html2rss 0.17.0 → 0.19.0
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/README.md +90 -639
- data/exe/html2rss +1 -1
- data/html2rss.gemspec +5 -2
- data/lib/html2rss/articles/deduplicator.rb +50 -0
- data/lib/html2rss/auto_source/cleanup.rb +44 -5
- data/lib/html2rss/auto_source/scraper/html.rb +123 -43
- data/lib/html2rss/auto_source/scraper/json_state.rb +457 -0
- data/lib/html2rss/auto_source/scraper/microdata.rb +505 -0
- data/lib/html2rss/auto_source/scraper/schema/category_extractor.rb +102 -0
- data/lib/html2rss/auto_source/scraper/schema/item_list.rb +3 -2
- data/lib/html2rss/auto_source/scraper/schema/list_item.rb +6 -4
- data/lib/html2rss/auto_source/scraper/schema/thing.rb +69 -8
- data/lib/html2rss/auto_source/scraper/schema.rb +27 -12
- data/lib/html2rss/auto_source/scraper/semantic_html/anchor_selector.rb +204 -0
- data/lib/html2rss/auto_source/scraper/semantic_html.rb +88 -79
- data/lib/html2rss/auto_source/scraper/wordpress_api/page_scope.rb +311 -0
- data/lib/html2rss/auto_source/scraper/wordpress_api/posts_endpoint.rb +135 -0
- data/lib/html2rss/auto_source/scraper/wordpress_api.rb +186 -0
- data/lib/html2rss/auto_source/scraper.rb +160 -8
- data/lib/html2rss/auto_source.rb +123 -47
- data/lib/html2rss/blocked_surface.rb +65 -0
- data/lib/html2rss/category_extractor.rb +82 -0
- data/lib/html2rss/cli.rb +194 -23
- data/lib/html2rss/config/class_methods.rb +178 -0
- data/lib/html2rss/config/dynamic_params.rb +70 -0
- data/lib/html2rss/config/multiple_feeds_config.rb +51 -0
- data/lib/html2rss/config/request_headers.rb +136 -0
- data/lib/html2rss/config/schema.rb +240 -0
- data/lib/html2rss/config/validator.rb +146 -0
- data/lib/html2rss/config.rb +118 -61
- data/lib/html2rss/error.rb +31 -0
- data/lib/html2rss/feed_pipeline/auto_fallback.rb +127 -0
- data/lib/html2rss/feed_pipeline.rb +127 -0
- data/lib/html2rss/hash_util.rb +101 -0
- data/lib/html2rss/html_extractor/date_extractor.rb +20 -0
- data/lib/html2rss/html_extractor/enclosure_extractor.rb +120 -0
- data/lib/html2rss/html_extractor/image_extractor.rb +58 -0
- data/lib/html2rss/html_extractor.rb +141 -0
- data/lib/html2rss/html_navigator.rb +54 -0
- data/lib/html2rss/json_feed_builder/item.rb +94 -0
- data/lib/html2rss/json_feed_builder.rb +59 -0
- data/lib/html2rss/rendering/audio_renderer.rb +36 -0
- data/lib/html2rss/rendering/description_builder.rb +87 -0
- data/lib/html2rss/rendering/image_renderer.rb +41 -0
- data/lib/html2rss/rendering/media_renderer.rb +37 -0
- data/lib/html2rss/rendering/pdf_renderer.rb +34 -0
- data/lib/html2rss/rendering/video_renderer.rb +36 -0
- data/lib/html2rss/rendering.rb +23 -0
- data/lib/html2rss/request_controls.rb +123 -0
- data/lib/html2rss/request_service/botasaurus_contract.rb +161 -0
- data/lib/html2rss/request_service/botasaurus_strategy.rb +98 -0
- data/lib/html2rss/request_service/browserless_strategy.rb +103 -7
- data/lib/html2rss/request_service/budget.rb +39 -0
- data/lib/html2rss/request_service/context.rb +77 -21
- data/lib/html2rss/request_service/faraday_strategy.rb +137 -5
- data/lib/html2rss/request_service/policy.rb +252 -0
- data/lib/html2rss/request_service/puppet_commander.rb +212 -13
- data/lib/html2rss/request_service/response.rb +51 -3
- data/lib/html2rss/request_service/response_guard.rb +62 -0
- data/lib/html2rss/request_service.rb +50 -15
- data/lib/html2rss/request_session/rel_next_pager.rb +70 -0
- data/lib/html2rss/request_session/runtime_input.rb +71 -0
- data/lib/html2rss/request_session/runtime_policy.rb +83 -0
- data/lib/html2rss/request_session.rb +122 -0
- data/lib/html2rss/rss_builder/article.rb +187 -0
- data/lib/html2rss/rss_builder/channel.rb +105 -11
- data/lib/html2rss/rss_builder/enclosure.rb +62 -0
- data/lib/html2rss/rss_builder/stylesheet.rb +8 -4
- data/lib/html2rss/rss_builder.rb +76 -71
- data/lib/html2rss/selectors/config.rb +123 -0
