cobweb 0.0.68 → 0.0.70
Sign up to get free protection for your applications and to get access to all the features.
- data/README.textile +5 -7
- data/lib/{crawl.rb → cobweb_crawl_helper.rb} +1 -1
- data/lib/cobweb_version.rb +1 -1
- data/lib/crawl_job.rb +10 -7
- data/lib/stats.rb +4 -4
- data/spec/cobweb/cobweb_job_spec.rb +3 -3
- data/spec/cobweb/crawl_spec.rb +5 -5
- metadata +23 -23
data/README.textile
CHANGED
@@ -1,5 +1,5 @@
|
|
1
1
|
|
2
|
-
h1. Cobweb v0.0.
|
2
|
+
h1. Cobweb v0.0.70
|
3
3
|
|
4
4
|
!https://secure.travis-ci.org/stewartmckee/cobweb.png?branch=master!
|
5
5
|
|
@@ -138,15 +138,13 @@ You can also run within a block and get access to each page as it is being crawl
|
|
138
138
|
bc. statistics = CobwebCrawler.new(:cache => 600).crawl("http://www.pepsico.com") do |page|
|
139
139
|
puts "Just crawled #{page[:url]} and got a status of #{page[:status_code]}."
|
140
140
|
end
|
141
|
-
puts "Finished Crawl
|
141
|
+
puts "Finished Crawl with #{statistics[:page_count]} pages and #{statistics[:asset_count]} assets."
|
142
142
|
|
143
|
+
h3. CobwebCrawlHelper
|
143
144
|
|
145
|
+
The CobwebCrawlHelper class is a helper class to assist in getting information about a crawl and to perform functions against the crawl
|
144
146
|
|
145
|
-
|
146
|
-
|
147
|
-
The crawl class is a helper class to assist in getting information about a crawl and to perform functions against the crawl
|
148
|
-
|
149
|
-
bc. crawl = Crawl.new(options)
|
147
|
+
bc. crawl = CobwebCrawlHelper.new(options)
|
150
148
|
|
151
149
|
* options - the hash of options passed into Cobweb.new (must include a :crawl_id)
|
152
150
|
|
data/lib/cobweb_version.rb
CHANGED
data/lib/crawl_job.rb
CHANGED
@@ -14,7 +14,7 @@ class CrawlJob
|
|
14
14
|
# change all hash keys to symbols
|
15
15
|
content_request = HashUtil.deep_symbolize_keys(content_request)
|
16
16
|
@content_request = content_request
|
17
|
-
@crawl =
|
17
|
+
@crawl = CobwebCrawlHelper.new(content_request)
|
18
18
|
|
19
19
|
content_request[:redis_options] = {} unless content_request.has_key? :redis_options
|
20
20
|
content_request[:crawl_limit_by_page] = false unless content_request.has_key? :crawl_limit_by_page
|
@@ -28,13 +28,14 @@ class CrawlJob
|
|
28
28
|
# check we haven't crawled this url before
|
29
29
|
unless @redis.sismember "crawled", content_request[:url]
|
30
30
|
# if there is no limit or we're still under it lets get the url
|
31
|
-
if within_crawl_limits?(content_request[:crawl_limit]) and @crawl.status !=
|
31
|
+
if within_crawl_limits?(content_request[:crawl_limit]) and @crawl.status != CobwebCrawlHelper::CANCELLED
|
32
32
|
content = Cobweb.new(content_request).get(content_request[:url], content_request)
|
33
33
|
if content_request[:url] == @redis.get("original_base_url")
|
34
34
|
@redis.set("crawled_base_url", content[:base_url])
|
35
35
|
end
|
36
36
|
if is_permitted_type(content)
|
37
37
|
begin
|
38
|
+
@redis.incr "inprogress"
|
38
39
|
# move the url from the queued list to the crawled list - for both the original url, and the content url (to handle redirects)
|
39
40
|
@redis.srem "queued", content_request[:url]
|
40
41
|
@redis.sadd "crawled", content_request[:url]
|
@@ -70,8 +71,8 @@ class CrawlJob
|
|
70
71
|
|
71
72
|
internal_links.each do |link|
|
72
73
|
puts link
|
73
|
-
puts "Not enqueuing due to cancelled crawl" if @crawl.status ==
|
74
|
-
if within_queue_limits?(content_request[:crawl_limit]) and @crawl.status !=
|
74
|
+
puts "Not enqueuing due to cancelled crawl" if @crawl.status == CobwebCrawlHelper::CANCELLED
|
75
|
+
if within_queue_limits?(content_request[:crawl_limit]) and @crawl.status != CobwebCrawlHelper::CANCELLED
|
75
76
|
enqueue_content(content_request, link)
|
76
77
|
end
|
77
78
|
end
|
@@ -88,6 +89,7 @@ class CrawlJob
|
|
88
89
|
end
|
89
90
|
|
90
91
|
ensure
|
92
|
+
@redis.decr "inprogress"
|
91
93
|
#update the queued and crawled lists if we are within the crawl limits.
