Module: Html2rss

Defined in:
lib/html2rss.rb,
lib/html2rss/cli.rb,
lib/html2rss/mcp.rb,
lib/html2rss/sst.rb,
lib/html2rss/url.rb,
lib/html2rss/html.rb,
lib/html2rss/test.rb,
lib/html2rss/batch.rb,
lib/html2rss/error.rb,
lib/html2rss/recon.rb,
lib/html2rss/config.rb,
lib/html2rss/status.rb,
lib/html2rss/article.rb,
lib/html2rss/capture.rb,
lib/html2rss/channel.rb,
lib/html2rss/scoring.rb,
lib/html2rss/version.rb,
lib/html2rss/defaults.rb,
lib/html2rss/sst/node.rb,
lib/html2rss/sst/tags.rb,
lib/html2rss/sst/text.rb,
lib/html2rss/hash_util.rb,
lib/html2rss/selectors.rb,
lib/html2rss/sst/attrs.rb,
lib/html2rss/sst/index.rb,
lib/html2rss/cli/render.rb,
lib/html2rss/html/probe.rb,
lib/html2rss/mcp/server.rb,
lib/html2rss/page_recon.rb,
lib/html2rss/auto_source.rb,
lib/html2rss/feed_result.rb,
lib/html2rss/mcp/outcome.rb,
lib/html2rss/mcp/runtime.rb,
lib/html2rss/syndication.rb,
lib/html2rss/cli/validate.rb,
lib/html2rss/feed_builder.rb,
lib/html2rss/mcp/contract.rb,
lib/html2rss/sst/document.rb,
lib/html2rss/config/schema.rb,
lib/html2rss/feed_pipeline.rb,
lib/html2rss/scoring/score.rb,
lib/html2rss/scrape_target.rb,
lib/html2rss/cli/probe_view.rb,
lib/html2rss/html/card_walk.rb,
lib/html2rss/html/feed_link.rb,
lib/html2rss/html/navigator.rb,
lib/html2rss/html/rendering.rb,
lib/html2rss/scoring/engine.rb,
lib/html2rss/sst/normalizer.rb,
lib/html2rss/feed_resolution.rb,
lib/html2rss/request_service.rb,
lib/html2rss/request_session.rb,
lib/html2rss/config/validator.rb,
lib/html2rss/feed_builder/rss.rb,
lib/html2rss/link_destination.rb,
lib/html2rss/mcp/server/tools.rb,
lib/html2rss/surface_category.rb,
lib/html2rss/article/enclosure.rb,
lib/html2rss/doctor/botasaurus.rb,
lib/html2rss/html/article_rules.rb,
lib/html2rss/syndication/parser.rb,
lib/html2rss/test/enhance_audit.rb,
lib/html2rss/auto_source/cleanup.rb,
lib/html2rss/auto_source/scraper.rb,
lib/html2rss/auto_source/segment.rb,
lib/html2rss/mcp/config_argument.rb,
lib/html2rss/scoring/observation.rb,
lib/html2rss/article/deduplicator.rb,
lib/html2rss/feed_resolution/diag.rb,
lib/html2rss/mcp/outcome/playbook.rb,
lib/html2rss/selectors/extractors.rb,
lib/html2rss/selectors/item_scope.rb,
lib/html2rss/selectors/schema_doc.rb,
lib/html2rss/auto_source/segmenter.rb,
lib/html2rss/config/dynamic_params.rb,
lib/html2rss/feed_resolution/probe.rb,
lib/html2rss/request_session/pager.rb,
lib/html2rss/scoring/link_resolver.rb,
lib/html2rss/syndication/discovery.rb,
lib/html2rss/config/request_headers.rb,
lib/html2rss/feed_builder/json_feed.rb,
lib/html2rss/feed_resolution/policy.rb,
lib/html2rss/feed_resolution/scorer.rb,
lib/html2rss/html/article_extractor.rb,
lib/html2rss/page_recon/diagnostics.rb,
lib/html2rss/request_service/budget.rb,
lib/html2rss/request_service/policy.rb,
lib/html2rss/scoring/cluster_scorer.rb,
lib/html2rss/scoring/ranked_segment.rb,
lib/html2rss/config/request_controls.rb,
lib/html2rss/feed_resolution/options.rb,
lib/html2rss/html/article_rules/date.rb,
lib/html2rss/request_service/context.rb,
lib/html2rss/auto_source/scraper/html.rb,
lib/html2rss/html/article_rules/image.rb,
lib/html2rss/request_service/response.rb,
lib/html2rss/request_service/strategy.rb,
lib/html2rss/selectors/extractors/href.rb,
lib/html2rss/selectors/extractors/html.rb,
lib/html2rss/selectors/extractors/text.rb,
lib/html2rss/selectors/post_processors.rb,
lib/html2rss/auto_source/scraper/schema.rb,
lib/html2rss/auto_source/segmenter/list.rb,
lib/html2rss/config/selectors_validator.rb,
lib/html2rss/html/sst_article_extractor.rb,
lib/html2rss/request_session/pager/base.rb,
lib/html2rss/scoring/container_assessor.rb,
lib/html2rss/auto_source/scraper/sitemap.rb,
lib/html2rss/config/auto_source_contract.rb,
lib/html2rss/feed_builder/json_feed/item.rb,
lib/html2rss/feed_builder/rss/stylesheet.rb,
lib/html2rss/feed_pipeline/auto_fallback.rb,
lib/html2rss/feed_pipeline/strategy_plan.rb,
lib/html2rss/html/article_rules/category.rb,
