bitreaper 0.1.2 → 0.1.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/bitreaper.rb +27 -29
- metadata +114 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 8099d3d4a818b30b2ac24729cc564e0f30ca282fa0dd169961b4440f74e53d87
|
4
|
+
data.tar.gz: 507a81e5d915195358dc62c1cc8fddc86565778b97d02bf2cefe4951748d64f7
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: a89b5f7e9c6e5bb7bbd019a3cab051a5ceea8f3cd5c195ab1a95c7a3c776279567180918ad3aebb4cd911d83d5ea80bc464e3661cb4314200433d3e5d483af7c
|
7
|
+
data.tar.gz: 07ad9cecd4e25faca388ce8e3fe05612a748189873f17acf21b07560099d1af8dff0acbc3ffe3556f99a1e6356c18a1b88fb54b7c7089fb9210112dcc127b7cd
|
data/lib/bitreaper.rb
CHANGED
@@ -17,31 +17,24 @@ require 'liquid'
|
|
17
17
|
require 'nokogiri'
|
18
18
|
require 'open-uri'
|
19
19
|
require 'sdl4r'
|
20
|
-
require 'watir'
|
21
|
-
require 'webdrivers'
|
22
20
|
|
23
21
|
require_relative 'bitreaper/helpers.rb'
|
24
22
|
|
25
|
-
|
26
|
-
# SUPERGLOBALS
|
27
|
-
##########################################
|
23
|
+
$bitreaper_version = "0.1.3"
|
28
24
|
|
29
|
-
|
30
|
-
|
31
|
-
####################################################################################
|
32
|
-
# **MAIN CLASS**
|
25
|
+
##
|
33
26
|
# This is the main Web Scraper object. It is through a `BitScraper` instance
|
34
27
|
# that you can start scraping
|
35
|
-
####################################################################################
|
36
28
|
|
37
29
|
class BitReaper
|
38
30
|
|
31
|
+
##
|
39
32
|
# Create a new BitReaper instance
|
40
33
|
#
|
41
34
|
# @param [String] url The URL of the page to be scraped
|
42
35
|
# @param [String,SDL4R::Tag] parser The parser
|
43
36
|
# @param [Integer] i Index of the current operation (for reporting purposes)
|
44
|
-
|
37
|
+
|
45
38
|
def initialize(url,parser,i=0)
|
46
39
|
@url = url
|
47
40
|
@parser = (parser.is_a? String) ? self.getParser(parser) : parser
|
@@ -52,12 +45,13 @@ class BitReaper
|
|
52
45
|
@noko = self.download(@url)
|
53
46
|
end
|
54
47
|
|
48
|
+
##
|
55
49
|
# Get a new parser from a given parser path
|
56
50
|
#
|
57
51
|
# @param [String] file The path of the `.br` parser file
|
58
52
|
#
|
59
53
|
# @return [SDL4R::Tag] The resulting parser
|
60
|
-
|
54
|
+
|
61
55
|
def self.getParser(file)
|
62
56
|
parserFile = File.read(file)
|
63
57
|
parserFile = parserFile.gsub(/([\w]+)\!\s/,'\1=on')
|
@@ -69,30 +63,20 @@ class BitReaper
|
|
69
63
|
return SDL4R::read(parserFile)
|
70
64
|
end
|
71
65
|
|
72
|
-
|
73
|
-
#---------------------------------------------------------------------------
|
74
|
-
def process
|
75
|
-
printProgress(@url,@index,1)
|
76
|
-
processNode(@noko, @parser, @store)
|
77
|
-
|
78
|
-
printProgress(@url,@index,2)
|
79
|
-
return @store
|
80
|
-
end
|
81
|
-
|
82
|
-
private
|
83
|
-
|
66
|
+
##
|
84
67
|
# Download given URL
|
85
68
|
#
|
86
69
|
# @param [String] url The URL to be downloaded
|
87
70
|
#
|
88
71
|
# @return [Nokogiri::XML::NodeSet] The resulting nodes
|
89
|
-
|
72
|
+
|
90
73
|
def download(url,withProgress=true)
|
91
74
|
printProgress(@url,@index,0) if withProgress
|
92
75
|
|
93
76
|
return Nokogiri::HTML(open(url))
|
94
77
|
end
|
95
78
|
|
79
|
+
##
|
96
80
|
# Process String value using attribute
|
97
81
|
#
|
98
82
|
# @param [String] attrb The attribute to be processed
|
@@ -100,7 +84,7 @@ class BitReaper
|
|
100
84
|
# @param [String] param The attribute's param (if any)
|
101
85
|
#
|
102
86
|
# @return [String,Array] The result of the operation
|
103
|
-
|
87
|
+
|
104
88
|
def processStringValue(attrb,val,param)
|
105
89
|
case attrb
|
106
90
|
when "prepend"
|