- data/lib/html2rss/selectors/extractors/attribute.rb +52 -0
- data/lib/html2rss/selectors/extractors/href.rb +55 -0
- data/lib/html2rss/selectors/extractors/html.rb +49 -0
- data/lib/html2rss/selectors/extractors/static.rb +42 -0
- data/lib/html2rss/selectors/extractors/text.rb +47 -0
- data/lib/html2rss/selectors/extractors.rb +53 -0
- data/lib/html2rss/selectors/object_to_xml_converter.rb +62 -0
- data/lib/html2rss/selectors/post_processors/base.rb +80 -0
- data/lib/html2rss/selectors/post_processors/gsub.rb +88 -0
- data/lib/html2rss/selectors/post_processors/html_to_markdown.rb +48 -0
- data/lib/html2rss/selectors/post_processors/html_transformers/transform_urls_to_absolute_ones.rb +44 -0
- data/lib/html2rss/selectors/post_processors/html_transformers/wrap_img_in_a.rb +53 -0
- data/lib/html2rss/selectors/post_processors/markdown_to_html.rb +55 -0
- data/lib/html2rss/selectors/post_processors/parse_time.rb +78 -0
- data/lib/html2rss/selectors/post_processors/parse_uri.rb +43 -0
- data/lib/html2rss/selectors/post_processors/sanitize_html.rb +154 -0
- data/lib/html2rss/selectors/post_processors/substring.rb +77 -0
- data/lib/html2rss/selectors/post_processors/template.rb +76 -0
- data/lib/html2rss/selectors/post_processors.rb +48 -0
- data/lib/html2rss/selectors.rb +301 -0
- data/lib/html2rss/url.rb +266 -0
- data/lib/html2rss/version.rb +2 -1
- data/lib/html2rss.rb +67 -71
- data/lib/tasks/config_schema.rake +17 -0
- data/schema/html2rss-config.schema.json +551 -0
- metadata +120 -38
- data/lib/html2rss/attribute_post_processors/base.rb +0 -74
- data/lib/html2rss/attribute_post_processors/gsub.rb +0 -64
- data/lib/html2rss/attribute_post_processors/html_to_markdown.rb +0 -43
- data/lib/html2rss/attribute_post_processors/html_transformers/transform_urls_to_absolute_ones.rb +0 -27
- data/lib/html2rss/attribute_post_processors/html_transformers/wrap_img_in_a.rb +0 -41
- data/lib/html2rss/attribute_post_processors/markdown_to_html.rb +0 -50
- data/lib/html2rss/attribute_post_processors/parse_time.rb +0 -46
- data/lib/html2rss/attribute_post_processors/parse_uri.rb +0 -46
- data/lib/html2rss/attribute_post_processors/sanitize_html.rb +0 -115
- data/lib/html2rss/attribute_post_processors/substring.rb +0 -72
- data/lib/html2rss/attribute_post_processors/template.rb +0 -101
- data/lib/html2rss/attribute_post_processors.rb +0 -44
- data/lib/html2rss/auto_source/article.rb +0 -127
- data/lib/html2rss/auto_source/channel.rb +0 -78
- data/lib/html2rss/auto_source/reducer.rb +0 -48
- data/lib/html2rss/auto_source/rss_builder.rb +0 -70
- data/lib/html2rss/auto_source/scraper/semantic_html/extractor.rb +0 -136
- data/lib/html2rss/auto_source/scraper/semantic_html/image.rb +0 -54
- data/lib/html2rss/config/channel.rb +0 -125
- data/lib/html2rss/config/selectors.rb +0 -103
- data/lib/html2rss/item.rb +0 -186
- data/lib/html2rss/item_extractors/attribute.rb +0 -50
- data/lib/html2rss/item_extractors/href.rb +0 -52
- data/lib/html2rss/item_extractors/html.rb +0 -46
- data/lib/html2rss/item_extractors/static.rb +0 -39
- data/lib/html2rss/item_extractors/text.rb +0 -44
- data/lib/html2rss/item_extractors.rb +0 -88
- data/lib/html2rss/object_to_xml_converter.rb +0 -56
- data/lib/html2rss/rss_builder/item.rb +0 -83
- data/lib/html2rss/utils.rb +0 -113
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 695f871fe38ceaa657e684c6016d39d74afee79f32608eb28faded39ae25597b
|
|
4
|
+
data.tar.gz: 8c9f4060d63d56688cb324d821a35a0b80aca1a2ec7c53faae9f980b29212182
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 3d72d0f4b1f581c694f5ec4580425a5ee14da73f3cd7a793da5518fa46784ed0eae98f1e98bf3a840d2405f9b7fb94843c28ffe2cd6cba9279ac0e1e083e40cf
|
|
7
|
+
data.tar.gz: 71ca6aad736d10dd3486fd00b136851a8bcabbb840b9e206c56c80c5edbe1840f4556702e68344ef45726939632f780c3b74f31f579fb068a50b497c29f044fc
|