spider 0.5.0 → 0.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1d6465ee9f80195a1002053f826f1b80187020a3
-  data.tar.gz: 1218142b1d76482cf5baccd1f288934cd7a6b003
+  metadata.gz: ae84ef471855de9c49c3499eb658d961342a4338
+  data.tar.gz: cf80d52423709af79478ff051f212dea0b8021a2
 SHA512:
-  metadata.gz: 2725ca0197ec2801836d94615e4ece0196c131a9ff500ed5837c22e320e06b33a8f609add7d41eabb8fa19114a60af71057b5bdebaf8f94e2be116148d6ad123
-  data.tar.gz: 5497c85e9759542ecb0cbb612484de0b185f7428c5a2c5222e1fbc7e1e3f69bac727bfddd883967c5eeb6c5bfaca0b9dfbe130eaaed35cc9e8cb96fb87abddc5
+  metadata.gz: 72785824697410005b8738a32e74d71a78d4623522e7f3f4bb56318349c12d693cee8a8a003766c33afec0b70bb195ce079117413543d9a004fe7adfae03b9d8
+  data.tar.gz: 8bdd202aa793c3f39984e3394e915c915c2fd7d68b7f475c0d317103d31c4a61bdc3ceaa87cfea02a77ec2cdbf2e23cc245a4e080c211c03322ce729b5551bb8

data/AUTHORS

@@ -7,6 +7,6 @@ James Edward Gray II
 Joao Eriberto Mota Filho
 John Buckley
 John Nagro
-Mike Burns
 Matt Horan
+Mike Burns (original author)
 Sander van der Vliet

data/CHANGES

@@ -1,4 +1,7 @@
-2016-05-13
+2016-09-04 v0.5.1
+* added the ability to stop a crawl
+
+2016-05-13 v0.5.0
 * fixed #1 thanks to @eribertomota
 * got it running on more recent versions of ruby
 * cleaned up the docs a bit

data/README.md

@@ -151,3 +151,5 @@ scraping, collecting, and looping so that you can just handle the data._
    end
  end
 ```
+
+_Copyright (c) 2007-2016 Spider Team Authors_

data/lib/spider.rb

@@ -4,7 +4,7 @@ require File.dirname(__FILE__)+'/spider/spider_instance'
 # links, and doing it all over again.
 class Spider
 
-  VERSION_INFO = [0, 5, 0] unless defined?(self::VERSION_INFO)
+  VERSION_INFO = [0, 5, 1] unless defined?(self::VERSION_INFO)
   VERSION = VERSION_INFO.map(&:to_s).join('.') unless defined?(self::VERSION)
 
   def self.version

data/lib/spider/spider_instance.rb

@@ -35,6 +35,7 @@ class SpiderInstance
     @headers     = {}
     @setup       = nil
     @teardown    = nil
+    @interrupted = false
   end
 
   # Add a predicate that determines whether to continue down this URL's path.
@@ -161,8 +162,7 @@ class SpiderInstance
   end
 
   def start! #:nodoc:
-    interrupted = false
-    trap("SIGINT") { interrupted = true }
+    trap("SIGINT") { @interrupted = true }
     begin
       next_urls = @next_urls.pop
       tmp_n_u = {}
@@ -184,10 +184,14 @@ class SpiderInstance
             #exit if interrupted
           end
           @teardown.call(a_url) unless @teardown.nil?
-          exit if interrupted
+          break if @interrupted
         end
       end
-    end while !@next_urls.empty?
+    end while !@next_urls.empty? && !@interrupted
+  end
+
+  def stop! #:nodoc:
+    @interrupted = true
   end
 
   def success_or_failure(code) #:nodoc:

data/spider.gemspec

@@ -5,6 +5,7 @@ require File.expand_path('../lib/spider', __FILE__)
 spec = Gem::Specification.new do |s|
   s.author = 'John Nagro'
   s.email = 'john.nagro@gmail.com'
+  s.license = 'MIT'
   s.has_rdoc = true
   s.homepage = 'https://github.com/johnnagro/spider'
   s.name = 'spider'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: spider
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.5.1
 platform: ruby
 authors:
 - John Nagro
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-05-13 00:00:00.000000000 Z
+date: 2016-09-04 00:00:00.000000000 Z
 dependencies: []
 description: |
   A Web spidering library: handles robots.txt, scraping, finding more
@@ -33,7 +33,8 @@ files:
 - spec/spider_spec.rb
 - spider.gemspec
 homepage: https://github.com/johnnagro/spider
-licenses: []
+licenses:
+- MIT
 metadata: {}
 post_install_message: 
 rdoc_options: []
@@ -51,7 +52,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: spider
-rubygems_version: 2.5.1
+rubygems_version: 2.6.6
 signing_key: 
 specification_version: 4
 summary: A Web spidering library