web-page-parser 0.25 → 1.0.0

data/spec/spec_helper.rb

@@ -0,0 +1,5 @@
+$:.unshift File.join(File.dirname(__FILE__), '../lib')
+$:.unshift File.join(File.dirname(__FILE__), '../spec')
+
+require 'web-page-parser'
+

metadata

@@ -1,50 +1,111 @@
 --- !ruby/object:Gem::Specification
 name: web-page-parser
 version: !ruby/object:Gem::Version
-  version: '0.25'
-  prerelease: 
+  version: 1.0.0
 platform: ruby
 authors:
 - John Leach
 autorequire: 
 bindir: bin
-cert_chain: []
-date: 2012-06-05 00:00:00.000000000 Z
+cert_chain:
+- |
+  -----BEGIN CERTIFICATE-----
+  MIIDmjCCAoKgAwIBAgIBATANBgkqhkiG9w0BAQUFADBSMQ0wCwYDVQQDDARqb2hu
+  MRkwFwYKCZImiZPyLGQBGRYJam9obmxlYWNoMRIwEAYKCZImiZPyLGQBGRYCY28x
+  EjAQBgoJkiaJk/IsZAEZFgJ1azAeFw0xNDEwMjUxNzAyMDBaFw0xNTEwMjUxNzAy
+  MDBaMFIxDTALBgNVBAMMBGpvaG4xGTAXBgoJkiaJk/IsZAEZFglqb2hubGVhY2gx
+  EjAQBgoJkiaJk/IsZAEZFgJjbzESMBAGCgmSJomT8ixkARkWAnVrMIIBIjANBgkq
+  hkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEA49t9Dck0zPjDiEuRLTEsoXVQEZECcFtu
+  FU2j6ZFGd/twm4dlZ2qHYs5GYtpSwlfJYhAOc2a9cHz1KKSevGaPRxpsFhKEZ+Yj
+  5R8y4VZCY1Rx7tyX2PYdWBNaeTNPIACdW4HNg2/n1bbhu4LkQ+PYBQb6bbeFnzTx
+  dl2ZLvhwSRUbl7aIiYyENbpOmPKCL1ReJUkQn+1Kyq76ZMY6pG6iSeeZvDtKZKqd
+  MX4bWAIBeT6mUv/jhIDkJgj+JO11v3wbhojAcVHInGnyCQ7dLn3hurlLfII4SiLT
+  foOh2i2OY5ZTG5PoPEGMiagBWAUmQUA+Yc6gnfpjrX/aFG/aa6T2+wIDAQABo3sw
+  eTAJBgNVHRMEAjAAMAsGA1UdDwQEAwIEsDAdBgNVHQ4EFgQUqd/WZnE4x+pZ+DS1
+  +H3vH+/gvfkwHwYDVR0RBBgwFoEUam9obkBqb2hubGVhY2guY28udWswHwYDVR0S
+  BBgwFoEUam9obkBqb2hubGVhY2guY28udWswDQYJKoZIhvcNAQEFBQADggEBABG0
+  Avvj8mNb+0drmLLFLMLck8oEcpzONbVG6A3XWrkUkTsdsw8VB848QuFg3gR+3ReU
+  C98Bm+8L1zYVkfhTzHNJ8Y9HGC+8eEXoMQw1C2jGBcN+i4G+eylOBv+PTJX3UU8r
+  r7Tb7QqD7tPjy7TS91OvyImc7Jixt848nrrs9nWSiEIaVxQqBRRdKANsgFISvvA4
+  CPFEkKZm3GcFRIVu9yQO1LWfsbvbVLhD5HSynklijwo2RroPXlNKi6RXsxKwgtqD
+  MghEyBTNQa+QTUTKQMjYOO3kV+Wuv+iQGaMm/bu2SD+Ov0XUzzAsSfz0ZvrF3fbG
+  jdD4CMQtJNDqDiWuUkg=
+  -----END CERTIFICATE-----
+date: 2014-10-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: oniguruma
+  name: htmlentities
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.1.0
+        version: '4.3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.1.0
+        version: '4.3'
 - !ruby/object:Gem::Dependency
-  name: htmlentities
+  name: curb
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.8'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.8'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 4.0.0
+        version: '1.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.11'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.11'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 4.0.0
-description: A Ruby library to parse the content out of web pages, such as BBC News
-  pages and Guardian articles. Used by the News Sniffer project.
+        version: '0'
+description: A Ruby library to parse the content out of web pages. Currently supports
+  BBC News pages, The Guardian, Independent and New York Times articles. Used by the
+  News Sniffer project. http://www.newssniffer.co.uk
 email: john@johnleach.co.uk
 executables: []
 extensions: []
@@ -52,71 +113,118 @@ extra_rdoc_files:
 - README.rdoc
 - LICENSE
 files:
-- lib/web-page-parser/parser_factory.rb
+- LICENSE
+- README.rdoc
+- lib/web-page-parser.rb
 - lib/web-page-parser/base_parser.rb