lib/html2rss/html/rendering/pdf_renderer.rb,
lib/html2rss/selectors/extractors/static.rb,
lib/html2rss/config/multiple_feeds_config.rb,
lib/html2rss/feed_pipeline/runtime_policy.rb,
lib/html2rss/html/article_rules/enclosure.rb,
lib/html2rss/request_session/pager/offset.rb,
lib/html2rss/auto_source/scraper/microdata.rb,
lib/html2rss/auto_source/segmenter/cluster.rb,
lib/html2rss/html/navigator/text_extractor.rb,
lib/html2rss/html/rendering/audio_renderer.rb,
lib/html2rss/html/rendering/image_renderer.rb,
lib/html2rss/html/rendering/media_renderer.rb,
lib/html2rss/html/rendering/video_renderer.rb,
lib/html2rss/link_destination/noise_policy.rb,
lib/html2rss/request_service/network_guard.rb,
lib/html2rss/syndication/candidate_catalog.rb,
lib/html2rss/auto_source/scraper/json_state.rb,
lib/html2rss/auto_source/segmenter/semantic.rb,
lib/html2rss/feed_builder/item_presentation.rb,
lib/html2rss/html/article_rules/description.rb,
lib/html2rss/request_service/httpx_strategy.rb,
lib/html2rss/request_service/response_guard.rb,
lib/html2rss/request_session/pager/rel_next.rb,
lib/html2rss/selectors/extractors/attribute.rb,
lib/html2rss/selectors/post_processors/base.rb,
lib/html2rss/selectors/post_processors/gsub.rb,
lib/html2rss/auto_source/scraper/meta_oembed.rb,
lib/html2rss/auto_source/scraper/native_feed.rb,
lib/html2rss/request_service/blocked_surface.rb,
lib/html2rss/request_service/compressed_body.rb,
lib/html2rss/auto_source/scraper/schema/thing.rb,
lib/html2rss/auto_source/scraper/xhr_articles.rb,
lib/html2rss/link_destination/path_classifier.rb,
lib/html2rss/link_destination/text_classifier.rb,
lib/html2rss/auto_source/scraper/microformats2.rb,
lib/html2rss/auto_source/scraper/semantic_html.rb,
lib/html2rss/auto_source/scraper/wordpress_api.rb,
lib/html2rss/html/rendering/escaped_attributes.rb,
lib/html2rss/request_session/pager/json_cursor.rb,
lib/html2rss/selectors/object_to_xml_converter.rb,
lib/html2rss/auto_source/scraper/sitemap/parser.rb,
lib/html2rss/auto_source/segmenter/primary_link.rb,
lib/html2rss/html/rendering/description_builder.rb,
lib/html2rss/link_destination/destination_facts.rb,
lib/html2rss/request_session/pager/url_template.rb,
lib/html2rss/selectors/post_processors/template.rb,
lib/html2rss/feed_resolution/candidate_generator.rb,
lib/html2rss/html/article_extractor/id_generator.rb,
lib/html2rss/request_service/botasaurus_contract.rb,
lib/html2rss/request_service/botasaurus_strategy.rb,
lib/html2rss/request_service/local_file_strategy.rb,
lib/html2rss/selectors/post_processors/parse_uri.rb,
lib/html2rss/selectors/post_processors/substring.rb,
lib/html2rss/auto_source/scraper/schema/item_list.rb,
lib/html2rss/selectors/post_processors/parse_time.rb,
lib/html2rss/html/article_extractor/date_extractor.rb,
lib/html2rss/request_session/pager/custom_selector.rb,
lib/html2rss/html/article_extractor/image_extractor.rb,
lib/html2rss/selectors/post_processors/sanitize_html.rb,
lib/html2rss/html/article_extractor/heading_extractor.rb,
lib/html2rss/html/article_extractor/category_extractor.rb,
lib/html2rss/html/article_extractor/enclosure_extractor.rb,
lib/html2rss/selectors/post_processors/markdown_to_html.rb,
lib/html2rss/auto_source/scraper/json_state/value_finder.rb,
lib/html2rss/auto_source/scraper/wordpress_api/page_scope.rb,
lib/html2rss/auto_source/scraper/schema/category_extractor.rb,
lib/html2rss/auto_source/scraper/json_state/document_scanner.rb,
lib/html2rss/auto_source/scraper/wordpress_api/posts_endpoint.rb,
lib/html2rss/auto_source/scraper/json_state/article_normalizer.rb,
lib/html2rss/auto_source/scraper/json_state/candidate_detector.rb,
lib/html2rss/auto_source/scraper/semantic_html/entry_deduplicator.rb,
lib/html2rss/selectors/post_processors/html_transformers/wrap_img_in_a.rb,
lib/html2rss/auto_source/scraper/wordpress_api/page_scope/date_archive_range.rb,
lib/html2rss/selectors/post_processors/html_transformers/transform_urls_to_absolute_ones.rb

