apollo-crawler 0.0.44 → 0.0.45
Sign up to get free protection for your applications and to get access to all the features.
- data/bin/apollo-crawler +48 -48
- data/lib/apollo_crawler.rb +6 -9
- data/lib/apollo_crawler/crawler.rb +77 -0
- data/lib/apollo_crawler/{plugin_template.rb → crawler_template.rb} +6 -7
- data/lib/apollo_crawler/{plugins → crawlers}/alexa_com/alexa.rb +4 -4
- data/lib/apollo_crawler/{plugins → crawlers}/firmy_cz/firmy.rb +4 -4
- data/lib/apollo_crawler/{plugins → crawlers}/slashdot_org/slashdot.rb +4 -4
- data/lib/apollo_crawler/{plugins → crawlers}/stackoverflow_com/stackoverflow.rb +5 -5
- data/lib/apollo_crawler/{plugins → crawlers}/xkcd_com/xkcd.rb +4 -4
- data/lib/apollo_crawler/{plugins → crawlers}/ycombinator_com/hacker_news.rb +4 -4
- data/lib/apollo_crawler/version.rb +1 -1
- metadata +26 -11
- data/lib/apollo_crawler/plugin.rb +0 -73
data/bin/apollo-crawler
CHANGED
@@ -24,22 +24,22 @@ require File.join(File.dirname(__FILE__), '..', 'lib', 'apollo_crawler', 'versio
|
|
24
24
|
|
25
25
|
module Crawler
|
26
26
|
class Program
|
27
|
-
@@
|
27
|
+
@@CRAWLERS_DIR = File.join(File.dirname(__FILE__), "..", "lib", "apollo_crawler", "crawlers")
|
28
28
|
@@FORMATTERS_DIR = File.join(File.dirname(__FILE__), "..", "lib", "apollo_crawler", "formatters")
|
29
|
-
@@
|
29
|
+
@@CRAWLER_TEMPLATE_NAME = "crawler_template.rb"
|
30
30
|
|
31
31
|
# This hash will hold all of the options
|
32
32
|
# parsed from the command-line by
|
33
33
|
# OptionParser.
|
34
34
|
@options = nil
|
35
35
|
@optparser = nil
|
36
|
-
@
|
36
|
+
@crawlers = nil
|
37
37
|
@formatters = nil
|
38
38
|
@formatter = nil
|
39
39
|
|
40
40
|
# Initializer - Constructor
|
41
41
|
def initialize
|
42
|
-
@
|
42
|
+
@crawlers = {}
|
43
43
|
@formatters = {}
|
44
44
|
end
|
45
45
|
|
@@ -48,13 +48,13 @@ module Crawler
|
|
48
48
|
@options = {}
|
49
49
|
@options[:verbose] = false
|
50
50
|
@options[:version] = false
|
51
|
-
@options[:
|
52
|
-
@@
|
51
|
+
@options[:crawler_dirs] = [
|
52
|
+
@@CRAWLERS_DIR
|
53
53
|
]
|
54
54
|
@options[:formatter_dirs] = [
|
55
55
|
@@FORMATTERS_DIR
|
56
56
|
]
|
57
|
-
@options[:
|
57
|
+
@options[:generate_crawler] = nil
|
58
58
|
|
59
59
|
@optparser = OptionParser.new do | opts |
|
60
60
|
# This displays the help screen, all programs are
|
@@ -64,7 +64,7 @@ module Crawler
|
|
64
64
|
exit
|
65
65
|
end
|
66
66
|
|
67
|
-
opts.on('-a', '--all', 'Run all
|
67
|
+
opts.on('-a', '--all', 'Run all crawlers') do
|
68
68
|
@options[:run_all] = true
|
69
69
|
end
|
70
70
|
|
@@ -72,12 +72,12 @@ module Crawler
|
|
72
72
|
@options[:formatter] = name
|
73
73
|
end
|
74
74
|
|
75
|
-
opts.on('-g', '--generate [NAME]', "Generate scaffold for new
|
76
|
-
@options[:
|
75
|
+
opts.on('-g', '--generate [NAME]', "Generate scaffold for new crawler") do |name|
