simple-rss 1.3.3 → 2.1.0

data/simple-rss.gemspec

@@ -1,15 +1,14 @@
 Gem::Specification.new do |s|
   s.name = "simple-rss"
-  s.version = "1.3.3"
-  s.version = "#{s.version}-alpha-#{ENV['TRAVIS_BUILD_NUMBER']}" if ENV['TRAVIS']
-  s.date = "2015-08-17"
+  s.version = "2.1.0"
+  s.date = "2025-12-29"
   s.summary = "A simple, flexible, extensible, and liberal RSS and Atom reader for Ruby. It is designed to be backwards compatible with the standard RSS parser, but will never do RSS generation."
   s.email = "lucas@rufy.com"
-  s.homepage = "http://github.com/cardmagic/simple-rss"
+  s.homepage = "https://github.com/cardmagic/simple-rss"
   s.description = "A simple, flexible, extensible, and liberal RSS and Atom reader for Ruby. It is designed to be backwards compatible with the standard RSS parser, but will never do RSS generation."
   s.authors = ["Lucas Carlson"]
-  s.files = ["install.rb", "lib", "lib/simple-rss.rb", "LICENSE", "Rakefile", "README.markdown", "simple-rss.gemspec", "test", "test/base", "test/base/base_test.rb", "test/data", "test/data/atom.xml", "test/data/not-rss.xml", "test/data/rss09.rdf", "test/data/rss20.xml", "test/test_helper.rb"]
-  s.rubyforge_project = 'simple-rss'
+  s.files = Dir["lib/**/*", "test/**/*", "LICENSE", "README.md", "Rakefile", "simple-rss.gemspec"]
+  s.required_ruby_version = ">= 3.1"
   s.add_development_dependency "rake"
   s.add_development_dependency "rdoc"
   s.add_development_dependency "test-unit"

data/test/base/array_tags_test.rb

@@ -0,0 +1,37 @@
+require "test_helper"
+
+class ArrayTagsTest < Test::Unit::TestCase
+  def setup
+    @rss20 = SimpleRSS.parse(
+      open(File.dirname(__FILE__) + "/../data/rss20.xml"),
+      array_tags: [:category]
+    )
+    @rss20_no_array = SimpleRSS.parse(
+      open(File.dirname(__FILE__) + "/../data/rss20.xml")
+    )
+  end
+
+  def test_array_tag_returns_array
+    assert_kind_of Array, @rss20.items.first.category
+  end
+
+  def test_array_tag_contains_all_values
+    categories = @rss20.items.first.category
+    assert_equal 2, categories.size
+    assert_includes categories, "Programming"
+    assert_includes categories, "Ruby"
+  end
+
+  def test_single_value_still_returns_array
+    # Item with only one category should still return an array
+    categories = @rss20.items[2].category
+    assert_kind_of Array, categories
+    assert_equal 1, categories.size
+    assert_equal ["General"], categories
+  end
+
+  def test_without_array_tags_returns_string
+    # Default behavior should return just the first/last match as a string
+    assert_kind_of String, @rss20_no_array.items.first.category
+  end
+end