Overview

rubocop:disable Metrics/ModuleLength -- Channel value object owns extract + freeze + Marshal

Defined Under Namespace

Modules: Batch, Doctor, FeedBuilder, FeedResolution, HashUtil, Html, LinkDestination, Log, MCP, Recon, SST, Scoring, Syndication, Test Classes: Article, AutoSource, CLI, Capture, Channel, Config, Defaults, Error, FeedPipeline, FeedResult, NoFeedItemsExtracted, PageRecon, RequestService, RequestSession, ScrapeTarget, Selectors, Status, SurfaceCategory, Url

Constant Summary collapse

VERSION =

Current application version.

'0.30.0'

Class Method Summary collapse

Class Method Details

.apply(raw_config) ⇒ Html2rss::FeedResult

Ships RSS from a validated config (user-facing verb for feed_result). Golden path step 5.

Parameters:

  • raw_config (Hash{Symbol => Object}) —

    feed configuration

Returns:



111
112
113
 
# File 'lib/html2rss.rb', line 111

def self.apply(raw_config)
  feed_result(raw_config)
end

.auto_feed_result(url, strategy: :auto, items_selector: nil, max_redirects: nil, max_requests: 4, local_file_path: nil, limit: nil) ⇒ Html2rss::FeedResult

Scrapes the provided URL without hand-written selectors and returns FeedResult.

Prefer this when callers need Html2rss::FeedResult#status (MCP envelope payload, CLI --explain).

Parameters:

  • url (String) —

    source page URL

  • strategy (Symbol) (defaults to: :auto) —

    request strategy to use

  • items_selector (String, nil) (defaults to: nil) —

    optional selector hint for item extraction

  • max_redirects (Integer, nil) (defaults to: nil) —

    optional redirect limit override

  • max_requests (Integer) (defaults to: 4) —

    optional request budget override (default: 4 for sitemap sub-fetches)

  • local_file_path (String, nil) (defaults to: nil) —

    optional local HTML file path

  • limit (Integer, nil) (defaults to: nil) —

    max articles to keep (default: Html2rss::AutoSource::DEFAULT_LIMIT)

Returns:



240
241
242
243
244
245
246
247
248
249
 
# File 'lib/html2rss.rb', line 240

def self.auto_feed_result(url,
                          strategy: :auto,
                          items_selector: nil,
                          max_redirects: nil,
                          max_requests: 4,
                          local_file_path: nil,
                          limit: nil)
  feed_result(build_auto_source_config(url:, strategy:, items_selector:, max_redirects:, max_requests:,
                                       local_file_path:, limit:))
end

.auto_json_feed(url, strategy: :auto, items_selector: nil, max_redirects: nil, max_requests: 4, local_file_path: nil, limit: nil) ⇒ Hash

Scrapes the provided URL without hand-written selectors and returns a JSONFeed 1.1 hash.

Same auto_source pipeline as auto_source; see lib/html2rss/auto_source/README.md.

Parameters:

  • url (String) —

    source page URL

  • strategy (Symbol) (defaults to: :auto) —

    request strategy to use

  • items_selector (String, nil) (defaults to: nil) —

    optional selector hint for item extraction

  • max_redirects (Integer, nil) (defaults to: nil) —

    optional redirect limit override

  • max_requests (Integer) (defaults to: 4) —

    optional request budget override (default: 4 for sitemap sub-fetches)

  • local_file_path (String, nil) (defaults to: nil) —

    optional local HTML file path

  • limit (Integer, nil) (defaults to: nil) —

    max articles to keep (default: Html2rss::AutoSource::DEFAULT_LIMIT)

Returns:

  • (Hash) —

    JSONFeed-compliant hash



289
290
291
292
293
294
295
296
297
298
 
# File 'lib/html2rss.rb', line 289

def self.auto_json_feed(url,
                        strategy: :auto,
                        items_selector: nil,
                        max_redirects: nil,
                        max_requests: 4,
                        local_file_path: nil,
                        limit: nil)
  auto_feed_result(url, strategy:, items_selector:, max_redirects:, max_requests:,
                        local_file_path:, limit:).to_json_feed
end

.auto_source(url, strategy: :auto, items_selector: nil, max_redirects: nil, max_requests: 4, local_file_path: nil, limit: nil) ⇒ RSS::Rss

Scrapes the provided URL without hand-written selectors and returns an RSS object.

Builds an auto_source config, then FeedPipeline runs structured scrapers and (when needed) the SST heuristic path — see lib/html2rss/auto_source/README.md.

Parameters:

  • url (String) —

    source page URL

  • strategy (Symbol) (defaults to: :auto) —

    request strategy to use

  • items_selector (String, nil) (defaults to: nil) —

    optional selector hint for item extraction

  • max_redirects (Integer, nil) (defaults to: nil) —

    optional redirect limit override

  • max_requests (Integer) (defaults to: 4) —

    optional request budget override (default: 4 for sitemap sub-fetches)

  • local_file_path (String, nil) (defaults to: nil) —

    optional local HTML file path

  • limit (Integer, nil) (defaults to: nil) —

    max articles to keep (default: Html2rss::AutoSource::DEFAULT_LIMIT)

Returns:

  • (RSS::Rss) —

    generated RSS feed



265
266
267
268
269
270
271
272
273
274
 
# File 'lib/html2rss.rb', line 265

def self.auto_source(url,
                     strategy: :auto,
                     items_selector: nil,
                     max_redirects: nil,
                     max_requests: 4,
                     local_file_path: nil,
                     limit: nil)
  auto_feed_result(url, strategy:, items_selector:, max_redirects:, max_requests:,
                        local_file_path:, limit:).to_rss
end

.batch_inspect(urls, strategy: :auto, concurrency: Batch::DEFAULT_CONCURRENCY) ⇒ Html2rss::Batch::BatchResult

Inspects multiple URLs in parallel with per-URL error isolation.

Parameters:

  • urls (Enumerable<String>) —

    list of URLs to inspect

  • strategy (Symbol) (defaults to: :auto) —

    request strategy (:auto, :default, :botasaurus)

  • concurrency (Integer) (defaults to: Batch::DEFAULT_CONCURRENCY) —

    max worker threads (default: 5)

Returns:



158
159
160
 
# File 'lib/html2rss.rb', line 158

def self.batch_inspect(urls, strategy: :auto, concurrency: Batch::DEFAULT_CONCURRENCY)
  Batch.batch_inspect(urls:, strategy:, concurrency:)
end

.batch_recon(urls, strategy: :auto, concurrency: Batch::DEFAULT_CONCURRENCY) ⇒ Html2rss::Batch::BatchResult

Runs recon across multiple URLs in parallel with per-URL error isolation.

Parameters:

  • urls (Enumerable<String>) —

    list of URLs to recon

  • strategy (Symbol) (defaults to: :auto) —

    request strategy (:auto, :default, :botasaurus)

  • concurrency (Integer) (defaults to: Batch::DEFAULT_CONCURRENCY) —

    max worker threads (default: 5)

  • options (Hash) —

    a customizable set of options

Returns:



170
171
172
 
# File 'lib/html2rss.rb', line 170

def self.batch_recon(urls, strategy: :auto, concurrency: Batch::DEFAULT_CONCURRENCY, **)
  Batch.batch_recon(urls:, strategy:, concurrency:, **)
end

.batch_scrape(urls, strategy: :auto, limit: 10, concurrency: Batch::DEFAULT_CONCURRENCY) ⇒ Html2rss::Batch::BatchResult

Scrapes multiple URLs in parallel using auto-source article discovery.

Parameters:

  • urls (Enumerable<String>) —

    list of URLs to scrape

  • strategy (Symbol) (defaults to: :auto) —

    request strategy (:auto, :default, :botasaurus)

  • limit (Integer) (defaults to: 10) —

    max articles to keep per URL (default: 10)

  • concurrency (Integer) (defaults to: Batch::DEFAULT_CONCURRENCY) —

    max worker threads (default: 5)

Returns:



147
148
149
 
# File 'lib/html2rss.rb', line 147

def self.batch_scrape(urls, strategy: :auto, limit: 10, concurrency: Batch::DEFAULT_CONCURRENCY)
  Batch.batch_scrape(urls:, strategy:, limit:, concurrency:)
end

.capture(url, strategy: :auto) ⇒ Html2rss::Capture::CaptureResult

Derives a reusable YAML-ready feed config from a URL. Golden path step 3.

Parameters:

  • url (String) —

    source page URL

  • strategy (Symbol) (defaults to: :auto) —

    request strategy (+:auto+, :default, :botasaurus)

  • options (Hash) —

    a customizable set of options

Returns:



71
72
73
 
# File 'lib/html2rss.rb', line 71

def self.capture(url, strategy: :auto, **)
  Capture.build(url, strategy:, **)
end

.config_from_yaml_file(file, feed_name = nil) ⇒ Hash{Symbol => Object}

Loads a feed configuration from YAML.