|
76
|
+
@options[:generate_crawler] = name
|
77
77
|
end
|
78
78
|
|
79
|
-
opts.on('-i', '--include [PATH]', 'Include additional
|
80
|
-
@options[:
|
79
|
+
opts.on('-i', '--include [PATH]', 'Include additional crawler or crawler directory') do |path|
|
80
|
+
@options[:crawler_dirs] << path
|
81
81
|
end
|
82
82
|
|
83
83
|
opts.on('-v', '--verbose', 'Enable verbose output') do
|
@@ -88,8 +88,8 @@ module Crawler
|
|
88
88
|
@options[:version] = true
|
89
89
|
end
|
90
90
|
|
91
|
-
opts.on('-l', '--list-
|
92
|
-
@options[:
|
91
|
+
opts.on('-l', '--list-crawlers', 'List of crawlers') do
|
92
|
+
@options[:list_crawlers] = true
|
93
93
|
end
|
94
94
|
|
95
95
|
opts.on(nil, '--list-formatters', 'List of formatters available') do
|
@@ -163,10 +163,10 @@ module Crawler
|
|
163
163
|
end
|
164
164
|
end
|
165
165
|
|
166
|
-
# Register
|
167
|
-
def
|
166
|
+
# Register crawlers
|
167
|
+
def register_crawlers(dir)
|
168
168
|
if(@options[:verbose])
|
169
|
-
puts "Registering
|
169
|
+
puts "Registering crawlers - '#{dir}'"
|
170
170
|
end
|
171
171
|
|
172
172
|
files = File.join(dir, "**", "*.rb")
|
@@ -174,36 +174,36 @@ module Crawler
|
|
174
174
|
require file
|
175
175
|
end
|
176
176
|
|
177
|
-
tmp = Apollo::Crawler::
|
178
|
-
Class === Apollo::Crawler::
|
177
|
+
tmp = Apollo::Crawler::Crawlers.constants.select { |c|
|
178
|
+
Class === Apollo::Crawler::Crawlers.const_get(c)
|
179
179
|
}
|
180
180
|
|
181
181
|
tmp.each do |x|
|
182
|
-
klass = Object.const_get('Apollo').const_get('Crawler').const_get('
|
183
|
-
@
|
182
|
+
klass = Object.const_get('Apollo').const_get('Crawler').const_get('Crawlers').const_get(x)
|
183
|
+
@crawlers.merge!({ x.downcase.to_s => klass})
|
184
184
|
end
|
185
185
|
|
186
186
|
if(@options[:verbose])
|
187
|
-
@
|
187
|
+
@crawlers.each do |crawler, klass|
|
188
188
|
name = klass.new.class.name
|
189
189
|
|
190
|
-
if name == "Apollo::Crawler::
|
190
|
+
if name == "Apollo::Crawler::Crawlers::Crawler"
|
191
191
|
next
|
192
192
|
end
|
193
193
|
|
194
|
-
puts "Registered
|
194
|
+
puts "Registered crawler '#{crawler}' -> '#{name}'"
|
195
195
|
end
|
196
196
|
end
|
197
197
|
end
|
198
198
|
|
199
|
-
def
|
199
|
+
def generate_crawler(name, url = nil, matcher = nil)
|
200
200
|
name = name.titleize.gsub(" ", "")
|
201
201
|
|
202
202
|
if(@options[:verbose])
|
203
|
-
puts "Generating new
|
203
|
+
puts "Generating new crawler '#{name}'"
|
204
204
|
end
|
205
205
|
|
206
|
-
template_path = File.join(File.dirname(__FILE__), '..', 'lib', 'apollo_crawler', @@
|
206
|
+
template_path = File.join(File.dirname(__FILE__), '..', 'lib', 'apollo_crawler', @@CRAWLER_TEMPLATE_NAME)
|
207
207
|
if(File.exists?(template_path) == false)
|
208
208
|
puts "Template file '#{template_path}' does not exists!"
