/pattern_spec.rb
CHANGED
@@ -3,12 +3,12 @@ require 'json'
|
|
3
3
|
|
4
4
|
describe Digger::Pattern do
|
5
5
|
it 'json fetch' do
|
6
|
-
json = JSON.parse('{"a":1,"b":[1,2,3]}')
|
6
|
+
json = JSON.parse('[{"a":1,"b":[1,2,3]}]')
|
7
7
|
pt = Digger::Pattern.new
|
8
|
-
expect(pt.json_fetch(json, '$')['a']).to eq(1)
|
9
|
-
expect(pt.json_fetch(json, '
|
10
|
-
expect(pt.json_fetch(json, '
|
11
|
-
expect(pt.json_fetch(json, '
|
8
|
+
expect(pt.json_fetch(json, '$[0]')['a']).to eq(1)
|
9
|
+
expect(pt.json_fetch(json, '$[0].a')).to eq(1)
|
10
|
+
expect(pt.json_fetch(json, '$[0].b').length).to eq(3)
|
11
|
+
expect(pt.json_fetch(json, '$[0].b[2]')).to eq(3)
|
12
12
|
end
|
13
13
|
|
14
14
|
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: digger
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.7
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- binz
|
@@ -87,6 +87,7 @@ files:
|
|
87
87
|
- lib/digger/pattern.rb
|
88
88
|
- lib/digger/version.rb
|
89
89
|
- spec/digger_spec.rb
|
90
|
+
- spec/index_spec.rb
|
90
91
|
- spec/page_spec.rb
|
91
92
|
- spec/pattern_spec.rb
|
92
93
|
- spec/validate_spec.rb
|
@@ -115,6 +116,7 @@ specification_version: 4
|
|
115
116
|
summary: Dig need stractual infomation from web page.
|
116
117
|
test_files:
|
117
118
|
- spec/digger_spec.rb
|
119
|
+
- spec/index_spec.rb
|
118
120
|
- spec/page_spec.rb
|
119
121
|
- spec/pattern_spec.rb
|
120
122
|
- spec/validate_spec.rb
|