data/test/base/base_test.rb

@@ -1,83 +1,82 @@
-# -*- coding: utf-8 -*-
-require 'test_helper'
+require "test_helper"
 class BaseTest < Test::Unit::TestCase
-	def setup
-		@rss09 = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/rss09.rdf')
-		@rss20 = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/rss20.xml')
-                @rss20_utf8 = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/rss20_utf8.xml')
-		@media_rss = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/media_rss.xml')
-		@atom = SimpleRSS.parse open(File.dirname(__FILE__) + '/../data/atom.xml')
-	end
-	
-	def test_channel
-		assert_equal @rss09, @rss09.channel
-		assert_equal @rss20, @rss20.channel
-		assert_equal @atom, @atom.feed
-	end
-	
-	def test_items
-		assert_kind_of Array, @rss09.items
-		assert_kind_of Array, @rss20.items
-		assert_kind_of Array, @atom.entries
-	end
-	
-	def test_rss09
-		assert_equal 10, @rss09.items.size
-		assert_equal "Slashdot", @rss09.title
-		assert_equal "http://slashdot.org/", @rss09.channel.link
-		assert_equal "http://books.slashdot.org/article.pl?sid=05/08/29/1319236&amp;from=rss", @rss09.items.first.link
-		assert_equal "http://books.slashdot.org/article.pl?sid=05/08/29/1319236&amp;from=rss", @rss09.items.first[:link]
+  def setup
+    @rss09 = SimpleRSS.parse open(File.dirname(__FILE__) + "/../data/rss09.rdf")
+    @rss20 = SimpleRSS.parse open(File.dirname(__FILE__) + "/../data/rss20.xml")
+    @rss20_utf8 = SimpleRSS.parse open(File.dirname(__FILE__) + "/../data/rss20_utf8.xml")
+    @media_rss = SimpleRSS.parse open(File.dirname(__FILE__) + "/../data/media_rss.xml")
+    @atom = SimpleRSS.parse open(File.dirname(__FILE__) + "/../data/atom.xml")
+  end
+
+  def test_channel
+    assert_equal @rss09, @rss09.channel
+    assert_equal @rss20, @rss20.channel
+    assert_equal @atom, @atom.feed
+  end
+
+  def test_items
+    assert_kind_of Array, @rss09.items
+    assert_kind_of Array, @rss20.items
+    assert_kind_of Array, @atom.entries
+  end
+
+  def test_rss09
+    assert_equal 10, @rss09.items.size
+    assert_equal "Slashdot", @rss09.title
+    assert_equal "http://slashdot.org/", @rss09.channel.link
+    assert_equal "http://books.slashdot.org/article.pl?sid=05/08/29/1319236&amp;from=rss", @rss09.items.first.link
+    assert_equal "http://books.slashdot.org/article.pl?sid=05/08/29/1319236&amp;from=rss", @rss09.items.first[:link]
     assert_equal Time.parse("Wed Aug 24 13:33:34 UTC 2005"), @rss20.items.first.pubDate
     assert_equal Time.parse("Fri Sep 09 02:52:31 PDT 2005"), @rss09.channel.dc_date
-	end
+  end
+
+  def test_media_rss
+    assert_equal 20, @media_rss.items.size
+    assert_equal "Uploads from herval", @media_rss.title
+    assert_equal "http://www.flickr.com/photos/herval/", @media_rss.channel.link
+    assert_equal "http://www.flickr.com/photos/herval/4671960608/", @media_rss.items.first.link
+    assert_equal "http://www.flickr.com/photos/herval/4671960608/", @media_rss.items.first[:link]
+    assert_equal "http://farm5.static.flickr.com/4040/4671960608_10cb945d5c_o.jpg", @media_rss.items.first.media_content_url
+    assert_equal "image/jpeg", @media_rss.items.first.media_content_type
+    assert_equal "3168", @media_rss.items.first.media_content_height
+    assert_equal "4752", @media_rss.items.first.media_content_width
+    assert_equal "Woof?", @media_rss.items.first.media_title
+    assert_equal "http://farm5.static.flickr.com/4040/4671960608_954d2297bc_s.jpg", @media_rss.items.first.media_thumbnail_url
+    assert_equal "75", @media_rss.items.first.media_thumbnail_height
+    assert_equal "75", @media_rss.items.first.media_thumbnail_width
+    assert_equal "herval", @media_rss.items.first.media_credit
+    assert_equal "photographer", @media_rss.items.first.media_credit_role
+    assert_equal "pets frodo", @media_rss.items.first.media_category
+    assert_equal "urn:flickr:tags", @media_rss.items.first.media_category_scheme
+  end
+
+  def test_rss20
+    assert_equal 10, @rss20.items.size
+    assert_equal "Technoblog", @rss20.title
+    assert_equal "http://tech.rufy.com", @rss20.channel.link
+    assert_equal "http://feeds.feedburner.com/rufytech?m=68", @rss20.items.first.link
+    assert_equal "http://feeds.feedburner.com/rufytech?m=68", @rss20.items.first[:link]
+    assert_equal "This is an XML content feed. It is intended to be viewed in a newsreader or syndicated to another site.", @rss20.channel.feedburner_browserFriendly
+  end
+
+  def test_atom
+    assert_equal 1, @atom.entries.size
+    assert_equal "dive into mark", @atom.title
+    assert_equal "http://example.org/", @atom.feed.link
+    assert_equal "http://example.org/2005/04/02/atom", @atom.entries.first.link
+    assert_equal "http://example.org/2005/04/02/atom", @atom.entries.first[:link]
+  end
 