|
209
209
|
return
|
@@ -219,23 +219,23 @@ module Crawler
|
|
219
219
|
matcher = matcher ? matcher : "//a"
|
220
220
|
|
221
221
|
placeholders = {
|
222
|
-
"
|
223
|
-
"
|
224
|
-
"
|
225
|
-
"
|
222
|
+
"CRAWLER_CLASS_NAME" => name,
|
223
|
+
"CRAWLER_NAME" => name.titleize,
|
224
|
+
"CRAWLER_URL" => url,
|
225
|
+
"CRAWLER_MATCHER" => matcher
|
226
226
|
}
|
227
227
|
|
228
|
-
puts "Generating
|
228
|
+
puts "Generating crawler '#{name.titleize}', class: '#{name}', path: '#{dest_path}'"
|
229
229
|
|
230
230
|
File.open(template_path, 'r') do |tmpl|
|
231
|
-
File.open(dest_path, 'w') do |
|
231
|
+
File.open(dest_path, 'w') do |crawler|
|
232
232
|
while line = tmpl.gets
|
233
233
|
#puts line
|
234
234
|
placeholders.each do |k, v|
|
235
235
|
line.gsub!(k, v)
|
236
236
|
end
|
237
237
|
|
238
|
-
|
238
|
+
crawler.puts line
|
239
239
|
end
|
240
240
|
end
|
241
241
|
end
|
@@ -253,18 +253,18 @@ module Crawler
|
|
253
253
|
|
254
254
|
load_config_file()
|
255
255
|
|
256
|
-
if(@options[:
|
257
|
-
name = @options[:
|
256
|
+
if(@options[:generate_crawler])
|
257
|
+
name = @options[:generate_crawler]
|
258
258
|
url = ARGV.length > 0 ? ARGV[0] : nil
|
259
259
|
matcher = ARGV.length > 1 ? ARGV[1] : nil
|
260
260
|
|
261
|
-
self.
|
261
|
+
self.generate_crawler(name, url, matcher)
|
262
262
|
exit
|
263
263
|
end
|
264
264
|
|
265
265
|
# Register sites which can be crawled
|
266
|
-
@options[:
|
267
|
-
|
266
|
+
@options[:crawler_dirs].each do |dir|
|
267
|
+
register_crawlers(dir)
|
268
268
|
end
|
269
269
|
|
270
270
|
# Register sites which can be crawled
|
@@ -298,9 +298,9 @@ module Crawler
|
|
298
298
|
return
|
299
299
|
end
|
300
300
|
|
301
|
-
if(@options[:
|
301
|
+
if(@options[:list_crawlers])
|
302
302
|
headings = ['name', 'class']
|
303
|
-
rows = @
|
303
|
+
rows = @crawlers
|
304
304
|
|
305
305
|
table = Terminal::Table.new :headings => headings, :rows => rows
|
306
306
|
|
@@ -308,27 +308,27 @@ module Crawler
|
|
308
308
|
return
|
309
309
|
end
|
310
310
|
|
311
|
-
|
311
|
+
crawlers = ARGV
|
312
312
|
|
313
313
|
if(@options[:run_all])
|
314
|
-
|
314
|
+
crawlers = @crawlers.keys
|
315
315
|
end
|
316
316
|
|
317
|
-
if(
|
317
|
+
if(crawlers.empty?)
|
318
318
|
puts @optparser
|
319
319
|
exit
|
320
320
|
end
|
321
321
|
|
322
|
-
|
323
|
-
p = @
|
322
|
+
crawlers.each do |crawler|
|
323
|
+
p = @crawlers[crawler.downcase]
|
324
324
|
if(p == nil)
|
325
|
-
puts "Invalid
|
325
|
+
puts "Invalid crawler name - '#{crawler}'"
|
326
326
|
puts "See program help"
|
327
327
|
next
|
328
328
|
end
|
329
329
|
|
330
330
|
if(@options[:verbose])
|
331
|
-
puts "Running '#{
|
331
|
+
puts "Running '#{crawler}'"
|
332
332
|
end
|
333
333
|
|
334
334
|
res = p.new.etl
|
data/lib/apollo_crawler.rb
CHANGED
@@ -1,16 +1,13 @@
|
|
1
|
-
# require 'apollo_crawler/plugin'
|
2
|
-
|
3
1
|
require 'apollo_crawler/crawler'
|
4
2
|
require 'apollo_crawler/formatter'
|
5
|
-
|
3
|
+
|
4
|
+
# Crawlers
|
5
|
+
require 'apollo_crawler/crawlers/alexa_com/alexa'
|
6
|
+
require 'apollo_crawler/crawlers/firmy_cz/firmy'
|
7
|
+
require 'apollo_crawler/crawlers/slashdot_org/slashdot'
|
8
|
+
require 'apollo_crawler/crawlers/ycombinator_com/hacker_news'
|
6
9
|
|
7
10
|
# Formatters
|
8
11
|
require 'apollo_crawler/formatters/formatter_json'
|
9
12
|
require 'apollo_crawler/formatters/formatter_plain'
|
10
13
|
require 'apollo_crawler/formatters/formatter_table'
|
11
|
-
|
12
|
-
# Plugins
|
13
|
-
require 'apollo_crawler/plugins/alexa_com/alexa'
|
14
|
-
require 'apollo_crawler/plugins/firmy_cz/firmy'
|
15
|
-
require 'apollo_crawler/plugins/slashdot_org/slashdot'
|
16
|
-
require 'apollo_crawler/plugins/ycombinator_com/hacker_news'
|
@@ -0,0 +1,77 @@
|
|
1
|
+
require "open-uri"
|
2
|
+
require "nokogiri"
|
3
|
+
|
4
|
+
module Apollo
|
5
|
+
module Crawler
|
6
|
+
module Crawlers
|
7
|
+
class Crawler
|
8
|
+
|
9
|
+
# Name of the crawler
|
10
|
+
def name
|
11
|
+
return "Crawler Base"
|
12
|
+
end
|
13
|
+
|
14
|
+
def url
|
15
|
+
return nil
|
16
|
+
end
|
17
|
+
|
18
|
+
# - (0) Figure out URL
|
19
|
+
# - (1) Extract Data
|
20
|
+
# - (2) Extract Links
|
21
|
+
# - (3) Go to (0) eventually
|
22
|
+
def etl(url=nil)
|
23
|
+
# Look for passed URL use default instead and fail if it is not valid
|
24
|
+
url = url ? url : self.url
|
25
|
+
if(url.nil?)
|
26
|
+
return nil
|
27
|
+
end
|
28
|
+
|
29
|
+
# Try fetch document
|
30
|
+
doc = self.fetch_document(url)
|
31
|
+
if(doc.nil?)
|
32
|
+
return nil
|
33
|
+
end
|
34
|
+
|
35
|
+
# Try extract data from document
|
36
|
+
data = self.extract_data(doc)
|
37
|
+
|
38
|
+
# Try extract links for another documents
|
39
|
+
links = self.extract_links(doc)
|
40
|
+
|
41
|
+
# Return ETL result
|
42
|
+
return {
|
43
|
+
:crawler => self.class.name,
|
44
|
+
:title => doc.title,
|
45
|
+
:data => data,
|
46
|
+
:links => links
|
47
|
+
}
|
48
|
+
end
|
49
|
+
|
50
|
+
# Fetch document
|
51
|
+
def fetch_document(url)
|
52
|
+
ic = Iconv.new("UTF-8//IGNORE", "UTF-8")
|
53
|
+
|
54
|
+
if(self.url.nil?)
|
55
|
+
return nil
|
56
|
+
end
|
57
|
+
|
58
|
+
# TODO: Encapsulate and make more robust => invalid hostname, timeouts and so
|
59
|
+
doc = Nokogiri::HTML(ic.iconv(open(self.url).read))
|
60
|
+
return doc
|
61
|
+
end
|
62
|
+
|
63
|
+
# Extracts data from document
|
64
|
+
def extract_data(doc)
|
65
|
+
res = []
|
66
|
+
return res
|
67
|
+
end
|
68
|
+
|
69
|
+
# Extract links to another documents from this document
|
70
|
+
def extract_links(doc)
|
71
|
+
res = []
|
72
|
+
return res
|
73
|
+
end
|
74
|
+
end
|
75
|
+
end
|
76
|
+
end
|
77
|
+
end
|
@@ -2,17 +2,16 @@ require 'iconv'
|
|
2
2
|
|
3
3
|
module Apollo
|
4
4
|
module Crawler
|
5
|
-
module
|
6
|
-
|
7
|
-
|
8
|
-
@@MATCHER_ITEM = "PLUGIN_MATCHER"
|
5
|
+
module Crawlers
|
6
|
+
class CRAWLER_CLASS_NAME < Apollo::Crawler::Crawlers::Crawler
|
7
|
+
@@MATCHER_ITEM = "CRAWLER_MATCHER"
|
9
8
|
|
10
9
|
def name()
|
11
|
-
return "
|
10
|
+
return "CRAWLER_NAME"
|
12
11
|
end
|
13
12
|
|
14
13
|
def url()
|
15
|
-
return "
|
14
|
+
return "CRAWLER_URL"
|
16
15
|
end
|
17
16
|
|
18
17
|
def extract_data(doc)
|
@@ -24,6 +23,6 @@ module Apollo
|
|
24
23
|
}
|
25
24
|
end
|
26
25
|
end
|
27
|
-
end #
|
26
|
+
end # Crawlers
|
28
27
|
end # Crawler
|
29
28
|
end # Apollo
|
@@ -1,11 +1,11 @@
|
|
1
1
|
require 'iconv'
|
2
2
|
|
3
|
-
require File.join(File.dirname(__FILE__), '..', '..', '
|
3
|
+
require File.join(File.dirname(__FILE__), '..', '..', 'crawler')
|
4
4
|
|
5
5
|
module Apollo
|
6
6
|
module Crawler
|
7
|
-
module
|
8
|
-
class Alexa <
|
7
|
+
module Crawlers
|
8
|
+
class Alexa < Apollo::Crawler::Crawlers::Crawler
|
9
9
|
@@MATCHER_ITEM = "//div[@id = 'alphabetically']/ul/li/a"
|
10
10
|
|
11
11
|
def name()
|
@@ -25,6 +25,6 @@ module Apollo
|
|
25
25
|
}
|
26
26
|
end
|
27
27
|
end
|
28
|
-
end #
|
28
|
+
end # Crawlers
|
29
29
|
end # Crawler
|
30
30
|
end # Apollo
|
@@ -1,11 +1,11 @@
|
|
1
1
|
require 'iconv'
|
2
2
|
|
3
|
-
require File.join(File.dirname(__FILE__), '..', '..', '
|
3
|
+
require File.join(File.dirname(__FILE__), '..', '..', 'crawler')
|
4
4
|
|
5
5
|
module Apollo
|
6
6
|
module Crawler
|
7
|
-
module
|
8
|
-
class Firmy <
|
7
|
+
module Crawlers
|
8
|
+
class Firmy < Apollo::Crawler::Crawlers::Crawler
|
9
9
|
@@MATCHER_ITEM = "//div[@id = 'alphabetically']/ul/li/a"
|
10
10
|
|
11
11
|
def name()
|
@@ -25,6 +25,6 @@ module Apollo
|
|
25
25
|
}
|
26
26
|
end
|
27
27
|
end
|
28
|
-
end #
|
28
|
+
end # Crawlers
|
29
29
|
end # Crawler
|
30
30
|
end # Apollo
|
@@ -1,11 +1,11 @@
|
|
1
1
|
require 'iconv'
|
2
2
|
|
3
|
-
require File.join(File.dirname(__FILE__), '..', '..', '
|
3
|
+
require File.join(File.dirname(__FILE__), '..', '..', 'crawler')
|
4
4
|
|
5
5
|
module Apollo
|
6
6
|
module Crawler
|
7
|
-
module
|
8
|
-
class Slashdot <
|
7
|
+
module Crawlers
|
8
|
+
class Slashdot < Apollo::Crawler::Crawlers::Crawler
|
9
9
|
@@MATCHER_ITEM = "//article/header/h2/span/a"
|
10
10
|
|
11
11
|
def name
|
@@ -25,6 +25,6 @@ module Apollo
|
|
25
25
|
}
|
26
26
|
end
|
27
27
|
end
|
28
|
-
end #
|
28
|
+
end # Crawlers
|
29
29
|
end # Crawler
|
30
30
|
end # Apollo
|
@@ -1,11 +1,11 @@
|
|
1
1
|
require 'iconv'
|
2
2
|
|
3
|
-
require File.join(File.dirname(__FILE__), '..', '..', '
|
3
|
+
require File.join(File.dirname(__FILE__), '..', '..', 'crawler')
|
4
4
|
|
5
5
|
module Apollo
|
6
|
-
module
|
7
|
-
module
|
8
|
-
class StackOverflow <
|
6
|
+
module Crawlers
|
7
|
+
module Crawler
|
8
|
+
class StackOverflow < Apollo::Crawler::Crawlers::Crawler
|
9
9
|
@@MATCHER_ITEM = "//div[@class = 'summary']/h3/a"
|
10
10
|
|
11
11
|
def name
|
@@ -25,6 +25,6 @@ module Apollo
|
|
25
25
|
}
|
26
26
|
end
|
27
27
|
end
|
28
