youtube-transcript-rb 0.1.0

data/spec/integration_spec.rb

@@ -0,0 +1,363 @@
+# frozen_string_literal: true
+
+# Integration tests that make real HTTP requests to YouTube.
+# These tests are skipped by default to avoid network dependencies in CI.
+#
+# To run integration tests:
+#   INTEGRATION=1 bundle exec rspec spec/integration_spec.rb
+#
+# Or run all tests including integration:
+#   INTEGRATION=1 bundle exec rspec
+
+require "spec_helper"
+
+RSpec.describe "Integration Tests", :integration do
+  # Skip all integration tests unless INTEGRATION env var is set
+  before(:all) do
+    skip "Integration tests skipped. Set INTEGRATION=1 to run." unless ENV["INTEGRATION"]
+    WebMock.allow_net_connect!
+  end
+
+  after(:all) do
+    WebMock.disable_net_connect!(allow_localhost: true) if ENV["INTEGRATION"]
+  end
+
+  # Well-known videos that should have transcripts available
+  # Using popular, stable videos that are unlikely to be removed
+  let(:ted_talk_video_id) { "8jPQjjsBbIc" } # TED Talk - usually has good transcripts
+  let(:google_video_id) { "dQw4w9WgXcQ" }   # Rick Astley - Never Gonna Give You Up (very stable)
+
+  describe Youtube::Transcript::Rb::YouTubeTranscriptApi do
+    let(:api) { described_class.new }
+
+    describe "#list" do
+      it "fetches available transcripts for a video" do
+        transcript_list = api.list(ted_talk_video_id)
+
+        expect(transcript_list).to be_a(Youtube::Transcript::Rb::TranscriptList)
+        expect(transcript_list.video_id).to eq(ted_talk_video_id)
+        expect(transcript_list.count).to be > 0
+
+        # Print available transcripts for debugging
+        puts "\nAvailable transcripts for video #{ted_talk_video_id}:"
+        puts transcript_list.to_s
+      end
+
+      it "returns a TranscriptList that is enumerable" do
+        transcript_list = api.list(ted_talk_video_id)
+
+        transcript_list.each do |transcript|
+          expect(transcript).to be_a(Youtube::Transcript::Rb::Transcript)
+          expect(transcript.language_code).to be_a(String)
+          expect(transcript.language).to be_a(String)
+        end
+      end
+    end
+
+    describe "#fetch" do
+      it "fetches English transcript by default" do
+        transcript = api.fetch(ted_talk_video_id)
+
+        expect(transcript).to be_a(Youtube::Transcript::Rb::FetchedTranscript)
+        expect(transcript.video_id).to eq(ted_talk_video_id)
+        expect(transcript.snippets).not_to be_empty
+
+        first_snippet = transcript.first
+        expect(first_snippet).to be_a(Youtube::Transcript::Rb::TranscriptSnippet)
+        expect(first_snippet.text).to be_a(String)
+        expect(first_snippet.start).to be_a(Float)
+        expect(first_snippet.duration).to be_a(Float)
+
+        puts "\nFetched #{transcript.length} snippets"
+        puts "First snippet: #{first_snippet.text[0..50]}..."
+      end
+
+      it "fetches transcript with specific language" do
+        # Try to fetch English transcript
+        transcript = api.fetch(ted_talk_video_id, languages: ["en"])
+
+        expect(transcript.language_code).to eq("en")
+        expect(transcript.snippets).not_to be_empty
+      end
+
+      it "falls back to alternative language if primary not available" do
+        # Request Japanese first, then English as fallback
+        transcript = api.fetch(ted_talk_video_id, languages: ["ja", "en"])
+
+        expect(["ja", "en"]).to include(transcript.language_code)
+        expect(transcript.snippets).not_to be_empty
+      end
+
+      it "preserves HTML formatting when requested" do
+        transcript = api.fetch(ted_talk_video_id, preserve_formatting: true)
+
+        expect(transcript).to be_a(Youtube::Transcript::Rb::FetchedTranscript)
+        # Note: Not all videos have HTML formatting, so we just verify it doesn't break
+      end
+    end
+
+    describe "#fetch_all" do
+      it "fetches transcripts for multiple videos" do
+        video_ids = [ted_talk_video_id]
+        results = api.fetch_all(video_ids)
+
+        expect(results).to be_a(Hash)
+        expect(results.keys).to include(ted_talk_video_id)
+        expect(results[ted_talk_video_id]).to be_a(Youtube::Transcript::Rb::FetchedTranscript)
+      end
+
+      it "continues on error when option is set" do
+        video_ids = [ted_talk_video_id, "invalid_video_id_xyz"]
+        errors = []
+
+        results = api.fetch_all(video_ids, continue_on_error: true) do |video_id, result|
+          if result.is_a?(StandardError)
+            errors << { video_id: video_id, error: result }
+          end
+        end
+
+        expect(results).to have_key(ted_talk_video_id)
+        expect(errors.length).to be >= 0 # May or may not have errors
+      end
+    end
+  end
+
+  describe Youtube::Transcript::Rb do
+    describe ".fetch" do
+      it "provides convenience method for fetching transcripts" do
+        transcript = described_class.fetch(ted_talk_video_id)
+
+        expect(transcript).to be_a(Youtube::Transcript::Rb::FetchedTranscript)
+        expect(transcript.snippets).not_to be_empty
+      end
+    end
+
+    describe ".list" do
+      it "provides convenience method for listing transcripts" do
+        transcript_list = described_class.list(ted_talk_video_id)
+
+        expect(transcript_list).to be_a(Youtube::Transcript::Rb::TranscriptList)
+        expect(transcript_list.count).to be > 0
+      end
+    end
+  end
+
+  describe "Transcript Translation" do
+    it "translates a transcript to another language" do
+      api = Youtube::Transcript::Rb::YouTubeTranscriptApi.new
+      transcript_list = api.list(ted_talk_video_id)
+
+      # Find an English transcript
+      begin
+        transcript = transcript_list.find_transcript(["en"])
+      rescue Youtube::Transcript::Rb::NoTranscriptFound
+        skip "No English transcript available for this video"
+      end
+
+      if transcript.translatable?
+        # Try to translate to Spanish
+        begin
+          translated = transcript.translate("es")
+          fetched = translated.fetch
+
+          expect(fetched).to be_a(Youtube::Transcript::Rb::FetchedTranscript)
+          expect(fetched.language_code).to eq("es")
+          expect(fetched.snippets).not_to be_empty
+
+          puts "\nTranslated to Spanish: #{fetched.first.text[0..50]}..."
+        rescue Youtube::Transcript::Rb::TranslationLanguageNotAvailable
+          skip "Spanish translation not available for this video"
+        rescue Youtube::Transcript::Rb::IpBlocked
+          skip "IP blocked by YouTube - try again later or use a proxy"
+        end
+      else
+        skip "Transcript is not translatable"
+      end
+    end
+  end
+
+  describe "Formatters with Real Data" do
+    let(:api) { Youtube::Transcript::Rb::YouTubeTranscriptApi.new }
+    let(:transcript) { api.fetch(ted_talk_video_id) }
+
+    describe Youtube::Transcript::Rb::Formatters::JSONFormatter do
+      it "formats real transcript as JSON" do
+        formatter = described_class.new
+        output = formatter.format_transcript(transcript)
+
+        expect { JSON.parse(output) }.not_to raise_error
+        parsed = JSON.parse(output)
+        expect(parsed).to be_an(Array)
+        expect(parsed.first).to include("text", "start", "duration")
+      end
+    end
+
+    describe Youtube::Transcript::Rb::Formatters::TextFormatter do
+      it "formats real transcript as plain text" do
+        formatter = described_class.new
+        output = formatter.format_transcript(transcript)
+
+        expect(output).to be_a(String)
+        # Each snippet becomes one entry, but text may contain newlines
+        # so we just verify it's not empty and has reasonable content
+        expect(output).not_to be_empty
+        expect(output.length).to be > transcript.length
+      end
+    end
+
+    describe Youtube::Transcript::Rb::Formatters::SRTFormatter do
+      it "formats real transcript as SRT" do
+        formatter = described_class.new
+        output = formatter.format_transcript(transcript)
+
+        expect(output).to include("-->")
+        expect(output).to match(/^\d+$/m) # Sequence numbers
+
+        # Verify SRT timestamp format (HH:MM:SS,mmm)
+        expect(output).to match(/\d{2}:\d{2}:\d{2},\d{3}/)
+      end
+    end
+
+    describe Youtube::Transcript::Rb::Formatters::WebVTTFormatter do
+      it "formats real transcript as WebVTT" do
+        formatter = described_class.new
+        output = formatter.format_transcript(transcript)
+
+        expect(output).to start_with("WEBVTT")