|
92
94
|
|
93
95
|
# update the queue and crawl counts -- doing this very late in the piece so that the following transaction all occurs at once.
|
@@ -126,10 +128,10 @@ class CrawlJob
|
|
126
128
|
|
127
129
|
end
|
128
130
|
|
129
|
-
# Sets the crawl status to
|
131
|
+
# Sets the crawl status to CobwebCrawlHelper::FINISHED and enqueues the crawl finished job
|
130
132
|
def self.finished(content_request)
|
131
133
|
# finished
|
132
|
-
if @crawl.status !=
|
134
|
+
if @crawl.status != CobwebCrawlHelper::FINISHED and @crawl.status != CobwebCrawlHelper::CANCELLED && @redis.get("inprogress").to_i==0
|
133
135
|
ap "CRAWL FINISHED #{content_request[:url]}, #{counters}, #{@redis.get("original_base_url")}, #{@redis.get("crawled_base_url")}" if content_request[:debug]
|
134
136
|
@stats.end_crawl(content_request)
|
135
137
|
|
@@ -195,8 +197,9 @@ class CrawlJob
|
|
195
197
|
new_request = content_request.clone
|
196
198
|
new_request[:url] = link
|
197
199
|
new_request[:parent] = content_request[:url]
|
198
|
-
Resque.enqueue
|
200
|
+
#to help prevent accidentally double processing a link, let's mark it as queued just before the Resque.enqueue statement, rather than just after.
|
199
201
|
@redis.sadd "queued", link
|
202
|
+
Resque.enqueue(CrawlJob, new_request)
|
200
203
|
increment_queue_counter
|
201
204
|
end
|
202
205
|
|
data/lib/stats.rb
CHANGED
@@ -16,16 +16,16 @@ class Stats
|
|
16
16
|
@redis.hset "crawl_details", key, options[key].to_s
|
17
17
|
end
|
18
18
|
end
|
19
|
-
@redis.hset "statistics", "current_status",
|
19
|
+
@redis.hset "statistics", "current_status", CobwebCrawlHelper::STARTING
|
20
20
|
end
|
21
21
|
|
22
22
|
# Removes the crawl from the running crawls and updates status
|
23
23
|
def end_crawl(options, cancelled=false)
|
24
24
|
@full_redis.srem "cobweb_crawls", options[:crawl_id]
|
25
25
|
if cancelled
|
26
|
-
@redis.hset "statistics", "current_status",
|
26
|
+
@redis.hset "statistics", "current_status", CobwebCrawlHelper::CANCELLED
|
27
27
|
else
|
28
|
-
@redis.hset "statistics", "current_status",
|
28
|
+
@redis.hset "statistics", "current_status", CobwebCrawlHelper::FINISHED
|
29
29
|
end
|
30
30
|
@redis.del "crawl_details"
|
31
31
|
end
|
@@ -158,7 +158,7 @@ class Stats
|
|
158
158
|
|
159
159
|
# Sets the current status of the crawl
|
160
160
|
def update_status(status)
|
161
|
-
#@redis.hset("statistics", "current_status", status) unless status ==
|
161
|
+
#@redis.hset("statistics", "current_status", status) unless status == CobwebCrawlHelper::CANCELLED
|
162
162
|
end
|
163
163
|
|
164
164
|
# Returns the current status of the crawl
|
@@ -33,7 +33,7 @@ describe Cobweb, :local_only => true do
|
|
33
33
|
end
|
34
34
|
it "should not crawl anything if nothing has started" do
|
35
35
|
crawl = @cobweb.start(@base_url)
|
36
|
-
crawl_obj =
|
36
|
+
crawl_obj = CobwebCrawlHelper.new(crawl)
|
37
37
|
crawl_obj.destroy
|
38
38
|
@stat = Stats.new({:crawl_id => crawl[:crawl_id]})
|
39
39
|
wait_for_crawl_finished crawl[:crawl_id]
|
@@ -42,7 +42,7 @@ describe Cobweb, :local_only => true do
|
|
42
42
|
|
43
43
|
it "should not complete the crawl when cancelled" do
|
44
44
|
crawl = @cobweb.start(@base_url)
|
45
|
-
crawl_obj =
|
45
|
+
crawl_obj = CobwebCrawlHelper.new(crawl)