|
-
end #
|
28
|
+
end # Crawlers
|
29
29
|
end # Crawler
|
30
30
|
end # Apollo
|
@@ -1,11 +1,11 @@
|
|
1
1
|
require 'iconv'
|
2
2
|
|
3
|
-
require File.join(File.dirname(__FILE__), '..', '..', '
|
3
|
+
require File.join(File.dirname(__FILE__), '..', '..', 'crawler')
|
4
4
|
|
5
5
|
module Apollo
|
6
6
|
module Crawler
|
7
|
-
module
|
8
|
-
class Xkcd <
|
7
|
+
module Crawlers
|
8
|
+
class Xkcd < Apollo::Crawler::Crawlers::Crawler
|
9
9
|
@@MATCHER_ITEM = "//div[@id = 'comic']/img"
|
10
10
|
|
11
11
|
def name()
|
@@ -25,6 +25,6 @@ module Apollo
|
|
25
25
|
}
|
26
26
|
end
|
27
27
|
end
|
28
|
-
end #
|
28
|
+
end # Crawlers
|
29
29
|
end # Crawler
|
30
30
|
end # Apollo
|
@@ -1,11 +1,11 @@
|
|
1
1
|
require 'iconv'
|
2
2
|
|
3
|
-
require File.join(File.dirname(__FILE__), '..', '..', '
|
3
|
+
require File.join(File.dirname(__FILE__), '..', '..', 'crawler')
|
4
4
|
|
5
5
|
module Apollo
|
6
6
|
module Crawler
|
7
|
-
module
|
8
|
-
class HackerNews <
|
7
|
+
module Crawlers
|
8
|
+
class HackerNews < Apollo::Crawler::Crawlers::Crawler
|
9
9
|
@@MATCHER_ITEM = "//td[@class = 'title']/a"
|
10
10
|
|
11
11
|
def name
|
@@ -25,6 +25,6 @@ module Apollo
|
|
25
25
|
}
|
26
26
|
end
|
27
27
|
end
|
28
|
-
end #
|
28
|
+
end # Crawlers
|
29
29
|
end # Crawler
|
30
30
|
end # Apollo
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: apollo-crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.45
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-02-
|
12
|
+
date: 2013-02-24 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: amqp
|
@@ -91,6 +91,22 @@ dependencies:
|
|
91
91
|
- - ! '>='
|
92
92
|
- !ruby/object:Gem::Version
|
93
93
|
version: '0'
|
94
|
+
- !ruby/object:Gem::Dependency
|
95
|
+
name: writeexcel
|
96
|
+
requirement: !ruby/object:Gem::Requirement
|
97
|
+
none: false
|
98
|
+
requirements:
|
99
|
+
- - ! '>='
|
100
|
+
- !ruby/object:Gem::Version
|
101
|
+
version: '0'
|
102
|
+
type: :runtime
|
103
|
+
prerelease: false
|
104
|
+
version_requirements: !ruby/object:Gem::Requirement
|
105
|
+
none: false
|
106
|
+
requirements:
|
107
|
+
- - ! '>='
|
108
|
+
- !ruby/object:Gem::Version
|
109
|
+
version: '0'
|
94
110
|
- !ruby/object:Gem::Dependency
|
95
111
|
name: iconv
|
96
112
|
requirement: !ruby/object:Gem::Requirement
|
@@ -219,7 +235,7 @@ dependencies:
|
|
219
235
|
- - ! '>='
|
220
236
|
- !ruby/object:Gem::Version
|
221
237
|
version: '0'
|
222
|
-
description: Gem for crawling data from external
|
238
|
+
description: Gem for crawling data from external sources
|
223
239
|
email: korczis@gmail.com
|
224
240
|
executables:
|
225
241
|
- apollo-crawler
|
@@ -230,16 +246,15 @@ files:
|
|
230
246
|
- ./lib/apollo_crawler/formatters/formatter_json.rb
|
231
247
|
- ./lib/apollo_crawler/formatters/formatter_table.rb
|
232
248
|
- ./lib/apollo_crawler/version.rb
|
249
|
+
- ./lib/apollo_crawler/crawler_template.rb
|
233
250