+        expect(output).to include("-->")
+
+        # Verify WebVTT timestamp format (HH:MM:SS.mmm)
+        expect(output).to match(/\d{2}:\d{2}:\d{2}\.\d{3}/)
+      end
+    end
+
+    describe Youtube::Transcript::Rb::Formatters::PrettyPrintFormatter do
+      it "formats real transcript as pretty-printed output" do
+        formatter = described_class.new
+        output = formatter.format_transcript(transcript)
+
+        expect(output).to be_a(String)
+        expect(output).to include("text")
+        expect(output).to include("start")
+        expect(output).to include("duration")
+      end
+    end
+  end
+
+  describe "Error Handling" do
+    let(:api) { Youtube::Transcript::Rb::YouTubeTranscriptApi.new }
+
+    it "raises NoTranscriptFound for unavailable language" do
+      expect {
+        api.fetch(ted_talk_video_id, languages: ["xx"]) # Invalid language code
+      }.to raise_error(Youtube::Transcript::Rb::NoTranscriptFound)
+    end
+
+    it "raises appropriate error for invalid video ID" do
+      expect {
+        api.fetch("this_is_not_a_valid_video_id_12345")
+      }.to raise_error(Youtube::Transcript::Rb::CouldNotRetrieveTranscript)
+    end
+
+    it "raises TranscriptsDisabled for video without transcripts" do
+      # This test may need to be updated if the video gets transcripts
+      # or use a known video without transcripts
+      skip "Need a known video ID without transcripts"
+    end
+  end
+
+  describe "FetchedTranscript Interface" do
+    let(:api) { Youtube::Transcript::Rb::YouTubeTranscriptApi.new }
+    let(:transcript) { api.fetch(ted_talk_video_id) }
+
+    it "is enumerable" do
+      expect(transcript).to respond_to(:each)
+      expect(transcript).to respond_to(:map)
+      expect(transcript).to respond_to(:select)
+      expect(transcript).to respond_to(:first)
+      # Note: Enumerable doesn't provide #last by default, but we can use to_a.last
+      expect(transcript.to_a.last).to be_a(Youtube::Transcript::Rb::TranscriptSnippet)
+    end
+
+    it "is indexable" do
+      expect(transcript[0]).to be_a(Youtube::Transcript::Rb::TranscriptSnippet)
+      expect(transcript[-1]).to be_a(Youtube::Transcript::Rb::TranscriptSnippet)
+    end
+
+    it "has length" do
+      expect(transcript.length).to be > 0
+      expect(transcript.size).to eq(transcript.length)
+    end
+
+    it "converts to raw data" do
+      raw = transcript.to_raw_data
+
+      expect(raw).to be_an(Array)
+      expect(raw.first).to be_a(Hash)
+      expect(raw.first).to include("text", "start", "duration")
+    end
+
+    it "provides metadata" do
+      expect(transcript.video_id).to eq(ted_talk_video_id)
+      expect(transcript.language).to be_a(String)
+      expect(transcript.language_code).to be_a(String)
+      expect([true, false]).to include(transcript.is_generated)
+    end
+  end
+
+  describe "TranscriptList Interface" do
+    let(:api) { Youtube::Transcript::Rb::YouTubeTranscriptApi.new }
+    let(:transcript_list) { api.list(ted_talk_video_id) }
+
+    it "is enumerable" do
+      expect(transcript_list).to respond_to(:each)
+      expect(transcript_list).to respond_to(:map)
+      expect(transcript_list).to respond_to(:count)
+    end
+
+    it "finds transcripts by language" do
+      transcript = transcript_list.find_transcript(["en"])
+      expect(transcript).to be_a(Youtube::Transcript::Rb::Transcript)
+    end
+
+    it "provides string representation" do
+      output = transcript_list.to_s
+
+      expect(output).to include("MANUALLY CREATED")
+      expect(output).to include("GENERATED")
+      expect(output).to include(ted_talk_video_id)
+    end
+  end
+
+  describe "Transcript Object" do
+    let(:api) { Youtube::Transcript::Rb::YouTubeTranscriptApi.new }
+    let(:transcript_list) { api.list(ted_talk_video_id) }
+    let(:transcript) { transcript_list.find_transcript(["en"]) }
+
+    it "provides metadata properties" do
+      expect(transcript.video_id).to eq(ted_talk_video_id)
+      expect(transcript.language).to be_a(String)
+      expect(transcript.language_code).to eq("en")
+      expect([true, false]).to include(transcript.is_generated)
+    end
+
+    it "indicates translatability" do
+      expect([true, false]).to include(transcript.translatable?)