-- lib/web-page-parser/parsers/test_page_parser.rb
-- lib/web-page-parser/parsers/guardian_page_parser.rb
+- lib/web-page-parser/http.rb
+- lib/web-page-parser/parser_factory.rb
 - lib/web-page-parser/parsers/bbc_news_page_parser.rb
-- lib/web-page-parser.rb
-- README.rdoc
-- LICENSE
-- spec/parser_factory_spec.rb
+- lib/web-page-parser/parsers/guardian_page_parser.rb
+- lib/web-page-parser/parsers/independent_page_parser.rb
+- lib/web-page-parser/parsers/new_york_times_page_parser.rb
+- lib/web-page-parser/parsers/test_page_parser.rb
+- lib/web-page-parser/parsers/washingtonpost_page_parser.rb
 - spec/base_parser_spec.rb
-- spec/parsers/guardian_page_spec.rb
-- spec/parsers/bbc_news_page_spec.rb
-- spec/fixtures/guardian/anger-grows-rbs-chiefs-bonus.html
-- spec/fixtures/guardian/syria-libya-middle-east-unrest-live.html
-- spec/fixtures/bbc_news/10341015.stm.html
-- spec/fixtures/bbc_news/8029015.stm.html
-- spec/fixtures/bbc_news/7745137.stm.html
-- spec/fixtures/bbc_news/8063681.stm.html
 - spec/fixtures/bbc_news/10249066.stm.html
-- spec/fixtures/bbc_news/8011268.stm.html
+- spec/fixtures/bbc_news/10341015.stm.html
+- spec/fixtures/bbc_news/11125504.html
 - spec/fixtures/bbc_news/12921632.html
 - spec/fixtures/bbc_news/13293006.html
-- spec/fixtures/bbc_news/11125504.html
+- spec/fixtures/bbc_news/19957138.stm.html
+- spec/fixtures/bbc_news/20230333.stm.html
+- spec/fixtures/bbc_news/21528631.html
 - spec/fixtures/bbc_news/6072486.stm.html
+- spec/fixtures/bbc_news/7745137.stm.html
+- spec/fixtures/bbc_news/8011268.stm.html
+- spec/fixtures/bbc_news/8029015.stm.html
+- spec/fixtures/bbc_news/8040164.stm.html
+- spec/fixtures/bbc_news/8063681.stm.html
+- spec/fixtures/cassette_library/BbcNewsPageParserV4.yml
+- spec/fixtures/guardian/anger-grows-rbs-chiefs-bonus-with-explainer.html
+- spec/fixtures/guardian/anger-grows-rbs-chiefs-bonus.html
+- spec/fixtures/guardian/barack-obama-nicki-minaj-mariah-carey.html
+- spec/fixtures/guardian/nhs-patient-data-available-companies-buy.html
+- spec/fixtures/guardian/syria-libya-middle-east-unrest-live.html
+- spec/fixtures/independent/belgian-man-who-skipped-100-restaurant-bills-is-killed-9081407.html
+- spec/fixtures/independent/david-cameron-set-for-uturn-over-uk-sanctuary-9077647.html
+- spec/fixtures/independent/innocent-starving-close-to-death-one-victim-of-the-siege-that-shames-syria-9065538.html
+- spec/fixtures/independent/saudi-authorities-stop-textmessage-tracking-of-women-for-now-9065486.html
+- spec/fixtures/new_york_times/khaled-meshal-the-leader-of-hamas-vacates-damascus.html
+- spec/fixtures/new_york_times/show-banned-french-comedian-has-new-one.html
+- spec/fixtures/new_york_times/the-long-run-gingrich-stuck-to-caustic-path-in-ethics-battles.html
+- spec/fixtures/washingtonpost/pentagon-confirms-al-shabab-leader-killed.html
+- spec/fixtures/washingtonpost/sgt-bowe-bergdahls-capture-remains-amystery.html
+- spec/fixtures/washingtonpost/will-a-bust-follow-the-boom-in-britain.html
+- spec/parser_factory_spec.rb
+- spec/parsers/bbc_news_page_spec.rb
+- spec/parsers/guardian_page_spec.rb
+- spec/parsers/independent_page_parser_spec.rb
+- spec/parsers/new_york_times_page_parser_spec.rb
+- spec/parsers/washingtonpost_page_parser_spec.rb
 - spec/spec.opts
-homepage: http://github.com/johnl/web-page-parser/tree/master
-licenses: []
