html2rss 0.32.3 → 0.33.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/html2rss/article/enclosure.rb +2 -6
- data/lib/html2rss/auto_source/cleanup.rb +1 -3
- data/lib/html2rss/auto_source/scraper/html.rb +2 -8
- data/lib/html2rss/auto_source/scraper/json_document.rb +2 -3
- data/lib/html2rss/auto_source/scraper/json_state/article_normalizer.rb +128 -128
- data/lib/html2rss/auto_source/scraper/json_state/candidate_detector.rb +37 -37
- data/lib/html2rss/auto_source/scraper/json_state/document_scanner.rb +123 -123
- data/lib/html2rss/auto_source/scraper/json_state/value_finder.rb +34 -34
- data/lib/html2rss/auto_source/scraper/json_state.rb +2 -6
- data/lib/html2rss/auto_source/scraper/meta_oembed.rb +32 -2
- data/lib/html2rss/auto_source/scraper/microdata.rb +228 -245
- data/lib/html2rss/auto_source/scraper/microformats2.rb +9 -1
- data/lib/html2rss/auto_source/scraper/native_feed.rb +1 -1
- data/lib/html2rss/auto_source/scraper/schema/category_extractor.rb +7 -2
- data/lib/html2rss/auto_source/scraper/schema/item_list.rb +2 -2
- data/lib/html2rss/auto_source/scraper/schema/thing.rb +98 -21
- data/lib/html2rss/auto_source/scraper/schema.rb +49 -2
- data/lib/html2rss/auto_source/scraper/semantic_html.rb +12 -16
- data/lib/html2rss/auto_source/scraper/sitemap/parser.rb +1 -4
- data/lib/html2rss/auto_source/scraper/sitemap.rb +3 -11
- data/lib/html2rss/auto_source/scraper/wordpress_api/page_scope.rb +2 -2
- data/lib/html2rss/auto_source/scraper/wordpress_api/posts_endpoint.rb +1 -3
- data/lib/html2rss/auto_source/scraper/wordpress_api.rb +4 -4
- data/lib/html2rss/auto_source/scraper/xhr_articles.rb +1 -1
- data/lib/html2rss/auto_source/scraper.rb +0 -11
- data/lib/html2rss/auto_source/segmenter/cluster.rb +5 -11
- data/lib/html2rss/auto_source/segmenter/list.rb +25 -57
- data/lib/html2rss/auto_source/segmenter/semantic.rb +6 -13
- data/lib/html2rss/auto_source.rb +1 -1
- data/lib/html2rss/batch.rb +22 -32
- data/lib/html2rss/capture/README.md +1 -1
- data/lib/html2rss/capture.rb +7 -27
- data/lib/html2rss/cli/render.rb +97 -96
- data/lib/html2rss/cli/validate.rb +2 -4
- data/lib/html2rss/cli.rb +33 -27
- data/lib/html2rss/config/request_controls.rb +10 -2
- data/lib/html2rss/config/schema.rb +8 -10
- data/lib/html2rss/config/selectors_validator.rb +1 -0
- data/lib/html2rss/config/validator.rb +3 -3
- data/lib/html2rss/config.rb +1 -1
- data/lib/html2rss/defaults.rb +5 -16
- data/lib/html2rss/doctor/botasaurus.rb +11 -19
- data/lib/html2rss/error.rb +54 -1
- data/lib/html2rss/feed_builder/rss.rb +1 -1
- data/lib/html2rss/feed_pipeline/README.md +1 -1
- data/lib/html2rss/feed_pipeline/auto_fallback.rb +58 -55
- data/lib/html2rss/feed_resolution/candidate_generator.rb +3 -4
- data/lib/html2rss/feed_resolution/options.rb +3 -7
- data/lib/html2rss/feed_resolution/policy.rb +29 -33
- data/lib/html2rss/feed_resolution/probe.rb +3 -3
- data/lib/html2rss/feed_resolution/scorer.rb +29 -29
- data/lib/html2rss/feed_resolution.rb +5 -9
- data/lib/html2rss/feed_result.rb +4 -3
- data/lib/html2rss/hash_util.rb +91 -90
- data/lib/html2rss/html/article_extractor/category_extractor.rb +6 -9
- data/lib/html2rss/html/article_extractor/date_extractor.rb +1 -1
- data/lib/html2rss/html/article_extractor/enclosure_extractor.rb +1 -3
- data/lib/html2rss/html/article_extractor/id_generator.rb +1 -1
- data/lib/html2rss/html/probe.rb +51 -51
- data/lib/html2rss/link_destination/path_classifier.rb +11 -33
- data/lib/html2rss/mcp/config_argument.rb +9 -2
- data/lib/html2rss/mcp/contract.rb +7 -5
- data/lib/html2rss/mcp/outcome.rb +4 -5
- data/lib/html2rss/mcp/runtime.rb +17 -24
- data/lib/html2rss/mcp/server/tools.rb +9 -9
- data/lib/html2rss/option.rb +48 -0
- data/lib/html2rss/page_recon/diagnostics.rb +7 -9
- data/lib/html2rss/page_recon.rb +0 -4
- data/lib/html2rss/recon.rb +10 -12
- data/lib/html2rss/request_service/blocked_surface.rb +3 -7
- data/lib/html2rss/request_service/botasaurus_strategy.rb +2 -2
- data/lib/html2rss/request_service/budget.rb +3 -24
- data/lib/html2rss/request_service/compressed_body.rb +36 -48
- data/lib/html2rss/request_service/context.rb +1 -3
- data/lib/html2rss/request_service/local_file_strategy.rb +3 -1