-	def test_media_rss
-		assert_equal 20, @media_rss.items.size
-		assert_equal "Uploads from herval", @media_rss.title
-		assert_equal "http://www.flickr.com/photos/herval/", @media_rss.channel.link
-		assert_equal "http://www.flickr.com/photos/herval/4671960608/", @media_rss.items.first.link
-		assert_equal "http://www.flickr.com/photos/herval/4671960608/", @media_rss.items.first[:link]
-		assert_equal "http://farm5.static.flickr.com/4040/4671960608_10cb945d5c_o.jpg", @media_rss.items.first.media_content_url
-		assert_equal "image/jpeg", @media_rss.items.first.media_content_type
-		assert_equal "3168", @media_rss.items.first.media_content_height
-		assert_equal "4752", @media_rss.items.first.media_content_width
-		assert_equal "Woof?", @media_rss.items.first.media_title
-		assert_equal "http://farm5.static.flickr.com/4040/4671960608_954d2297bc_s.jpg", @media_rss.items.first.media_thumbnail_url
-		assert_equal "75", @media_rss.items.first.media_thumbnail_height
-		assert_equal "75", @media_rss.items.first.media_thumbnail_width
-		assert_equal "herval", @media_rss.items.first.media_credit
-		assert_equal "photographer", @media_rss.items.first.media_credit_role
-		assert_equal "pets frodo", @media_rss.items.first.media_category
-		assert_equal "urn:flickr:tags", @media_rss.items.first.media_category_scheme
-	end
-	
-	def test_rss20
-		assert_equal 10, @rss20.items.size
-		assert_equal "Technoblog", @rss20.title
-		assert_equal "http://tech.rufy.com", @rss20.channel.link
-		assert_equal "http://feeds.feedburner.com/rufytech?m=68", @rss20.items.first.link
-		assert_equal "http://feeds.feedburner.com/rufytech?m=68", @rss20.items.first[:link]
-		assert_equal "This is an XML content feed. It is intended to be viewed in a newsreader or syndicated to another site.", @rss20.channel.feedburner_browserFriendly
-	end
-	
-	def test_atom
-		assert_equal 1, @atom.entries.size
-		assert_equal "dive into mark", @atom.title
-		assert_equal "http://example.org/", @atom.feed.link
-		assert_equal "http://example.org/2005/04/02/atom", @atom.entries.first.link
-		assert_equal "http://example.org/2005/04/02/atom", @atom.entries.first[:link]
-	end
-	
-	def test_bad_feed
-	  assert_raise(SimpleRSSError) { SimpleRSS.parse(open(File.dirname(__FILE__) + '/../data/not-rss.xml')) }
-	end
+  def test_bad_feed
+    assert_raise(SimpleRSSError) { SimpleRSS.parse(open(File.dirname(__FILE__) + "/../data/not-rss.xml")) }
+  end
 
-        def test_rss_utf8
-		assert_equal 2, @rss20_utf8.items.size
-		assert_equal "SC5 Blog", @rss20_utf8.title
-		assert_equal Encoding::UTF_8, @rss20_utf8.title.encoding
-		item = @rss20_utf8.items.first
-		assert_equal "Mitä asiakkaamme ajattelevat meistä?", item.title
-		assert_equal Encoding::UTF_8, item.title.encoding
-	end
+  def test_rss_utf8
+    assert_equal 2, @rss20_utf8.items.size
+    assert_equal "SC5 Blog", @rss20_utf8.title
+    assert_equal Encoding::UTF_8, @rss20_utf8.title.encoding
+    item = @rss20_utf8.items.first
+    assert_equal "Mitä asiakkaamme ajattelevat meistä?", item.title
+    assert_equal Encoding::UTF_8, item.title.encoding
+  end
 end

data/test/base/empty_tag_test.rb

@@ -0,0 +1,56 @@
+require_relative "../test_helper"
+require "timeout"
+
+class EmptyTagTest < Test::Unit::TestCase
+  def setup
+    @rss20 = SimpleRSS.parse(open(File.dirname(__FILE__) + "/../data/rss20.xml"))
+  end
+
+  def test_empty_item_tag_does_not_hang
+    # Reproduces issue #16: 100% cpu and hanging process on blank item tag
+    # Adding an empty tag should not cause regex catastrophic backtracking
+    original_tags = SimpleRSS.item_tags.dup
+
+    begin
+      SimpleRSS.item_tags << :""
+
+      # This should complete quickly, not hang
+      Timeout.timeout(5) do
+        rss = SimpleRSS.parse(open(File.dirname(__FILE__) + "/../data/rss20.xml"))
+        assert_not_nil rss.items
+      end
+    ensure
+      SimpleRSS.item_tags.replace(original_tags)
+    end
+  end
+
+  def test_blank_item_tag_does_not_hang
+    original_tags = SimpleRSS.item_tags.dup
+
+    begin
+      SimpleRSS.item_tags << :"   "
+
+      Timeout.timeout(5) do
+        rss = SimpleRSS.parse(open(File.dirname(__FILE__) + "/../data/rss20.xml"))
+        assert_not_nil rss.items
+      end
+    ensure
+      SimpleRSS.item_tags.replace(original_tags)
+    end
+  end
+
+  def test_empty_feed_tag_does_not_hang
+    original_tags = SimpleRSS.feed_tags.dup
+
+    begin
+      SimpleRSS.feed_tags << :""
+
+      Timeout.timeout(5) do
+        rss = SimpleRSS.parse(open(File.dirname(__FILE__) + "/../data/rss20.xml"))
+        assert_not_nil rss.channel
+      end
+    ensure
+      SimpleRSS.feed_tags.replace(original_tags)
+    end
+  end
+end