|
46
46
|
sleep 6
|
47
47
|
crawl_obj.destroy
|
48
48
|
@stat = Stats.new({:crawl_id => crawl[:crawl_id]})
|
@@ -231,7 +231,7 @@ def wait_for_crawl_finished(crawl_id, timeout=20)
|
|
231
231
|
end
|
232
232
|
|
233
233
|
def running?(crawl_id)
|
234
|
-
@stat.get_status !=
|
234
|
+
@stat.get_status != CobwebCrawlHelper::FINISHED and @stat.get_status != CobwebCrawlHelper::CANCELLED
|
235
235
|
end
|
236
236
|
|
237
237
|
def clear_queues
|
data/spec/cobweb/crawl_spec.rb
CHANGED
@@ -1,23 +1,23 @@
|
|
1
1
|
require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
|
2
2
|
|
3
|
-
describe
|
3
|
+
describe CobwebCrawlHelper do
|
4
4
|
|
5
5
|
# this spec tests the crawl object
|
6
6
|
|
7
7
|
describe "initialize" do
|
8
8
|
describe "without data" do
|
9
9
|
it "should raise an exception" do
|
10
|
-
lambda {
|
10
|
+
lambda {CobwebCrawlHelper.new}.should raise_exception
|
11
11
|
end
|
12
12
|
end
|
13
13
|
|
14
14
|
describe "with data" do
|
15
15
|
before(:each) do
|
16
16
|
data = {:crawl_id => "asdf"}
|
17
|
-
@crawl =
|
17
|
+
@crawl = CobwebCrawlHelper.new(data)
|
18
18
|
end
|
19
19
|
it "should create a crawl object" do
|
20
|
-
@crawl.should be_an_instance_of
|
20
|
+
@crawl.should be_an_instance_of CobwebCrawlHelper
|
21
21
|
end
|
22
22
|
it "should return an id" do
|
23
23
|
@crawl.should respond_to "id"
|
@@ -46,7 +46,7 @@ describe Crawl do
|
|
46
46
|
end
|
47
47
|
describe "after called" do
|
48
48
|
before(:each) do
|
49
|
-
@crawl =
|
49
|
+
@crawl = CobwebCrawlHelper.new({:crawl_id => "crawl_0_id"})
|
50
50
|
@crawl.destroy
|
51
51
|
end
|
52
52
|
it "should delete only the crawl specified" do
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: cobweb
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.70
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,11 +9,11 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-09-
|
12
|
+
date: 2012-09-16 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: resque
|
16
|
-
requirement: &
|
16
|
+
requirement: &70248368307060 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ! '>='
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: '0'
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *70248368307060
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: redis
|
27
|
-
requirement: &
|
27
|
+
requirement: &70248368306020 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ! '>='
|
@@ -32,10 +32,10 @@ dependencies:
|
|
32
32
|
version: '0'
|
33
33
|
type: :runtime
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *70248368306020
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: nokogiri
|
38
|
-
requirement: &
|
38
|
+
requirement: &70248368305360 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ! '>='
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: '0'
|
44
44
|
type: :runtime
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *70248368305360
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: addressable
|
49
|
-
requirement: &
|
49
|
+
requirement: &70248368304140 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ! '>='
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: '0'
|
55
55
|
type: :runtime
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *70248368304140
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: rspec