Parameters:

  • file (String) —

    path to the YAML file

  • feed_name (String, nil) (defaults to: nil) —

    optional feed name inside a multi-feed config

Returns:

  • (Hash{Symbol => Object}) —

    loaded configuration hash



191
192
193
 
# File 'lib/html2rss.rb', line 191

def self.config_from_yaml_file(file, feed_name = nil)
  Config.load_yaml(file, feed_name)
end

.configure {|config| ... } ⇒ Html2rss::Defaults

Configures global library defaults.

Yield Parameters:

Returns:



315
316
317
318
319
 
# File 'lib/html2rss.rb', line 315

def configure
  config = defaults.dup
  yield config
  @defaults = config.freeze
end

.defaults ⇒ Html2rss::Defaults

Returns the global defaults instance.

Returns:



306
307
308
 
# File 'lib/html2rss.rb', line 306

def defaults
  @defaults ||= Defaults.new.freeze
end

.feed(raw_config) ⇒ RSS::Rss

Returns an RSS object generated from the provided configuration.

Parameters:

  • raw_config (Hash{Symbol => Object}) —

    feed configuration

Returns:

  • (RSS::Rss) —

    generated RSS feed



211
212
213
 
# File 'lib/html2rss.rb', line 211

def self.feed(raw_config)
  feed_result(raw_config).to_rss
end

.feed_result(raw_config) ⇒ Html2rss::FeedResult

Returns an opaque, Marshal-cacheable result of one scrape.

Prefer this when the same scrape must render as RSS and JSON Feed (e.g. web cache).

Parameters:

  • raw_config (Hash{Symbol => Object}) —

    feed configuration

Returns:



202
203
204
 
# File 'lib/html2rss.rb', line 202

def self.feed_result(raw_config)
  FeedPipeline.new(raw_config).to_result
end

.inspect(url, strategy: :auto, deep: false) ⇒ Html2rss::PageRecon::Diagnostics::Report

Cheap diagnostics for a URL (final URL, status, alternates, surface). Golden path step 1 (optional); use recon for verdict and native_feed.

Parameters:

  • url (String) —

    source page URL

  • strategy (Symbol) (defaults to: :auto) —

    request strategy (:auto, :default, :botasaurus)

  • deep (Boolean) (defaults to: false) —

    when true and strategy is :auto, one Botasaurus hop if configured

Returns:



39
40
41
 
# File 'lib/html2rss.rb', line 39

def self.inspect(url, strategy: :auto, deep: false, **)
  PageRecon::Diagnostics.call(url:, strategy:, deep:, **)
end

.json_feed(raw_config, feed_url: nil) ⇒ Hash

Returns a JSONFeed 1.1 hash generated from the provided configuration.

Parameters:

  • raw_config (Hash{Symbol => Object}) —

    feed configuration

  • feed_url (String, nil) (defaults to: nil) —

    optional self URL for the feed (JSON Feed feed_url)

Returns:

  • (Hash) —

    JSONFeed-compliant hash



221
222
223
 
# File 'lib/html2rss.rb', line 221

def self.json_feed(raw_config, feed_url: nil)
  feed_result(raw_config).to_json_feed(feed_url:)
end

.logger ⇒ Object

Returns the logger.

Returns:

  • (Object) —

    the logger



323
324
325
 
# File 'lib/html2rss.rb', line 323

def logger
  defaults.logger
end

.logger=(logger) ⇒ Object

Parameters:

  • logger (Object) —

    the new logger



329
330
331
 
# File 'lib/html2rss.rb', line 329

def logger=(logger)
  configure { |config| config.logger = logger }
end

.recon(url, strategy: :auto) ⇒ Html2rss::Recon::Result

Curation verdict and native_feed preference for a URL. Golden path step 2 (optional); adds verdict beyond inspect.

Parameters:

  • url (String, Html2rss::Url) —

    source page URL

  • strategy (Symbol) (defaults to: :auto) —

    request strategy (:auto, :default, :botasaurus)

Returns:



50
51
52
 
# File 'lib/html2rss.rb', line 50

def self.recon(url, strategy: :auto, **)
  Recon.call(url, strategy:, **)
end

.schema_json(pretty: true) ⇒ String

Exports the configuration JSON Schema as JSON string.

Parameters:

  • pretty (Boolean) (defaults to: true) —

    whether to pretty-print JSON

Returns:

  • (String) 


181
182
183
 
# File 'lib/html2rss.rb', line 181

def self.schema_json(pretty: true)
  Config.json_schema_json(pretty:)
end

.scrape(url, strategy: :auto, items_selector: nil, max_redirects: nil, max_requests: 4, local_file_path: nil, limit: nil) ⇒ Html2rss::FeedResult

One-shot auto-source scrape from a URL (user-facing verb for auto_feed_result).

Parameters:

  • url (String) —

    source page URL

  • strategy (Symbol) (defaults to: :auto) —

    request strategy to use

  • items_selector (String, nil) (defaults to: nil) —

    optional selector hint for item extraction

  • max_redirects (Integer, nil) (defaults to: nil) —

    optional redirect limit override

  • max_requests (Integer) (defaults to: 4) —

    optional request budget override (default: 4 for sitemap sub-fetches)

  • local_file_path (String, nil) (defaults to: nil) —

    optional local HTML file path

  • limit (Integer, nil) (defaults to: nil) —

    max articles to keep (default: Html2rss::AutoSource::DEFAULT_LIMIT)

Returns:



128
129
130
131
132
133
134
135
136
137
 
# File 'lib/html2rss.rb', line 128

def self.scrape(url,
                strategy: :auto,
                items_selector: nil,
                max_redirects: nil,
                max_requests: 4,
                local_file_path: nil,
                limit: nil)
  auto_feed_result(url, strategy:, items_selector:, max_redirects:, max_requests:,
                        local_file_path:, limit:)
end

.test(config_input, feed_name = nil, min_items: 1, params: {}, strategy: nil, strict_quality: false, compare_enhance: false) ⇒ Html2rss::Test::Result

Validates schema and asserts live item extraction. Golden path step 4.

Parameters:

  • config_input (Hash, String) —

    config hash, YAML string, or file path

  • feed_name (String, nil) (defaults to: nil) —

    optional feed name in multi-feed file

  • min_items (Integer) (defaults to: 1) —

    minimum required items (default: 1)

  • params (Hash) (defaults to: {}) —

    dynamic feed params

  • strategy (Symbol, nil) (defaults to: nil) —

    optional strategy override

  • strict_quality (Boolean) (defaults to: false) —

    when true, fail on ship-quality audit thresholds

  • compare_enhance (Boolean) (defaults to: false) —

    diagnostic enhance off vs on comparison on cached HTML

Returns:



100
101
102
103
 
# File 'lib/html2rss.rb', line 100

def self.test(config_input, feed_name = nil, min_items: 1, params: {}, strategy: nil, strict_quality: false, # rubocop:disable Metrics/ParameterLists
              compare_enhance: false)
  Test.call(config_input, feed_name, min_items:, params:, strategy:, strict_quality:, compare_enhance:)
end

.validate(config_input, feed_name = nil, params: {}) ⇒ Dry::Validation::Result, Html2rss::Config::ValidationResult

Validates a config hash, YAML string, or file path against the schema. Side door: schema-only check without live extraction.

Parameters:

  • config_input (Hash, String)
  • feed_name (String, nil) (defaults to: nil)
  • params (Hash) (defaults to: {})

Returns:



83
84
85
86
 
# File 'lib/html2rss.rb', line 83

def self.validate(config_input, feed_name = nil, params: {})
  _raw, validation = Config.resolve_and_validate(config_input, feed_name:, params:)
  validation
end