- data/lib/html2rss/request_service/network_guard.rb +3 -2
- data/lib/html2rss/request_service/policy.rb +8 -26
- data/lib/html2rss/request_service/response.rb +3 -6
- data/lib/html2rss/request_service/strategy.rb +2 -2
- data/lib/html2rss/request_service.rb +26 -2
- data/lib/html2rss/request_session/pager/base.rb +3 -3
- data/lib/html2rss/request_session/pager/custom_selector.rb +4 -4
- data/lib/html2rss/request_session/pager/offset.rb +1 -7
- data/lib/html2rss/request_session/pager/rel_next.rb +1 -1
- data/lib/html2rss/request_session/pager/url_template.rb +1 -7
- data/lib/html2rss/scoring/engine.rb +4 -32
- data/lib/html2rss/scoring/link_resolver.rb +2 -7
- data/lib/html2rss/selectors/extractors/href.rb +2 -4
- data/lib/html2rss/selectors/json_xml.rb +33 -34
- data/lib/html2rss/selectors/post_processors/gsub.rb +2 -3
- data/lib/html2rss/selectors/post_processors/parse_time.rb +4 -5
- data/lib/html2rss/selectors/schema_export.rb +60 -60
- data/lib/html2rss/selectors.rb +14 -18
- data/lib/html2rss/sst/node.rb +9 -3
- data/lib/html2rss/sst/normalizer.rb +25 -24
- data/lib/html2rss/sst/text.rb +53 -57
- data/lib/html2rss/status.rb +23 -30
- data/lib/html2rss/syndication/alternate_links.rb +39 -0
- data/lib/html2rss/syndication/discovery.rb +117 -187
- data/lib/html2rss/syndication/parser.rb +92 -115
- data/lib/html2rss/test/enhance_audit.rb +13 -15
- data/lib/html2rss/test/policy.rb +9 -11
- data/lib/html2rss/test.rb +29 -48
- data/lib/html2rss/url.rb +53 -53
- data/lib/html2rss/version.rb +1 -1
- data/lib/html2rss.rb +2 -1
- metadata +4 -2
data/lib/html2rss.rb
CHANGED
|
@@ -101,7 +101,7 @@ module Html2rss # rubocop:disable Metrics/ModuleLength
|
|
|
101
101
|
#
|
|
102
102
|
# @param config_input [Hash, String] config hash, YAML string, or file path
|
|
103
103
|
# @param feed_name [String, nil] optional feed name in multi-feed file
|
|
104
|
-
# @param min_items [Integer] minimum required items (default: 1)
|
|
104
|
+
# @param min_items [Integer] minimum required items, >= 0 (default: 1)
|
|
105
105
|
# @param params [Hash] dynamic feed params
|
|
106
106
|
# @param strategy [Symbol, nil] optional strategy override
|
|
107
107
|
# @param strict_quality [Boolean] when true, fail on ship-quality audit thresholds
|
|
@@ -109,6 +109,7 @@ module Html2rss # rubocop:disable Metrics/ModuleLength
|
|
|
109
109
|
# @return [Html2rss::Test::Result]
|
|
110
110
|
def self.test(config_input, feed_name = nil, min_items: 1, params: {}, strategy: nil, strict_quality: false, # rubocop:disable Metrics/ParameterLists
|
|
111
111
|
compare_enhance: false)
|
|
112
|
+
Option.integer(:min_items, min_items, min: 0)
|
|
112
113
|
Test.call(config_input, feed_name, min_items:, params:, strategy:, strict_quality:, compare_enhance:)
|
|
113
114
|
end
|
|
114
115
|
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: html2rss
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.33.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Gil Desmarais
|
|
@@ -391,6 +391,7 @@ files:
|
|
|
391
391
|
- lib/html2rss/mcp/runtime.rb
|
|
392
392
|
- lib/html2rss/mcp/server.rb
|
|
393
393
|
- lib/html2rss/mcp/server/tools.rb
|
|
394
|
+
- lib/html2rss/option.rb
|
|
394
395
|
- lib/html2rss/page_recon.rb
|
|
395
396
|
- lib/html2rss/page_recon/README.md
|
|
396
397
|
- lib/html2rss/page_recon/diagnostics.rb
|
|
@@ -463,6 +464,7 @@ files:
|
|
|
463
464
|
- lib/html2rss/surface_category.rb
|
|
464
465
|
- lib/html2rss/syndication.rb
|
|
465
466
|
- lib/html2rss/syndication/README.md
|
|
467
|
+
- lib/html2rss/syndication/alternate_links.rb
|
|
466
468
|
- lib/html2rss/syndication/candidate_catalog.rb
|
|
467
469
|
- lib/html2rss/syndication/discovery.rb
|
|
468
470
|
- lib/html2rss/syndication/parser.rb
|
|
@@ -478,7 +480,7 @@ licenses:
|
|
|
478
480
|
- MIT
|
|
479
481
|
metadata:
|
|
480
482
|
allowed_push_host: https://rubygems.org
|
|
481
|
-
changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.
|
|
483
|
+
changelog_uri: https://github.com/html2rss/html2rss/releases/tag/v0.33.0
|
|
482
484
|
rubygems_mfa_required: 'true'
|
|
483
485
|
rdoc_options: []
|
|
484
486
|
require_paths:
|