|
60
|
-
requirement: &
|
60
|
+
requirement: &70248368303560 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ! '>='
|
@@ -65,10 +65,10 @@ dependencies:
|
|
65
65
|
version: '0'
|
66
66
|
type: :runtime
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *70248368303560
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: awesome_print
|
71
|
-
requirement: &
|
71
|
+
requirement: &70248368302820 !ruby/object:Gem::Requirement
|
72
72
|
none: false
|
73
73
|
requirements:
|
74
74
|
- - ! '>='
|
@@ -76,10 +76,10 @@ dependencies:
|
|
76
76
|
version: '0'
|
77
77
|
type: :runtime
|
78
78
|
prerelease: false
|
79
|
-
version_requirements: *
|
79
|
+
version_requirements: *70248368302820
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: sinatra
|
82
|
-
requirement: &
|
82
|
+
requirement: &70248368302080 !ruby/object:Gem::Requirement
|
83
83
|
none: false
|
84
84
|
requirements:
|
85
85
|
- - ! '>='
|
@@ -87,10 +87,10 @@ dependencies:
|
|
87
87
|
version: '0'
|
88
88
|
type: :runtime
|
89
89
|
prerelease: false
|
90
|
-
version_requirements: *
|
90
|
+
version_requirements: *70248368302080
|
91
91
|
- !ruby/object:Gem::Dependency
|
92
92
|
name: thin
|
93
|
-
requirement: &
|
93
|
+
requirement: &70248368301260 !ruby/object:Gem::Requirement
|
94
94
|
none: false
|
95
95
|
requirements:
|
96
96
|
- - ! '>='
|
@@ -98,10 +98,10 @@ dependencies:
|
|
98
98
|
version: '0'
|
99
99
|
type: :runtime
|
100
100
|
prerelease: false
|
101
|
-
version_requirements: *
|
101
|
+
version_requirements: *70248368301260
|
102
102
|
- !ruby/object:Gem::Dependency
|
103
103
|
name: haml
|
104
|
-
requirement: &
|
104
|
+
requirement: &70248368300400 !ruby/object:Gem::Requirement
|
105
105
|
none: false
|
106
106
|
requirements:
|
107
107
|
- - ! '>='
|
@@ -109,10 +109,10 @@ dependencies:
|
|
109
109
|
version: '0'
|
110
110
|
type: :runtime
|
111
111
|
prerelease: false
|
112
|
-
version_requirements: *
|
112
|
+
version_requirements: *70248368300400
|
113
113
|
- !ruby/object:Gem::Dependency
|
114
114
|
name: namespaced_redis
|
115
|
-
requirement: &
|
115
|
+
requirement: &70248368299680 !ruby/object:Gem::Requirement
|
116
116
|
none: false
|
117
117
|
requirements:
|
118
118
|
- - ! '>='
|
@@ -120,7 +120,7 @@ dependencies:
|
|
120
120
|
version: 1.0.2
|
121
121
|
type: :runtime
|
122
122
|
prerelease: false
|
123
|
-
version_requirements: *
|
123
|
+
version_requirements: *70248368299680
|
124
124
|
description: Cobweb is a web crawler that can use resque to cluster crawls to quickly
|
125
125
|
crawl extremely large sites which is much more perofmant than multi-threaded crawlers. It
|
126
126
|
is also a standalone crawler that has a sophisticated statistics monitoring interface
|
@@ -310,13 +310,13 @@ files:
|
|
310
310
|
- spec/spec.opts
|
311
311
|
- spec/spec_helper.rb
|
312
312
|
- lib/cobweb.rb
|
313
|
+
- lib/cobweb_crawl_helper.rb
|
313
314
|
- lib/cobweb_crawler.rb
|
314
315
|
- lib/cobweb_finished_job.rb
|
315
316
|
- lib/cobweb_links.rb
|
316
317
|
- lib/cobweb_process_job.rb
|
317
318
|
- lib/cobweb_version.rb
|
318
319
|
- lib/content_link_parser.rb
|
319
|
-
- lib/crawl.rb
|
320
320
|
- lib/crawl_job.rb
|
321
321
|
- lib/encoding_safe_process_job.rb
|
322
322
|
- lib/hash_util.rb
|