Method List
-
#<=> Html2rss::Url
-
#<=> Html2rss::Article
-
#== Html2rss::Url
-
#absolute? Html2rss::Url
-
accepted_names Html2rss::FeedPipeline::StrategyPlan
-
add Html2rss::FeedBuilder::Rss::Stylesheet
-
add_enclosure Html2rss::FeedBuilder::Rss
-
add_item Html2rss::FeedBuilder::Rss
-
add_split_text! Html2rss::Html::ArticleRules::Category
-
add_text! Html2rss::Html::ArticleRules::Category
-
#allow_cross_origin_followups? Html2rss::RequestService::Policy
-
#allow_private_networks? Html2rss::RequestService::Policy
-
#already_wrapped? Html2rss::Selectors::PostProcessors::HtmlTransformers::WrapImgInA
-
#apply_to Html2rss::Config::RequestControls
-
archive_href? Html2rss::Html::ArticleRules::Enclosure
-
array_of_articles? Html2rss::AutoSource::Scraper::JsonState::CandidateDetector
-
#article_container Html2rss::Scoring::Observation
-
#article_for Html2rss::AutoSource::Scraper::SemanticHtml::EntryDeduplicator
-
#articles Html2rss::Selectors
-
#articles Html2rss::AutoSource
-
#articles Html2rss::FeedPipeline::PipelineOutcome
-
articles? Html2rss::AutoSource::Scraper::Html
-
articles? Html2rss::AutoSource::Scraper::Schema
-
articles? Html2rss::AutoSource::Scraper::Sitemap
-
articles? Html2rss::AutoSource::Scraper::Microdata
-
articles? Html2rss::AutoSource::Scraper::JsonState
-
articles? Html2rss::AutoSource::Scraper::MetaOembed
-
articles? Html2rss::AutoSource::Scraper::Microformats2
-
articles? Html2rss::AutoSource::Scraper::SemanticHtml
-
articles? Html2rss::AutoSource::Scraper::WordpressApi
-
assert! Html2rss::Scoring::FeatureId
-
assert_string_keys! Html2rss::HashUtil
-
assert_symbol_keys! Html2rss::HashUtil
-
assert_type Html2rss::Selectors::PostProcessors::Base
-
assignment_documents Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
assignment_payload Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
#attempt_count Html2rss::Status
-
#attempt_count Html2rss::FeedPipeline::PipelineOutcome
-
#attempts Html2rss::NoFeedItemsExtracted
-
#attempts Html2rss::FeedPipeline::AutoFallback::AttemptState
-
attr_name_match? Html2rss::Html::ArticleRules::Category
-
#attribute Html2rss::Selectors::Extractors::Attribute::Options
-
#attrs Html2rss::SST::Node
-
#author Html2rss::Article
-
#author Html2rss::Channel
-
#author Html2rss::AutoSource::Scraper::Schema::Thing
-
#auto Html2rss::CLI
-
auto_json_feed Html2rss
-
auto_source Html2rss
-
#auto_source Html2rss::Config
-
auto_source_config Html2rss::Config
-
#avg_words Html2rss::Scoring::ClusterScorer
-
#base_url Html2rss::Selectors::ItemScope
-
#base_url Html2rss::AutoSource::Segmenter
-
#base_url Html2rss::AutoSource::Scraper::Schema::Thing
-
#begin_navigation! Html2rss::RequestService::PuppetCommander::NavigationGuards
-
best_from_styles Html2rss::Html::ArticleRules::Image
-
#body Html2rss::RequestService::Response
-
#breakdown Html2rss::Scoring::Score
-
browser_defaults Html2rss::Config::RequestHeaders
-
#browser_ws_endpoint Html2rss::RequestService::BrowserlessStrategy
-
#browserless Html2rss::RequestService::Context
-
#browserless_preload Html2rss::RequestService::Context
-
#budget Html2rss::RequestService::Context
-
#budget Html2rss::FeedPipeline::RuntimePolicy::Resources
-
budget_for Html2rss::FeedPipeline::RuntimePolicy
-
build Html2rss::Status
-
build Html2rss::SST::Node
-
build Html2rss::SST::Attrs
-
build Html2rss::SST::Document
-
build Html2rss::Scoring::Score
-
build Html2rss::RequestSession
-
build Html2rss::AutoSource::Segment
-
build Html2rss::Scoring::RankedSegment
-
build Html2rss::LinkDestination::DestinationFacts
-
build_instance Html2rss::AutoSource::Scraper
-
#bytes_length Html2rss::Article::Enclosure
-
#call Html2rss::Config::Preparer
-
call Html2rss::Config::Schema::Builder
-
#call Html2rss::Config::Schema::Builder
-
call Html2rss::Config::Schema::DeepStringifier
-
call Html2rss::SST::Normalizer
-
#call Html2rss::SST::Normalizer
-
#call Html2rss::FeedBuilder::Rss
-
call Html2rss::AutoSource::Cleanup
-
#call Html2rss::Article::Deduplicator
-
call Html2rss::AutoSource::Segmenter
-
#call Html2rss::AutoSource::Segmenter
-
call Html2rss::Config::DynamicParams
-
#call Html2rss::FeedBuilder::JsonFeed
-
call Html2rss::Html::ArticleExtractor
-
#call Html2rss::Html::ArticleExtractor
-
call Html2rss::AutoSource::Segmenter::List
-
call Html2rss::Config::SelectorsValidator
-
call Html2rss::Html::SstArticleExtractor
-
#call Html2rss::Html::SstArticleExtractor
-
#call Html2rss::Scoring::ContainerAssessor
-
#call Html2rss::FeedPipeline::AutoFallback
-
call Html2rss::AutoSource::Segmenter::Cluster
-
call Html2rss::Html::Navigator::TextExtractor
-
call Html2rss::AutoSource::Segmenter::Semantic
-
#call Html2rss::AutoSource::Scraper::Schema::Thing
-
#call Html2rss::RequestService::PuppetCommander
-
#call Html2rss::Selectors::ObjectToXmlConverter
-
call Html2rss::AutoSource::Scraper::Sitemap::Parser
-
#call Html2rss::AutoSource::Scraper::Sitemap::Parser
-
#call Html2rss::Html::Rendering::DescriptionBuilder
-
call Html2rss::Html::ArticleExtractor::IdGenerator
-
#call Html2rss::AutoSource::Scraper::Schema::ItemList
-
call Html2rss::Html::ArticleExtractor::DateExtractor
-
call Html2rss::Html::ArticleExtractor::ImageExtractor
-
call Html2rss::Html::ArticleExtractor::HeadingExtractor
-
call Html2rss::Html::ArticleExtractor::CategoryExtractor
-
call Html2rss::Html::ArticleExtractor::EnclosureExtractor
-
#call Html2rss::AutoSource::Scraper::WordpressApi::PageScope::Resolver
-
call Html2rss::AutoSource::Scraper::Schema::CategoryExtractor
-
#call Html2rss::RequestService::PuppetCommander::PreloadRunner
-
#call Html2rss::AutoSource::Scraper::WordpressApi::PostsEndpoint
-
#call Html2rss::AutoSource::Scraper::SemanticHtml::EntryDeduplicator
-
#call Html2rss::Selectors::PostProcessors::HtmlTransformers::WrapImgInA
-
#call Html2rss::Selectors::PostProcessors::HtmlTransformers::TransformUrlsToAbsoluteOnes
-
candidate_array? Html2rss::AutoSource::Scraper::JsonState::CandidateDetector
-
#categories Html2rss::Article
-
#categories Html2rss::AutoSource::Scraper::Schema::Thing
-
categories Html2rss::AutoSource::Scraper::JsonState::ArticleNormalizer
-
#category Html2rss::AutoSource::Scraper::NoScraperFound
-
#challenge_block? Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
#challenge_message Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
#changefreq Html2rss::AutoSource::Scraper::Sitemap::Parser::SitemapEntry
-
#channel Html2rss::Config
-
#channel Html2rss::Selectors::ItemScope
-
#channel Html2rss::Selectors::Extractors::Href::Options
-
#channel_title Html2rss::FeedResult
-
#channel_titleized Html2rss::Url
-
#children Html2rss::SST::Node
-
#class_attr Html2rss::SST::Attrs
-
class_match? Html2rss::Html::ArticleRules::Category
-
#class_names Html2rss::SST::Attrs
-
coerce_javascript_object Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
#composite Html2rss::Scoring::Score
-
#config Html2rss::Selectors::Context
-
config_from_yaml_file Html2rss
-
configure Html2rss
-
#connect_timeout_seconds Html2rss::RequestService::Policy
-
#consume! Html2rss::RequestService::Budget
-
#consume_interaction! Html2rss::RequestService::Budget
-
#consume_request! Html2rss::RequestService::Budget
-
#content_path Html2rss::Scoring::Observation
-
#content_path Html2rss::LinkDestination::DestinationFacts
-
#content_path? Html2rss::LinkDestination::PathClassifier
-
#content_tokens Html2rss::Scoring::Observation
-
#content_type Html2rss::RequestService::Response
-
#context Html2rss::Selectors::PostProcessors::Base
-
#context_for Html2rss::Selectors::ItemScope
-
create_renderer_for_type Html2rss::Html::Rendering::MediaRenderer
-
#datetime Html2rss::SST::Attrs
-
#dedup_dropped Html2rss::Status
-
#dedup_dropped Html2rss::FeedPipeline::PipelineOutcome
-
deduplicate_by! Html2rss::AutoSource::Cleanup
-
#deduplicated_articles Html2rss::FeedPipeline
-
#deduplication_fingerprint Html2rss::Article
-
deep_dup Html2rss::HashUtil
-
deep_merge Html2rss::HashUtil
-
deep_symbolize_keys Html2rss::HashUtil
-
#deep_utility_context_route? Html2rss::LinkDestination::PathClassifier
-
default Html2rss::RequestService::Policy
-
default_config Html2rss::Config
-
#default_strategy Html2rss::Defaults
-
default_strategy_name Html2rss::Config
-
#default_strategy_name Html2rss::RequestService
-
defaults Html2rss
-
#degraded Html2rss::SST::Document
-
#depth_of Html2rss::SST::Index
-
#descendant_of? Html2rss::SST::Index
-
descendant_of? Html2rss::Html::Navigator
-
#descendants Html2rss::SST::Node
-
#description Html2rss::Article
-
#description Html2rss::Channel
-
#description Html2rss::AutoSource::Scraper::Schema::Thing
-
description_for Html2rss::FeedBuilder::ItemPresentation
-
#descriptive_context Html2rss::Scoring::Observation
-
#destination Html2rss::LinkDestination::DestinationFacts
-
#destination_facts Html2rss::Scoring::LinkResolver
-
#document Html2rss::AutoSource::Segmenter
-
#each Html2rss::Article
-
#each Html2rss::Selectors
-
#each Html2rss::AutoSource::Scraper::Html
-
#each Html2rss::AutoSource::Scraper::Schema
-
#each Html2rss::RequestSession::Pager::Base
-
#each Html2rss::AutoSource::Scraper::Sitemap
-
#each Html2rss::AutoSource::Scraper::Microdata
-
#each Html2rss::AutoSource::Scraper::JsonState
-
#each Html2rss::AutoSource::Scraper::MetaOembed
-
#each Html2rss::AutoSource::Scraper::Microformats2
-
#each Html2rss::AutoSource::Scraper::SemanticHtml
-
#each Html2rss::AutoSource::Scraper::WordpressApi
-
#each_node Html2rss::SST::Node
-
#each_node Html2rss::SST::Index
-
earliest Html2rss::Html::ArticleRules::Date
-
#effective_page_budget Html2rss::RequestSession
-
#effective_timeout_ms Html2rss::RequestService::Budget
-
#effective_timeout_seconds Html2rss::RequestService::Budget
-
#elapsed_seconds Html2rss::RequestService::Budget
-
element Html2rss::Selectors::Extractors
-
#eligible_href? Html2rss::SST::Node
-
empty Html2rss::SST::Attrs
-
#empty? Html2rss::FeedResult
-
#enclosures Html2rss::Article
-
#enforce_public_network! Html2rss::RequestService::NetworkGuard
-
#enhance? Html2rss::Selectors
-
#enhance_article_hash Html2rss::Selectors
-
#entries Html2rss::AutoSource::Scraper::Sitemap::Parser::Result
-
#eql? Html2rss::Url
-
#execute Html2rss::RequestService
-
#execute Html2rss::RequestService::Strategy
-
exit_on_failure? Html2rss::CLI
-
expect_options Html2rss::Selectors::PostProcessors::Base
-
#explicit? Html2rss::Config::RequestControls
-
#explicit_max_requests? Html2rss::Config
-
extract Html2rss::SST::Text
-
extract_all_categories Html2rss::Html::ArticleExtractor::CategoryExtractor
-
#extract_article Html2rss::Selectors
-
extract_assignment_payload Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
extract_element_data_categories! Html2rss::Html::ArticleExtractor::CategoryExtractor
-
extract_from_html Html2rss::Url
-
extract_json_block Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
extract_text_categories! Html2rss::Html::ArticleExtractor::CategoryExtractor
-
extract_visible_text Html2rss::Html::Navigator
-
#extractable? Html2rss::AutoSource::Scraper::Html
-
#extractable? Html2rss::AutoSource::Scraper::JsonState
-
#extractable? Html2rss::AutoSource::Scraper::SemanticHtml
-
extractable_instance? Html2rss::AutoSource::Scraper
-
feed Html2rss
-
#feed Html2rss::CLI
-
feed_result Html2rss
-
fetch Html2rss::AutoSource::Scraper::JsonState::ValueFinder
-
fetch_from_array Html2rss::AutoSource::Scraper::JsonState::ValueFinder
-
fetch_from_hash Html2rss::AutoSource::Scraper::JsonState::ValueFinder
-
#fetch_initial_response Html2rss::RequestSession
-
fetch_nested Html2rss::AutoSource::Scraper::JsonState::ValueFinder
-
#fetchable? Html2rss::AutoSource::Scraper::WordpressApi::PageScope
-
#filter_1_to_1_overlap Html2rss::AutoSource::Segmenter::Cluster::OverlapResolver
-
#filter_containers Html2rss::AutoSource::Segmenter::Cluster::OverlapResolver
-
#final_score Html2rss::Scoring::RankedSegment
-
#final_url Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
#find Html2rss::SST::Node
-
#find_all Html2rss::SST::Node
-
find_closest_selector_upwards Html2rss::Html::Navigator
-
find_tag_in_ancestors Html2rss::Html::Navigator
-
#follow_up Html2rss::RequestSession
-
#follow_up Html2rss::RequestService::Context
-
for Html2rss::RequestSession::Pager
-
for Html2rss::Html::Rendering::MediaRenderer
-
for_channel Html2rss::Url
-
for_node Html2rss::SST::Index
-
#fragment Html2rss::Url
-
from Html2rss::AutoSource::Scraper
-
from Html2rss::AutoSource::Scraper::Schema
-
from Html2rss::AutoSource::Scraper::WordpressApi::PageScope
-
from_absolute Html2rss::Url
-
from_anchor Html2rss::Html::ArticleRules::Enclosure
-
from_cli_options Html2rss::Config::RequestControls
-
from_config Html2rss::Config::RequestControls
-
from_config Html2rss::FeedPipeline::RuntimePolicy
-
from_hash Html2rss::Config
-
from_iframe Html2rss::Html::ArticleRules::Enclosure
-
from_image Html2rss::Html::ArticleRules::Enclosure
-
from_img Html2rss::Html::ArticleExtractor::ImageExtractor
-
from_media Html2rss::Html::ArticleRules::Enclosure
-
from_relative Html2rss::Url
-
from_response Html2rss::Channel
-
from_segments Html2rss::AutoSource::Scraper::WordpressApi::PageScope::DateArchiveRange
-
from_shortcut Html2rss::Config::RequestControls
-
from_source Html2rss::Html::ArticleExtractor::ImageExtractor
-
from_style Html2rss::Html::ArticleExtractor::ImageExtractor
-
get Html2rss::Selectors::Extractors
-
#get Html2rss::Selectors::Extractors::Href
-
#get Html2rss::Selectors::Extractors::Html
-
#get Html2rss::Selectors::Extractors::Text
-
get Html2rss::Selectors::PostProcessors
-
#get Html2rss::Selectors::Extractors::Static
-
#get Html2rss::Selectors::Extractors::Attribute
-
#get Html2rss::Selectors::PostProcessors::Base
-
#get Html2rss::Selectors::PostProcessors::Gsub
-
#get Html2rss::Selectors::PostProcessors::Template
-
#get Html2rss::Selectors::PostProcessors::ParseUri
-
#get Html2rss::Selectors::PostProcessors::Substring
-
#get Html2rss::Selectors::PostProcessors::ParseTime
-
get Html2rss::Selectors::PostProcessors::SanitizeHtml
-
#get Html2rss::Selectors::PostProcessors::SanitizeHtml
-
#get Html2rss::Selectors::PostProcessors::HtmlToMarkdown
-
#get Html2rss::Selectors::PostProcessors::MarkdownToHtml
-
guess_content_type_from_url Html2rss::Article::Enclosure
-
#guid Html2rss::Article
-
#hard_junk? Html2rss::Scoring::Observation
-
#hash Html2rss::Url
-
#headers Html2rss::Config
-
#headers Html2rss::Defaults
-
#headers Html2rss::RequestService::Context
-
#headers Html2rss::RequestService::Response
-
#headers Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
#heading? Html2rss::SST::Node
-
heuristic_tier? Html2rss::AutoSource::Scraper
-
#high_confidence_junk_path Html2rss::Scoring::Observation
-
#high_confidence_junk_path Html2rss::LinkDestination::DestinationFacts
-
#high_confidence_utility_destination Html2rss::Scoring::Observation
-
#high_confidence_utility_destination Html2rss::LinkDestination::DestinationFacts
-
#host Html2rss::Url
-
#href Html2rss::SST::Attrs
-
#href Html2rss::FeedBuilder::Rss::Stylesheet
-
#html Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
#html_response? Html2rss::RequestService::Response
-
#id Html2rss::Article
-
#id Html2rss::SST::Attrs
-
#id Html2rss::AutoSource::Scraper::Schema::Thing
-
identifier Html2rss::AutoSource::Scraper::JsonState::ArticleNormalizer
-
#ignored_chrome? Html2rss::SST::Index
-
#ignored_container_name? Html2rss::SST::Node
-
ignored_container_path? Html2rss::Html::Navigator
-
#image Html2rss::Article
-
#image Html2rss::Channel
-
#image Html2rss::AutoSource::Scraper::Schema::Thing
-
#image? Html2rss::SST::Node
-
#image_urls Html2rss::AutoSource::Scraper::Schema::Thing
-
#index Html2rss::SST::Document
-
#index Html2rss::AutoSource::Segmenter
-
#initialize Html2rss::Url
-
#initialize Html2rss::NoFeedItemsExtracted
-
#initialize Html2rss::Config
-
#initialize Html2rss::Status
-
#initialize Html2rss::Article
-
#initialize Html2rss::Channel
-
#initialize Html2rss::Defaults
-
#initialize Html2rss::Selectors
-
#initialize Html2rss::SST::Index
-
#initialize Html2rss::AutoSource
-
#initialize Html2rss::FeedResult
-
#initialize Html2rss::FeedPipeline
-
#initialize Html2rss::Scoring::Engine
-
#initialize Html2rss::SST::Normalizer
-
#initialize Html2rss::RequestService
-
#initialize Html2rss::RequestSession
-
#initialize Html2rss::FeedBuilder::Rss
-
#initialize Html2rss::Article::Enclosure
-
#initialize Html2rss::AutoSource::Scraper::NoScraperFound
-
#initialize Html2rss::Article::Deduplicator
-
#initialize Html2rss::AutoSource::Segmenter
-
#initialize Html2rss::Scoring::LinkResolver
-
#initialize Html2rss::Config::RequestHeaders
-
#initialize Html2rss::FeedBuilder::JsonFeed
-
#initialize Html2rss::Html::ArticleExtractor
-
#initialize Html2rss::RequestService::Budget
-
#initialize Html2rss::RequestService::Policy
-
#initialize Html2rss::Scoring::ClusterScorer
-
#initialize Html2rss::Config::RequestControls
-
#initialize Html2rss::RequestService::Context
-
#initialize Html2rss::AutoSource::Scraper::Html
-
#initialize Html2rss::RequestService::Response
-
#initialize Html2rss::RequestService::Strategy
-
#initialize Html2rss::Selectors::Extractors::Href
-
#initialize Html2rss::Selectors::Extractors::Html
-
#initialize Html2rss::Selectors::Extractors::Text
-
#initialize Html2rss::AutoSource::Scraper::Schema
-
#initialize Html2rss::Html::SstArticleExtractor
-
#initialize Html2rss::RequestSession::Pager::Base
-
#initialize Html2rss::Scoring::ContainerAssessor
-
#initialize Html2rss::AutoSource::Scraper::Sitemap
-
#initialize Html2rss::FeedBuilder::JsonFeed::Item
-
#initialize Html2rss::FeedBuilder::Rss::Stylesheet
-
#initialize Html2rss::FeedPipeline::AutoFallback::AttemptState
-
#initialize Html2rss::FeedPipeline::AutoFallback
-
#initialize Html2rss::Html::Rendering::PdfRenderer
-
#initialize Html2rss::Selectors::Extractors::Static
-
#initialize Html2rss::AutoSource::Scraper::Microdata
-
#initialize Html2rss::AutoSource::Segmenter::Cluster::OverlapResolver
-
#initialize Html2rss::Html::Rendering::AudioRenderer
-
#initialize Html2rss::Html::Rendering::ImageRenderer
-
#initialize Html2rss::Html::Rendering::VideoRenderer
-
#initialize Html2rss::LinkDestination::NoisePolicy
-
#initialize Html2rss::RequestService::NetworkGuard
-
#initialize Html2rss::AutoSource::Scraper::JsonState
-
#initialize Html2rss::RequestService::ResponseGuard
-
#initialize Html2rss::Selectors::Extractors::Attribute
-
#initialize Html2rss::Selectors::PostProcessors::Base
-
#initialize Html2rss::Selectors::PostProcessors::Gsub
-
#initialize Html2rss::AutoSource::Scraper::MetaOembed
-
#initialize Html2rss::AutoSource::Scraper::Schema::Thing
-
#initialize Html2rss::LinkDestination::PathClassifier
-
#initialize Html2rss::RequestService::PuppetCommander
-
#initialize Html2rss::AutoSource::Scraper::Microformats2
-
#initialize Html2rss::AutoSource::Scraper::SemanticHtml
-
#initialize Html2rss::AutoSource::Scraper::WordpressApi
-
#initialize Html2rss::Selectors::ObjectToXmlConverter
-
#initialize Html2rss::AutoSource::Scraper::Sitemap::Parser
-
#initialize Html2rss::AutoSource::Segmenter::PrimaryLink
-
#initialize Html2rss::Html::Rendering::DescriptionBuilder
-
#initialize Html2rss::Selectors::PostProcessors::Template
-
#initialize Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
#initialize Html2rss::RequestService::BotasaurusContract
-
#initialize Html2rss::AutoSource::Scraper::WordpressApi::PageScope
-
#initialize Html2rss::AutoSource::Scraper::WordpressApi::PageScope::Resolver
-
#initialize Html2rss::RequestService::PuppetCommander::PreloadRunner
-
#initialize Html2rss::AutoSource::Scraper::WordpressApi::PostsEndpoint
-
#initialize Html2rss::RequestService::PuppetCommander::NavigationGuards
-
#initialize Html2rss::AutoSource::Scraper::SemanticHtml::EntryDeduplicator
-
#initialize Html2rss::Selectors::PostProcessors::HtmlTransformers::TransformUrlsToAbsoluteOnes
-
#inspect Html2rss::Url
-
#inspect_body! Html2rss::RequestService::ResponseGuard
-
#inspect_chunk! Html2rss::RequestService::ResponseGuard
-
install! Html2rss::RequestService::FaradayStrategy::PeerIpValidator
-
#install! Html2rss::RequestService::PuppetCommander::NavigationGuards
-
interaction_budget_for Html2rss::FeedPipeline::RuntimePolicy
-
interstitial? Html2rss::RequestService::BlockedSurface
-
interstitial_signature_for Html2rss::RequestService::BlockedSurface
-
#item Html2rss::Selectors::Context
-
#item Html2rss::Selectors::ItemScope
-
#item_scope Html2rss::Selectors::Context
-
#itemprop Html2rss::SST::Attrs
-
#items_selector Html2rss::Selectors
-
json_documents Html2rss::AutoSource::Scraper::JsonState
-
json_documents Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
json_feed Html2rss
-
#json_response? Html2rss::RequestService::Response
-
json_schema Html2rss::Config
-
json_schema Html2rss::Config::Schema
-
json_schema_json Html2rss::Config
-
#junk Html2rss::Scoring::Score
-
#junk_path? Html2rss::LinkDestination::PathClassifier
-
#junk_score Html2rss::Scoring::RankedSegment
-
#junk_tokens Html2rss::Scoring::Observation
-
keep_only_http_urls! Html2rss::AutoSource::Cleanup
-
keep_only_with_min_words_title! Html2rss::AutoSource::Cleanup
-
#language Html2rss::Channel
-
largest_from_srcsets Html2rss::Html::ArticleRules::Image
-
#last_build_date Html2rss::Channel
-
#latest_navigation_response Html2rss::RequestService::PuppetCommander::NavigationGuards
-
#link? Html2rss::SST::Node
-
#link_resolver Html2rss::AutoSource::Segmenter
-
load_json_schema_extension! Html2rss::Config::Schema
-
load_yaml Html2rss::Config
-
#log_level Html2rss::Defaults
-
logger Html2rss
-
#logger Html2rss::Defaults
-
logger= Html2rss
-
#logger_formatter Html2rss::Defaults
-
main_anchor_for Html2rss::Html::Navigator
-
#max_decompressed_bytes Html2rss::RequestService::Policy
-
#max_redirects Html2rss::Config
-
#max_redirects Html2rss::RequestService::Policy
-
#max_redirects Html2rss::Config::RequestControls
-
#max_requests Html2rss::Config
-
#max_requests Html2rss::RequestSession
-
#max_requests Html2rss::RequestService::Policy
-
#max_requests Html2rss::Config::RequestControls
-
#max_response_bytes Html2rss::RequestService::Policy
-
#media Html2rss::FeedBuilder::Rss::Stylesheet
-
#memo_visible_text Html2rss::SST::Index
-
#memo_word_count Html2rss::SST::Index
-
#min_ttl Html2rss::Defaults
-
#minimum_selector_frequency Html2rss::AutoSource::Segmenter
-
#name Html2rss::SST::Node
-
no_scraper_found_for Html2rss::AutoSource::Scraper
-
#node_count Html2rss::SST::Document
-
#noise_anchor? Html2rss::LinkDestination::NoisePolicy
-
#noise_policy Html2rss::AutoSource::Segmenter
-
normalise Html2rss::AutoSource::Scraper::JsonState::ArticleNormalizer
-
normalize Html2rss::Config::RequestHeaders
-
normalize_config Html2rss::RequestSession::Pager
-
normalize_sst Html2rss::AutoSource::Scraper
-
normalize_types Html2rss::AutoSource::Scraper::Schema
-
normalized_types Html2rss::AutoSource::Scraper::Microdata
-
#on_complete Html2rss::RequestService::FaradayStrategy::StreamingBodyMiddleware
-
#options Html2rss::Selectors::Context
-
options_key Html2rss::AutoSource::Scraper::Html
-
options_key Html2rss::AutoSource::Scraper::Schema
-
options_key Html2rss::AutoSource::Scraper::Sitemap
-
options_key Html2rss::AutoSource::Scraper::Microdata
-
options_key Html2rss::AutoSource::Scraper::JsonState
-
options_key Html2rss::AutoSource::Scraper::MetaOembed
-
options_key Html2rss::AutoSource::Scraper::Microformats2
-
options_key Html2rss::AutoSource::Scraper::SemanticHtml
-
options_key Html2rss::AutoSource::Scraper::WordpressApi
-
#origin_url Html2rss::RequestService::Context
-
#own_text Html2rss::SST::Node
-
#page_responses Html2rss::RequestSession
-
#parent_of Html2rss::SST::Index
-
#parent_until Html2rss::SST::Index
-
parent_until_condition Html2rss::Html::Navigator
-
parse_assignment Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
parse_js_object Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
parse_json Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
#parse_response Html2rss::RequestService::BotasaurusContract
-
#parsed_body Html2rss::RequestService::Response
-
#parsed_body Html2rss::AutoSource::Scraper::JsonState
-
#path Html2rss::Url
-
path Html2rss::Config::Schema
-
path? Html2rss::AutoSource::Scraper::WordpressApi::PageScope::DateArchiveRange
-
#path_length Html2rss::Scoring::Observation
-
#path_segments Html2rss::Url
-
peer_ip_for Html2rss::RequestService::FaradayStrategy::PeerIpValidator
-
#perform_execute Html2rss::RequestService::FaradayStrategy
-
#permit_unanchored Html2rss::AutoSource::Segmenter
-
#policy Html2rss::RequestService::Context
-
#policy Html2rss::FeedPipeline::RuntimePolicy::Resources
-
#port Html2rss::Url
-
#position Html2rss::AutoSource::Segment
-
#position Html2rss::Scoring::RankedSegment
-
#primary_link Html2rss::AutoSource::Segment
-
#primary_link Html2rss::Scoring::RankedSegment
-
#priority Html2rss::AutoSource::Scraper::Sitemap::Parser::SitemapEntry
-
#publish_marker Html2rss::Scoring::Observation
-
#published_at Html2rss::Article
-
#published_at Html2rss::AutoSource::Scraper::Schema::Thing
-
#published_at Html2rss::AutoSource::Scraper::Sitemap::Parser::SitemapEntry
-
#quality Html2rss::Scoring::Score
-
#quality_score Html2rss::Scoring::RankedSegment
-
#query Html2rss::Url
-
#query Html2rss::AutoSource::Scraper::WordpressApi::PageScope
-
#query_values Html2rss::Url
-
quote_unquoted_keys Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
#raise_deferred_error! Html2rss::RequestService::PuppetCommander::NavigationGuards
-
#range Html2rss::Selectors::PostProcessors::Substring
-
#rank Html2rss::Scoring::Engine
-
#rank_top Html2rss::Scoring::Engine
-
#raw Html2rss::SST::Attrs
-
#read_timeout_seconds Html2rss::RequestService::Policy
-
#reason Html2rss::AutoSource::Scraper::WordpressApi::PageScope
-
#recommended? Html2rss::LinkDestination::TextClassifier
-
#recommended_text? Html2rss::Scoring::LinkResolver
-
#recommended_title Html2rss::Scoring::Observation
-
#record_error Html2rss::FeedPipeline::AutoFallback::AttemptState
-
#record_items Html2rss::FeedPipeline::AutoFallback::AttemptState
-
#register_strategy Html2rss::RequestService
-
reject_different_domain! Html2rss::AutoSource::Cleanup
-
#relation Html2rss::RequestService::Context
-
#remaining Html2rss::RequestService::Budget
-
#remaining_interactions Html2rss::RequestService::Budget
-
#remaining_requests Html2rss::RequestService::Budget
-
#remaining_timeout_seconds Html2rss::RequestService::Budget
-
#remember! Html2rss::RequestSession
-
remove_pattern_from_start Html2rss::Html::Rendering::DescriptionBuilder
-
#request Html2rss::Config
-
#request Html2rss::RequestService::Context
-
#request_controls Html2rss::Config
-
#request_payload Html2rss::RequestService::BotasaurusContract
-
#request_session_for Html2rss::FeedPipeline
-
request_slots Html2rss::AutoSource::Scraper::Sitemap
-
#request_slots Html2rss::FeedPipeline::StrategyPlan::Auto
-
#request_slots Html2rss::FeedPipeline::StrategyPlan::Concrete
-
request_slots Html2rss::AutoSource::Scraper::WordpressApi
-
request_slots_for Html2rss::AutoSource
-
request_slots_for Html2rss::RequestSession::Pager
-
resolve Html2rss::FeedPipeline::StrategyPlan
-
resolve Html2rss::AutoSource::Scraper::WordpressApi::PostsEndpoint
-
resolve_link Html2rss::AutoSource::Scraper::JsonState::ArticleNormalizer
-
resources_for Html2rss::FeedPipeline::RuntimePolicy
-
#response Html2rss::FeedPipeline::PipelineOutcome
-
#response_guard Html2rss::RequestService::FaradayStrategy
-
response_url Html2rss::RequestService::PuppetCommander::NavigationGuards
-
#result Html2rss::FeedPipeline::AutoFallback::AttemptState
-
#root Html2rss::SST::Index
-
#root Html2rss::SST::Document
-
#root_node Html2rss::AutoSource::Segment
-
#root_node Html2rss::Scoring::RankedSegment
-