+- spec/spec_helper.rb
+homepage: http://github.com/johnl/web-page-parser
+licenses:
+- MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: web-page-parser
-rubygems_version: 1.8.23
+rubyforge_project: 
+rubygems_version: 2.2.2
 signing_key: 
-specification_version: 3
-summary: A parser for web pages
+specification_version: 4
+summary: A parser for various news organisation's web pages
 test_files:
-- spec/parser_factory_spec.rb
-- spec/base_parser_spec.rb
-- spec/parsers/guardian_page_spec.rb
-- spec/parsers/bbc_news_page_spec.rb
-- spec/fixtures/guardian/anger-grows-rbs-chiefs-bonus.html
+- spec/fixtures/new_york_times/show-banned-french-comedian-has-new-one.html
+- spec/fixtures/new_york_times/the-long-run-gingrich-stuck-to-caustic-path-in-ethics-battles.html
+- spec/fixtures/new_york_times/khaled-meshal-the-leader-of-hamas-vacates-damascus.html
 - spec/fixtures/guardian/syria-libya-middle-east-unrest-live.html
-- spec/fixtures/bbc_news/10341015.stm.html
-- spec/fixtures/bbc_news/8029015.stm.html
-- spec/fixtures/bbc_news/7745137.stm.html
-- spec/fixtures/bbc_news/8063681.stm.html
+- spec/fixtures/guardian/anger-grows-rbs-chiefs-bonus.html
+- spec/fixtures/guardian/anger-grows-rbs-chiefs-bonus-with-explainer.html
+- spec/fixtures/guardian/nhs-patient-data-available-companies-buy.html
+- spec/fixtures/guardian/barack-obama-nicki-minaj-mariah-carey.html
+- spec/fixtures/washingtonpost/sgt-bowe-bergdahls-capture-remains-amystery.html
+- spec/fixtures/washingtonpost/will-a-bust-follow-the-boom-in-britain.html
+- spec/fixtures/washingtonpost/pentagon-confirms-al-shabab-leader-killed.html
+- spec/fixtures/cassette_library/BbcNewsPageParserV4.yml
+- spec/fixtures/independent/innocent-starving-close-to-death-one-victim-of-the-siege-that-shames-syria-9065538.html
+- spec/fixtures/independent/david-cameron-set-for-uturn-over-uk-sanctuary-9077647.html
+- spec/fixtures/independent/belgian-man-who-skipped-100-restaurant-bills-is-killed-9081407.html
+- spec/fixtures/independent/saudi-authorities-stop-textmessage-tracking-of-women-for-now-9065486.html
+- spec/fixtures/bbc_news/20230333.stm.html
 - spec/fixtures/bbc_news/10249066.stm.html
-- spec/fixtures/bbc_news/8011268.stm.html
-- spec/fixtures/bbc_news/12921632.html
 - spec/fixtures/bbc_news/13293006.html
+- spec/fixtures/bbc_news/7745137.stm.html
+- spec/fixtures/bbc_news/8029015.stm.html
 - spec/fixtures/bbc_news/11125504.html
+- spec/fixtures/bbc_news/8040164.stm.html
+- spec/fixtures/bbc_news/21528631.html
+- spec/fixtures/bbc_news/10341015.stm.html
+- spec/fixtures/bbc_news/8063681.stm.html
+- spec/fixtures/bbc_news/19957138.stm.html
 - spec/fixtures/bbc_news/6072486.stm.html
+- spec/fixtures/bbc_news/8011268.stm.html
+- spec/fixtures/bbc_news/12921632.html
+- spec/base_parser_spec.rb
+- spec/parsers/washingtonpost_page_parser_spec.rb
+- spec/parsers/bbc_news_page_spec.rb
+- spec/parsers/guardian_page_spec.rb
+- spec/parsers/independent_page_parser_spec.rb
+- spec/parsers/new_york_times_page_parser_spec.rb
 - spec/spec.opts
-has_rdoc: true
+- spec/spec_helper.rb
+- spec/parser_factory_spec.rb

metadata.gz.sig

@@ -0,0 +1,2 @@
+um��^~c-6�q�!,+�[���ʷ�����̹���`Qݎ�5�a��l%�t�k�}5C
+�,�l��z@��ؾ:�?C�%�G�x�]�+"�バ
�����g֫_���{ě��$��t!z �l��Ҍ��=�no�Ui9����_W�IpH�&G��:��4��FLCM�X�}�}�Fdǩ�s�7w�zGcn��ʥ
�j\���`��@ӝ��FC]߾s9�"��G�~z