rubyretriever 1.2.2 → 1.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cc417c965402019ab69f33f3a1dfea8b061f6f8c
-  data.tar.gz: d70ddf42a2d7a845239119ba7563f51bd11d1fb1
+  metadata.gz: 3bb32aa2e9c8317d2f3cb13572e2cdecb1da24a9
+  data.tar.gz: 732e5610104345efed80651929cb9a050e01d9be
 SHA512:
-  metadata.gz: 7e02bd67a9b355c7e23423bfd4e8a4b045d6f30be94ffa8b3fedec9d9a58385d29c134d7c429221b157fed75a59351d9584b066ff2bf27d6b940ac4195e4fda9
-  data.tar.gz: 21a3318dfe7eb85bddc6a07dfe9dfccbcd7903170427aea87d346dce36b5bda7c9cc54b64951d5835b5efd8dd3ad5ce44529a8881fbba93d9a78ff2de2289eaa
+  metadata.gz: 3d4e109785452db3906dc7b66158846cda24e4c3e1b942f600918338e141d6a337f1f9b3087b94b2561c64095fcdc2f2fb439d29b73574a2ddae501a8f0d965b
+  data.tar.gz: 2e0befea22dfc2bc689d15ad3c33efaf015f7b1ee5c53a322cccca7f6394a4def445e362585600e1934f770377ce193c5a762caa3639ccda480f7c481ce64d64

data/lib/retriever/fetch.rb

@@ -91,7 +91,7 @@ module Retriever
       @sitemap      = options['sitemap']
       @seo          = options['seo']
       @autodown     = options['autodown']
-      @file_re      = Regexp.new(".#{@fileharvest}\z").freeze if @fileharvest
+      @file_re      = Regexp.new(/.#{@fileharvest}\z/).freeze if @fileharvest
     end
 
     def setup_bloom_filter

data/lib/retriever/fetchfiles.rb

@@ -6,7 +6,7 @@ module Retriever
     def initialize(url, options)
       super
       temp_file_collection = @page_one.parse_files(@page_one.parse_internal)
-      @data.concat(tempFileCollection) if temp_file_collection.size > 0
+      @data.concat(temp_file_collection) if temp_file_collection.size > 0
       lg("#{@data.size} new files found")
 
       async_crawl_and_collect

data/lib/retriever/version.rb

@@ -1,4 +1,4 @@
 #
 module Retriever
-  VERSION = '1.2.2'
+  VERSION = '1.2.3'
 end

data/readme.md

@@ -6,7 +6,7 @@ By Joe Norton
 
 RubyRetriever is a Web Crawler, Site Mapper, File Harvester & Autodownloader.  
 
-RubyRetriever (RR) uses asynchronous HTTP requests, thanks to [Eventmachine](https://github.com/eventmachine/eventmachine) & [Synchrony](https://github.com/igrigorik/em-synchrony), to crawl webpages *very quickly*.  Another neat thing about RR, is it uses a ruby implementation of the [bloomfilter](https://github.com/igrigorik/bloomfilter-rb) in order to keep track of page's it has already crawled.  
+RubyRetriever (RR) uses asynchronous HTTP requests, thanks to [Eventmachine](https://github.com/eventmachine/eventmachine) & [Synchrony](https://github.com/igrigorik/em-synchrony), to crawl webpages *very quickly*.  Another neat thing about RR, is it uses a ruby implementation of the [bloomfilter](https://github.com/igrigorik/bloomfilter-rb) in order to keep track of pages it has already crawled.  
 
 **v1.0 Update (6/07/2014)** - Includes major code changes, a lot of bug fixes. Much better in dealing with redirects, and issues with the host changing, etc. Also, added the SEO mode -- which grabs a number of key SEO components from every page on a site. Lastly, this update was so extensive that I could not ensure backward compatibility -- and thus, this was update 1.0!  
 mission  

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rubyretriever
 version: !ruby/object:Gem::Version
-  version: 1.2.2
+  version: 1.2.3
 platform: ruby
 authors:
 - Joe Norton