data/test/base/encoding_test.rb

@@ -0,0 +1,87 @@
+require_relative "../test_helper"
+
+class EncodingTest < Test::Unit::TestCase
+  def test_strings_are_utf8_encoded
+    rss = SimpleRSS.parse(open(File.dirname(__FILE__) + "/../data/rss20.xml"))
+
+    assert_equal Encoding::UTF_8, rss.title.encoding
+    assert_equal Encoding::UTF_8, rss.link.encoding
+    assert_equal Encoding::UTF_8, rss.description.encoding
+  end
+
+  def test_strings_without_percent_are_utf8_encoded
+    # Issue #28: strings without '%' were returning ASCII-8BIT
+    rss = SimpleRSS.parse(open(File.dirname(__FILE__) + "/../data/rss20.xml"))
+
+    rss.items.each do |item|
+      assert_equal Encoding::UTF_8, item.title.encoding, "Item title should be UTF-8"
+      assert_equal Encoding::UTF_8, item.link.encoding, "Item link should be UTF-8"
+    end
+  end
+
+  def test_utf8_content_preserved
+    rss = SimpleRSS.parse(open(File.dirname(__FILE__) + "/../data/rss20_utf8.xml"))
+
+    assert_equal Encoding::UTF_8, rss.title.encoding
+    # Verify UTF-8 characters are preserved
+    assert(rss.items.any? { |item| item.title && item.title.encoding == Encoding::UTF_8 })
+  end
+
+  def test_ascii_8bit_source_normalized_to_utf8
+    # Issue #28: when source is ASCII-8BIT, output should still be UTF-8
+    xml = <<~XML.b # .b forces ASCII-8BIT encoding
+      <?xml version="1.0"?>
+      <rss version="2.0">
+        <channel>
+          <title>Test Feed</title>
+          <link>http://example.com</link>
+          <description>A test feed</description>
+          <item>
+            <title>Test Item</title>
+            <link>http://example.com/item</link>
+          </item>
+        </channel>
+      </rss>
+    XML
+
+    assert_equal Encoding::ASCII_8BIT, xml.encoding, "Source should be ASCII-8BIT"
+
+    rss = SimpleRSS.parse(xml)
+
+    assert_equal Encoding::UTF_8, rss.title.encoding, "Title should be UTF-8"
+    assert_equal Encoding::UTF_8, rss.link.encoding, "Link should be UTF-8"
+    assert_equal Encoding::UTF_8, rss.items.first.title.encoding, "Item title should be UTF-8"
+  end
+
+  def test_consistent_encoding_with_and_without_percent
+    # Issue #28: CGI.unescape returns UTF-8, but without '%' we got ASCII-8BIT
+    xml_with_percent = <<~XML.b
+      <?xml version="1.0"?>
+      <rss version="2.0">
+        <channel>
+          <title>Test%20Feed</title>
+          <link>http://example.com</link>
+          <description>Test</description>
+        </channel>
+      </rss>
+    XML
+
+    xml_without_percent = <<~XML.b
+      <?xml version="1.0"?>
+      <rss version="2.0">
+        <channel>
+          <title>Test Feed</title>
+          <link>http://example.com</link>
+          <description>Test</description>
+        </channel>
+      </rss>
+    XML
+
+    rss_with = SimpleRSS.parse(xml_with_percent)
+    rss_without = SimpleRSS.parse(xml_without_percent)
+
+    assert_equal rss_with.title.encoding, rss_without.title.encoding,
+                 "Encoding should be consistent regardless of '%' in content"
+    assert_equal Encoding::UTF_8, rss_without.title.encoding
+  end
+end

data/test/base/enumerable_test.rb

@@ -0,0 +1,101 @@
+require "test_helper"
+
+class EnumerableTest < Test::Unit::TestCase
+  def setup
+    @rss20 = SimpleRSS.parse open(File.dirname(__FILE__) + "/../data/rss20.xml")
+    @atom = SimpleRSS.parse open(File.dirname(__FILE__) + "/../data/atom.xml")
+  end
+
+  def test_includes_enumerable
+    assert_includes SimpleRSS.included_modules, Enumerable
+  end
+
+  def test_each_iterates_over_items
+    titles = @rss20.map { |item| item[:title] }
+    assert_equal @rss20.items.map { |i| i[:title] }, titles
+  end
+
+  def test_each_returns_enumerator_without_block
+    enumerator = @rss20.each
+    assert_kind_of Enumerator, enumerator
+    assert_equal @rss20.items.size, enumerator.count
+  end
+
+  def test_each_returns_self_with_block
+    count = 0
+    result = @rss20.each { |_item| count += 1 }
+    assert_equal @rss20, result
+    assert_equal @rss20.items.size, count
+  end
+
+  def test_enumerable_map
+    titles = @rss20.map { |item| item[:title] }
+    assert_equal @rss20.items.map { |i| i[:title] }, titles
+  end
+
+  def test_enumerable_select
+    items_with_link = @rss20.select { |item| item[:link] }
+    assert_equal @rss20.items.select { |i| i[:link] }, items_with_link
+  end
+
+  def test_enumerable_first
+    assert_equal @rss20.items.first, @rss20.first
+    assert_equal @rss20.items.first(3), @rss20.first(3)
+  end
+
+  def test_enumerable_count
+    assert_equal @rss20.items.size, @rss20.count
+  end
+
+  def test_index_accessor
+    assert_equal @rss20.items[0], @rss20[0]
+    assert_equal @rss20.items[5], @rss20[5]
+    assert_equal @rss20.items[-1], @rss20[-1]
+  end
+
+  def test_index_accessor_out_of_bounds
+    assert_nil @rss20[100]
+  end
+
+  def test_latest_returns_sorted_items
+    latest = @rss20.latest(3)
+    assert_equal 3, latest.size
+
+    dates = latest.map { |item| item[:pubDate] }
+    assert_equal dates, dates.sort.reverse
+  end
+
+  def test_latest_default_count
+    latest = @rss20.latest
+    assert latest.size <= 10
+  end
+
+  def test_latest_with_atom_uses_updated
+    latest = @atom.latest(1)
+    assert_equal 1, latest.size
+  end
+
+  def test_latest_handles_missing_dates
+    rss_with_missing_dates = SimpleRSS.parse <<~RSS
+      <?xml version="1.0" encoding="UTF-8"?>
+      <rss version="2.0">
+        <channel>
+          <title>Test Feed</title>
+          <link>http://example.com</link>
+          <item>
+            <title>No Date</title>
+          </item>
+          <item>
+            <title>Has Date</title>
+            <pubDate>Wed, 24 Aug 2005 13:33:34 GMT</pubDate>
+          </item>
+        </channel>
+      </rss>
+    RSS
+
+    latest = rss_with_missing_dates.latest(2)
+    assert_equal 2, latest.size
+    assert_equal "Has Date", latest.first[:title]
+    assert_equal "No Date", latest.last[:title]
+  end
+end

data/test/base/feed_attributes_test.rb

@@ -0,0 +1,26 @@
+require "test_helper"
+
+class FeedAttributesTest < Test::Unit::TestCase
+  def setup
+    # Add feed attribute tags before parsing
+    SimpleRSS.feed_tags << :"channel#custom:version"
+    SimpleRSS.feed_tags << :"feed#app:id"
+
+    @rss20 = SimpleRSS.parse open(File.dirname(__FILE__) + "/../data/rss20_with_channel_attrs.xml")
+    @atom = SimpleRSS.parse open(File.dirname(__FILE__) + "/../data/atom_with_feed_attrs.xml")
+  end
+
+  def teardown
+    # Clean up added tags
+    SimpleRSS.feed_tags.delete(:"channel#custom:version")
+    SimpleRSS.feed_tags.delete(:"feed#app:id")
+  end
+
+  def test_rss20_channel_attribute
+    assert_equal "2.0", @rss20.channel_custom_version
+  end
+
+  def test_atom_feed_attribute
+    assert_equal "12345", @atom.feed_app_id
+  end
+end