+      expect(transcript.translation_languages).to be_an(Array)
+    end
+
+    it "fetches transcript data" do
+      fetched = transcript.fetch
+
+      expect(fetched).to be_a(Youtube::Transcript::Rb::FetchedTranscript)
+      expect(fetched.snippets).not_to be_empty
+    end
+
+    it "provides string representation" do
+      output = transcript.to_s
+
+      expect(output).to include(transcript.language_code)
+      expect(output).to include(transcript.language)
+    end
+  end
+end

data/spec/settings_spec.rb

@@ -0,0 +1,67 @@
+# frozen_string_literal: true
+
+require "spec_helper"
+require "youtube/transcript/rb"
+
+RSpec.describe "Youtube::Transcript::Rb Settings" do
+  describe "WATCH_URL" do
+    it "is defined" do
+      expect(Youtube::Transcript::Rb::WATCH_URL).not_to be_nil
+    end
+
+    it "is a YouTube watch URL template" do
+      expect(Youtube::Transcript::Rb::WATCH_URL).to include("youtube.com/watch")
+    end
+
+    it "contains video_id placeholder" do
+      expect(Youtube::Transcript::Rb::WATCH_URL).to include("%<video_id>s")
+    end
+
+    it "can be formatted with a video_id" do
+      url = format(Youtube::Transcript::Rb::WATCH_URL, video_id: "abc123")
+      expect(url).to eq("https://www.youtube.com/watch?v=abc123")
+    end
+  end
+
+  describe "INNERTUBE_API_URL" do
+    it "is defined" do
+      expect(Youtube::Transcript::Rb::INNERTUBE_API_URL).not_to be_nil
+    end
+
+    it "is a YouTube API URL" do
+      expect(Youtube::Transcript::Rb::INNERTUBE_API_URL).to include("youtube.com/youtubei")
+    end
+
+    it "contains api_key placeholder" do
+      expect(Youtube::Transcript::Rb::INNERTUBE_API_URL).to include("%<api_key>s")
+    end
+
+    it "can be formatted with an api_key" do
+      url = format(Youtube::Transcript::Rb::INNERTUBE_API_URL, api_key: "my_api_key")
+      expect(url).to eq("https://www.youtube.com/youtubei/v1/player?key=my_api_key")
+    end
+  end
+
+  describe "INNERTUBE_CONTEXT" do
+    it "is defined" do
+      expect(Youtube::Transcript::Rb::INNERTUBE_CONTEXT).not_to be_nil
+    end
+
+    it "is a frozen hash" do
+      expect(Youtube::Transcript::Rb::INNERTUBE_CONTEXT).to be_frozen
+    end
+
+    it "contains client configuration" do
+      expect(Youtube::Transcript::Rb::INNERTUBE_CONTEXT).to have_key("client")
+    end
+
+    it "specifies clientName as ANDROID" do
+      expect(Youtube::Transcript::Rb::INNERTUBE_CONTEXT["client"]["clientName"]).to eq("ANDROID")
+    end
+
+    it "specifies a clientVersion" do
+      expect(Youtube::Transcript::Rb::INNERTUBE_CONTEXT["client"]["clientVersion"]).not_to be_nil
+      expect(Youtube::Transcript::Rb::INNERTUBE_CONTEXT["client"]["clientVersion"]).to be_a(String)
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,109 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause
+# this file to always be loaded, without a need to explicitly require it in any
+# files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need
+# it.
+#
+# See https://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+
+require "bundler/setup"
+require "youtube/transcript/rb"
+require "webmock/rspec"
+require "faraday"
+
+WebMock.disable_net_connect!(allow_localhost: true)
+
+RSpec.configure do |config|
+  # Exclude integration tests by default
+  # Run with: INTEGRATION=1 bundle exec rspec
+  config.filter_run_excluding integration: true unless ENV["INTEGRATION"]
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    #     be_bigger_than(2).and_smaller_than(4).description
+    #     # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #     # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+  # This option will default to `:apply_to_host_groups` in RSpec 4 (and will
+  # have no way to turn it off -- the option exists only for backwards
+  # compatibility in RSpec 3). It causes shared context metadata to be
+  # inherited by the metadata hash of host groups and examples, rather than
+  # triggering implicit auto-inclusion in groups with matching metadata.
+  config.shared_context_metadata_behavior = :apply_to_host_groups
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # This allows you to limit a spec run to individual examples or groups
+  # you care about by tagging them with `:focus` metadata. When nothing
+  # is tagged with `:focus`, all examples get run. RSpec also provides
+  # aliases for `it`, `describe`, and `context` that include `:focus`
+  # metadata: `fit`, `fdescribe` and `fcontext`, respectively.
+  config.filter_run_when_matching :focus
+
+  # Allows RSpec to persist some state between runs in order to support
+  # the `--only-failures` and `--next-failure` CLI options. We recommend
+  # you configure your source control system to ignore this file.
+  config.example_status_persistence_file_path = "spec/examples.txt"
+
+  # Limits the available syntax to the non-monkey patched syntax that is
+  # recommended. For more details, see:
+  # https://rspec.info/features/3-12/rspec-core/configuration/zero-monkey-patching-mode/
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = "doc"
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+=end
+end