@@ -128,6 +112,7 @@ class BitReaper
|
|
128
112
|
return val
|
129
113
|
end
|
130
114
|
|
115
|
+
##
|
131
116
|
# Process Array value using attribute
|
132
117
|
#
|
133
118
|
# @param [String] attrb The attribute to be processed
|
@@ -135,7 +120,7 @@ class BitReaper
|
|
135
120
|
# @param [String] param The attribute's param (if any)
|
136
121
|
#
|
137
122
|
# @return [String,Array] The result of the operation
|
138
|
-
|
123
|
+
|
139
124
|
def processArrayValue(attrb,val,param)
|
140
125
|
case attrb
|
141
126
|
when "join"
|
@@ -162,13 +147,14 @@ class BitReaper
|
|
162
147
|
return val
|
163
148
|
end
|
164
149
|
|
150
|
+
##
|
165
151
|
# Process parsed values using set of attributes
|
166
152
|
#
|
167
153
|
# @param [Array] values The parsed values
|
168
154
|
# @param [Array] attrbs The associated attributes
|
169
155
|
#
|
170
156
|
# @return [String,Array] The result of the operation
|
171
|
-
|
157
|
+
|
172
158
|
def processValues(values,attrbs)
|
173
159
|
# check if we have a single value or an array of values
|
174
160
|
ret = (values.count==1) ? values[0].content
|
@@ -197,13 +183,14 @@ class BitReaper
|
|
197
183
|
return (ret.nil?) ? "" : ret
|
198
184
|
end
|
199
185
|
|
186
|
+
##
|
200
187
|
# Process a given node using provided parser and temporary storage hash
|
201
188
|
#
|
202
189
|
# @param [Nokogiri::XML::node] noko The Nokogiri node to work on
|
203
190
|
# @param [SDL4R::Tag] node The parser node
|
204
191
|
# @param [Hash] store The temporary storage hash
|
205
192
|
# @param [Integer] level The nesting level (for informational purposes)
|
206
|
-
|
193
|
+
|
207
194
|
def processNode(noko,node,store,level=0)
|
208
195
|
node.children.each{|child|
|
209
196
|
command = child.namespace
|
@@ -231,6 +218,17 @@ class BitReaper
|
|
231
218
|
}
|
232
219
|
end
|
233
220
|
|
221
|
+
##
|
222
|
+
# Process current project
|
223
|
+
|
224
|
+
def process
|
225
|
+
printProgress(@url,@index,1)
|
226
|
+
processNode(@noko, @parser, @store)
|
227
|
+
|
228
|
+
printProgress(@url,@index,2)
|
229
|
+
return @store
|
230
|
+
end
|
231
|
+
|
234
232
|
end
|
235
233
|
|
236
234
|
#######################################################
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: bitreaper
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Dr.Kameleon
|
@@ -9,7 +9,119 @@ autorequire:
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
date: 2020-04-09 00:00:00.000000000 Z
|
12
|
-
dependencies:
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: awesome_print
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: colorize
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: down
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: fileutils
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: json
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: liquid
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :runtime
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: nokogiri
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - ">="
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :runtime
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - ">="
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: sdl4r
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - ">="
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
type: :runtime
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - ">="
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '0'
|
13
125
|
description: Automated Web-Scraping Client for Ruby using SLD2-like configuration
|
14
126
|
files. Supports XPath and CSS selectors via Nokogiri.
|
15
127
|
email: drkameleon@gmail.com
|