data/test/base/fetch_test.rb

@@ -0,0 +1,117 @@
+require "test_helper"
+require "net/http"
+
+class FetchTest < Test::Unit::TestCase
+  def setup
+    @sample_feed = File.read(File.dirname(__FILE__) + "/../data/rss20.xml")
+  end
+
+  # Test attr_readers exist and default to nil for parsed feeds
+
+  def test_etag_attr_reader_exists
+    rss = SimpleRSS.parse(@sample_feed)
+    assert_respond_to rss, :etag
+  end
+
+  def test_last_modified_attr_reader_exists
+    rss = SimpleRSS.parse(@sample_feed)
+    assert_respond_to rss, :last_modified
+  end
+
+  def test_etag_nil_for_parsed_feed
+    rss = SimpleRSS.parse(@sample_feed)
+    assert_nil rss.etag
+  end
+
+  def test_last_modified_nil_for_parsed_feed
+    rss = SimpleRSS.parse(@sample_feed)
+    assert_nil rss.last_modified
+  end
+
+  # Test fetch class method exists
+
+  def test_fetch_class_method_exists
+    assert_respond_to SimpleRSS, :fetch
+  end
+
+  # Test fetch with invalid URL raises error
+
+  def test_fetch_raises_on_invalid_host
+    # Socket::ResolutionError was added in Ruby 3.3, use SocketError for older versions
+    expected_errors = [SocketError, Errno::ECONNREFUSED, SimpleRSSError]
+    expected_errors << Socket::ResolutionError if defined?(Socket::ResolutionError)
+    assert_raise(*expected_errors) do
+      SimpleRSS.fetch("http://this-host-does-not-exist-12345.invalid/feed.xml", timeout: 1)
+    end
+  end
+
+  # Test fetch options are accepted
+
+  def test_fetch_accepts_etag_option
+    # Just verify it doesn't raise an ArgumentError
+    assert_nothing_raised do
+      SimpleRSS.fetch("http://localhost:1/feed.xml", etag: '"abc123"', timeout: 0.1)
+    rescue StandardError
+      # Expected - connection will fail
+    end
+  end
+
+  def test_fetch_accepts_last_modified_option
+    assert_nothing_raised do
+      SimpleRSS.fetch("http://localhost:1/feed.xml", last_modified: "Wed, 21 Oct 2015 07:28:00 GMT", timeout: 0.1)
+    rescue StandardError
+      # Expected - connection will fail
+    end
+  end
+
+  def test_fetch_accepts_headers_option
+    assert_nothing_raised do
+      SimpleRSS.fetch("http://localhost:1/feed.xml", headers: { "X-Custom" => "test" }, timeout: 0.1)
+    rescue StandardError
+      # Expected - connection will fail
+    end
+  end
+
+  def test_fetch_accepts_timeout_option
+    assert_nothing_raised do
+      SimpleRSS.fetch("http://localhost:1/feed.xml", timeout: 0.1)
+    rescue StandardError
+      # Expected - connection will fail
+    end
+  end
+
+  def test_fetch_accepts_follow_redirects_option
+    assert_nothing_raised do
+      SimpleRSS.fetch("http://localhost:1/feed.xml", follow_redirects: false, timeout: 0.1)
+    rescue StandardError
+      # Expected - connection will fail
+    end
+  end
+end
+
+# Integration tests that require network access
+# These are skipped by default, run with NETWORK_TESTS=1
+class FetchIntegrationTest < Test::Unit::TestCase
+  def test_fetch_real_feed
+    omit unless ENV["NETWORK_TESTS"]
+    # Use a reliable, long-lived RSS feed
+    rss = SimpleRSS.fetch("https://feeds.bbci.co.uk/news/rss.xml", timeout: 10)
+    assert_kind_of SimpleRSS, rss
+    assert rss.title
+    assert rss.items.any?
+  end
+
+  def test_fetch_stores_caching_headers
+    omit unless ENV["NETWORK_TESTS"]
+    rss = SimpleRSS.fetch("https://feeds.bbci.co.uk/news/rss.xml", timeout: 10)
+    # At least one of these should be present for most feeds
+    assert(rss.etag || rss.last_modified, "Expected ETag or Last-Modified header")
+  end
+
+  def test_fetch_follows_redirect
+    omit unless ENV["NETWORK_TESTS"]
+    # GitHub raw URLs often redirect
+    rss = SimpleRSS.fetch("https://github.com/cardmagic/simple-rss/commits/master.atom", timeout: 10)
+    assert_kind_of SimpleRSS, rss
+  end
+end