|
- ./lib/apollo_crawler/crawler.rb
|
251
|
+
- ./lib/apollo_crawler/crawlers/stackoverflow_com/stackoverflow.rb
|
252
|
+
- ./lib/apollo_crawler/crawlers/xkcd_com/xkcd.rb
|
253
|
+
- ./lib/apollo_crawler/crawlers/slashdot_org/slashdot.rb
|
254
|
+
- ./lib/apollo_crawler/crawlers/firmy_cz/firmy.rb
|
255
|
+
- ./lib/apollo_crawler/crawlers/alexa_com/alexa.rb
|
256
|
+
- ./lib/apollo_crawler/crawlers/ycombinator_com/hacker_news.rb
|
234
257
|
- ./lib/apollo_crawler/formatter.rb
|
235
|
-
- ./lib/apollo_crawler/plugin_template.rb
|
236
|
-
- ./lib/apollo_crawler/plugins/stackoverflow_com/stackoverflow.rb
|
237
|
-
- ./lib/apollo_crawler/plugins/xkcd_com/xkcd.rb
|
238
|
-
- ./lib/apollo_crawler/plugins/slashdot_org/slashdot.rb
|
239
|
-
- ./lib/apollo_crawler/plugins/firmy_cz/firmy.rb
|
240
|
-
- ./lib/apollo_crawler/plugins/alexa_com/alexa.rb
|
241
|
-
- ./lib/apollo_crawler/plugins/ycombinator_com/hacker_news.rb
|
242
|
-
- ./lib/apollo_crawler/plugin.rb
|
243
258
|
- ./lib/apollo_crawler.rb
|
244
259
|
- bin/apollo-crawler
|
245
260
|
homepage: https://github.com/korczis/apollo-crawler
|
@@ -1,73 +0,0 @@
|
|
1
|
-
require "open-uri"
|
2
|
-
require "nokogiri"
|
3
|
-
|
4
|
-
module Apollo
|
5
|
-
module Crawler
|
6
|
-
module Plugins
|
7
|
-
class Plugin
|
8
|
-
|
9
|
-
# Name of the plugin, used in docs, lookups, etc ...
|
10
|
-
def name
|
11
|
-
return "Plugin Base"
|
12
|
-
end
|
13
|
-
|
14
|
-
def url
|
15
|
-
return nil
|
16
|
-
end
|
17
|
-
|
18
|
-
def etl(url=nil)
|
19
|
-
# Look for passed URL use default instead and fail if it is not valid
|
20
|
-
url = url ? url : self.url
|
21
|
-
if(url.nil?)
|
22
|
-
return nil
|
23
|
-
end
|
24
|
-
|
25
|
-
# Try fetch document
|
26
|
-
doc = self.fetch_document(url)
|
27
|
-
if(doc.nil?)
|
28
|
-
return nil
|
29
|
-
end
|
30
|
-
|
31
|
-
# Try extract data from document
|
32
|
-
data = self.extract_data(doc)
|
33
|
-
|
34
|
-
# Try extract links for another documents
|
35
|
-
links = self.extract_links(doc)
|
36
|
-
|
37
|
-
# Return ETL result
|
38
|
-
return {
|
39
|
-
:plugin => self.class.name,
|
40
|
-
:title => doc.title,
|
41
|
-
:data => data,
|
42
|
-
:links => links
|
43
|
-
}
|
44
|
-
end
|
45
|
-
|
46
|
-
# Fetch document
|
47
|
-
def fetch_document(url)
|
48
|
-
ic = Iconv.new("UTF-8//IGNORE", "UTF-8")
|
49
|
-
|
50
|
-
if(self.url.nil?)
|
51
|
-
return nil
|
52
|
-
end
|
53
|
-
|
54
|
-
# TODO: Encapsulate and make more robust => invalid hostname, timeouts and so
|
55
|
-
doc = Nokogiri::HTML(ic.iconv(open(self.url).read))
|
56
|
-
return doc
|
57
|
-
end
|
58
|
-
|
59
|
-
# Extracts data from document
|
60
|
-
def extract_data(doc)
|
61
|
-
res = []
|
62
|
-
return res
|
63
|
-
end
|
64
|
-
|
65
|
-
# Extract links to another documents from this document
|
66
|
-
def extract_links(doc)
|
67
|
-
res = []
|
68
|
-
return res
|
69
|
-
end
|
70
|
-
end
|
71
|
-
end
|
72
|
-
end
|
73
|
-
end
|