sitemap-parser 0.2.1 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d03dd8db51f6b4d2f7fc07f1bf82a8208e09879e
-  data.tar.gz: 36e811e0184838fdb0332fc5914b5ef232f6ee87
+  metadata.gz: 1315feae0e6664ba1047dca9682663ab2854c9d9
+  data.tar.gz: 345c43faad3c00fce3bec650da8e0b1b9bc7903a
 SHA512:
-  metadata.gz: 49c136b2f86b00dffbf9c565a7284ea1349a68f752dae6e1cab96b8135ab69955091f9fbb2fbd2d32880d3bc5cde7b8a29bf8eca42c2e954f09a4f4a306d7e76
-  data.tar.gz: d5241537a66a454a6097a6c88bc3e1e643535c0a085d98f935c13aea902c5b5bf094042fbc2a140c437d548e1e9e9864dda05f21a42113452ce811499b7bd7cc
+  metadata.gz: b9656163ef064c3789b062deb5bff162676a426aa022a3bafe7926c4cb513207f2360920df1a81f5279cb352e6a0709a707d38cefa094ff6c038ba6a7714d15b
+  data.tar.gz: c8b3f196785154496d6cfa6966b0930ccd9afe115b665e962bc41042cd53de8430f03924055e4c01dd493ef0d46542075c8b636d9b9c6f989d49e5c117504da5

data/lib/sitemap-parser.rb

@@ -5,7 +5,7 @@ class SitemapParser
 
   def initialize(url, opts = {})
     @url = url
-    @options = {:followlocation => true}.merge(opts)
+    @options = {:followlocation => true, :recurse => false}.merge(opts)
   end
 
   def raw_sitemap
@@ -16,7 +16,7 @@ class SitemapParser
           if response.success?
             return response.body
           else
-            return nil
+            raise "HTTP request to #{@url} failed"
           end
         end
         request.run
@@ -28,19 +28,28 @@ class SitemapParser
 
   def sitemap
     @sitemap ||= Nokogiri::XML(raw_sitemap)
-  rescue
-    nil
   end
 
   def urls
-    sitemap.at("urlset").search("url")
-  rescue
-    nil
+    if sitemap.at('urlset')
+      sitemap.at("urlset").search("url")
+    elsif sitemap.at('sitemapindex')
+      found_urls = []
+      if @options[:recurse]
+        sitemap.at('sitemapindex').search('sitemap').each do |sitemap|
+          child_sitemap_location = sitemap.at('loc').content
+          found_urls << self.class.new(child_sitemap_location, :recurse => false).urls
+        end
+      end
+      return found_urls.flatten
+    else
+      raise 'Malformed sitemap, no urlset'
+    end
   end
 
   def to_a
     urls.map { |url| url.at("loc").content }
-  rescue
-    []
+  rescue NoMethodError
+    raise 'Malformed sitemap, url without loc'
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sitemap-parser
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.3.0
 platform: ruby
 authors:
 - Ben Balter
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-01-05 00:00:00.000000000 Z
+date: 2016-04-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -94,6 +94,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '4.7'
+- !ruby/object:Gem::Dependency
+  name: test-unit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.1'
 description: Ruby Gem to parse sitemaps.org compliant sitemaps.
 email: ben.balter@github.com
 executables: []
@@ -121,8 +135,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.0
+rubygems_version: 2.6.2
 signing_key: 
 specification_version: 4
 summary: Ruby Gem to parse sitemaps.org compliant sitemaps
 test_files: []
+has_rdoc: