site_validator 1.4.1 → 1.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4757d9e89c4e2e314b5b235dcba1d39ebfce20e6
-  data.tar.gz: 3e7afcda9986403a293f422dfbf5e925e4516cb7
+  metadata.gz: d4dbe8f5a7a4fff1b83b982a23ccf67918e06723
+  data.tar.gz: b7bf3908fd7ae4d1ede2362161589b9428632e73
 SHA512:
-  metadata.gz: c5e1ee9640cfbf9a273c63b0ee0c2f0f54f4cb6770e45f535d70ad079142d42f2b66c132317d4c299270246112a0212076120ba5a2b218893aae3fbc090e84e8
-  data.tar.gz: b4990b9aa1ffc3e279eb9f0f86ba409f7d13ec8e1f99e7cd60c6d294a70d5887447d6eeef3d82412e74f6108b38d5b0bb0555913a772906751ac24ef2c10519b
+  metadata.gz: a44be80ecbcc4da84f1f86ad809f7ef8467c1e9d06ca6911d203b71b7abb758c68a43776f84af3743ebc70dd05c1e97540c155e1d9d902f23e5ee8e2f9079bcf
+  data.tar.gz: 37b1fb6c80178ee3d9c98cb4abec0d7b2a9ab4a90e9f2960cd0c3a02e2a4840b97699c5881069300e40a1626e396f85edf7106ae420f4349fe0a922598166149

data/README.md

@@ -24,9 +24,9 @@ This will validate all the internal URLs found on the starting URL, up to a maxi
 
 You can pass site_validator an XML sitemap or the URL of a website; it will scrape it in search of URLs to validate.
 
-##Timeouts
+##Max pages
 
-By default, site_validator will set a 20 seconds timeout for each individual request. If you want to set a different timeout, pass it as a third parameter like this:
+By default, site_validator will validate up to 100 pages per sitemap. If you want to set a different value, pass it as a third parameter like this:
 
     site_validator http://validationhell.com report.html 60
 

data/bin/site_validator

@@ -9,8 +9,8 @@ begin
   else
     puts "USAGE:  site_validator  url_of_sitemap  output_file.html"
     puts " OR "
-    puts "USAGE:  site_validator  url_of_sitemap  output_file.html  timeout_in_seconds"
+    puts "USAGE:  site_validator  url_of_sitemap  output_file.html  max_pages"
   end
 rescue
   puts "There was an error processing your request"
-end
+end

data/lib/site_validator/sitemap.rb

@@ -2,24 +2,23 @@
 
 require 'nokogiri'
 require 'metainspector'
-require 'timeout'
 
 module SiteValidator
   ##
   # A sitemap has an URL, and holds a collection of pages to be validated
   #
   class Sitemap
-    attr_accessor :url, :timeout
+    attr_accessor :url, :max_pages
 
-    def initialize(url, timeout = 20)
-      @url      = url
-      @timeout  = timeout
+    def initialize(url, max_pages = 100)
+      @url       = url
+      @max_pages = max_pages
     end
 
     ##
     # Returns the first 250 unique URLs from the sitemap
     def pages
-      @pages ||= pages_in_sitemap.uniq {|p| p.url}[0..249]
+      @pages ||= pages_in_sitemap.uniq {|p| p.url}[0..max_pages-1]
     end
 
     ##
@@ -55,7 +54,7 @@ module SiteValidator
       pages = xml_locations.select {|loc| looks_like_html?(loc.text.strip)}.map {|loc| SiteValidator::Page.new(loc.text.strip)}
 
       if pages.empty?
-        m     = MetaInspector.new(url, :timeout => timeout, :allow_redirections => :all)
+        m     = MetaInspector.new(url, :timeout => 20, :allow_redirections => :all)
         links = [m.url]
 
         m.internal_links.select {|l| looks_like_html?(l)}.map {|l| l.split('#')[0]}.uniq.each do |link|

data/lib/site_validator/validator.rb

@@ -15,8 +15,8 @@ module SiteValidator
     # Shows progress on dot-style (...F...FFE..). A dot is a valid page,
     # an F is a page with errors, and an E is an exception
     # After the checking is done, a detailed summary is written to filename
-    def check(url, filename, timeout)
-      sitemap = SiteValidator::Sitemap.new(url, timeout.to_f)
+    def check(url, filename, max_pages)
+      sitemap = SiteValidator::Sitemap.new(url, max_pages.to_i)
       say "Validating #{sitemap.pages.length} pages"
 
       sitemap.pages.each do |page|
@@ -45,4 +45,4 @@ module SiteValidator
       printer.print text
     end
   end
-end
+end

data/lib/site_validator/version.rb

@@ -1,5 +1,5 @@
 # -*- encoding: utf-8 -*-
 
 module SiteValidator
-  VERSION = "1.4.1"
+  VERSION = "1.5.0"
 end

data/spec/sitemap_spec.rb

@@ -184,6 +184,11 @@ describe SiteValidator::Sitemap do
         @sitemap_with_protocol_relative.pages.map {|p| p.url}.should_not include 'http://yahoo.com'
       end
     end
+
+    it "should be able to limit the number of pages" do
+      sitemap = SiteValidator::Sitemap.new('http://guides.rubyonrails.org', 10)
+      sitemap.pages.length.should == 10
+    end
   end
 
   describe "validations" do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: site_validator
 version: !ruby/object:Gem::Version
-  version: 1.4.1
+  version: 1.5.0
 platform: ruby
 authors:
 - Jaime Iniesta
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-20 00:00:00.000000000 Z
+date: 2014-06-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: w3c_validators