rss_enclosure_for Html2rss::FeedBuilder::ItemPresentation
-
sanitize Html2rss::Url
-
sanitize_config Html2rss::Selectors::PostProcessors::SanitizeHtml
-
scan_for_json_end Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
#schema Html2rss::CLI
-
#schema_object Html2rss::AutoSource::Scraper::Schema::Thing
-
schema_path Html2rss::Config
-
#scheme Html2rss::Url
-
score Html2rss::Scoring::AnchorScore
-
#score Html2rss::Scoring::RankedSegment
-
#scraper Html2rss::Article
-
#scraper Html2rss::Selectors::Context
-
#scraper Html2rss::Selectors::ItemScope
-
scraper_for_schema_object Html2rss::AutoSource::Scraper::Schema
-
scraper_name Html2rss::Status
-
#scraper_tallies Html2rss::Status
-
script_documents Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
#segment Html2rss::Scoring::RankedSegment
-
#segments Html2rss::LinkDestination::PathClassifier
-
#segments Html2rss::LinkDestination::DestinationFacts
-
#select Html2rss::Selectors
-
#select Html2rss::Selectors::ItemScope
-
#select Html2rss::AutoSource::Segmenter::PrimaryLink
-
#select_best_group Html2rss::Scoring::ClusterScorer
-
#select_eligible Html2rss::Scoring::Engine
-
#select_in_scope Html2rss::Selectors
-
#selected_anchor_present Html2rss::Scoring::Observation
-
#selected_strategy Html2rss::Status
-
#selected_strategy Html2rss::FeedPipeline::PipelineOutcome
-
#selector Html2rss::Selectors::Extractors::Href::Options
-
#selector Html2rss::Selectors::Extractors::Html::Options
-
#selector Html2rss::Selectors::Extractors::Text::Options
-
#selector Html2rss::Selectors::Extractors::Attribute::Options
-
#selectors Html2rss::Config
-
#shallow Html2rss::Scoring::Observation
-
#shallow Html2rss::LinkDestination::DestinationFacts
-
#shallow? Html2rss::LinkDestination::PathClassifier
-
#shallow_high_confidence_route? Html2rss::LinkDestination::PathClassifier
-
#should_process? Html2rss::Selectors::PostProcessors::HtmlTransformers::WrapImgInA
-
#src Html2rss::SST::Attrs
-
#srcset Html2rss::SST::Attrs
-
#static Html2rss::Selectors::Extractors::Static::Options
-
#status Html2rss::FeedResult
-
#status Html2rss::RequestService::Response
-
#status Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
#strategy Html2rss::Config
-
#strategy Html2rss::AutoSource::Segment
-
#strategy Html2rss::Config::RequestControls
-
#strategy Html2rss::FeedPipeline::StrategyPlan::Concrete
-
#strategy_attempts Html2rss::Status
-
#strategy_attempts Html2rss::FeedPipeline::PipelineOutcome
-
#strategy_names Html2rss::RequestService
-
strategy_names Html2rss::RequestSession::Pager
-
#strategy_registered? Html2rss::RequestService
-
string Html2rss::AutoSource::Scraper::JsonState::ArticleNormalizer
-
stringify_hash Html2rss::Config::Schema::DeepStringifier
-
strip_trailing_commas Html2rss::AutoSource::Scraper::JsonState::DocumentScanner
-
#strong_post_suffix Html2rss::Scoring::Observation
-
#strong_post_suffix Html2rss::LinkDestination::DestinationFacts
-
#strong_post_suffix? Html2rss::LinkDestination::PathClassifier
-
#stronger_entry? Html2rss::AutoSource::Scraper::SemanticHtml::EntryDeduplicator
-
#style Html2rss::SST::Attrs
-
#stylesheets Html2rss::Config
-
#stylesheets Html2rss::Defaults
-
#sub_sitemap_urls Html2rss::AutoSource::Scraper::Sitemap::Parser::Result
-
#succeed! Html2rss::FeedPipeline::AutoFallback::AttemptState
-
#succeeded? Html2rss::FeedPipeline::AutoFallback::AttemptState
-
supported_root? Html2rss::AutoSource::Scraper::Microdata
-
supported_roots Html2rss::AutoSource::Scraper::Microdata
-
supported_schema_object? Html2rss::AutoSource::Scraper::Schema
-
supported_schema_type? Html2rss::AutoSource::Scraper::Schema
-
supported_type_name Html2rss::AutoSource::Scraper::Microdata
-
#tag_path Html2rss::SST::Node
-
#taxonomy_path Html2rss::LinkDestination::DestinationFacts
-
#taxonomy_path? Html2rss::LinkDestination::PathClassifier
-
#text_classifier Html2rss::Scoring::LinkResolver
-
#text_density Html2rss::SST::Node
-
#time_zone Html2rss::Config
-
time_zone Html2rss::Selectors::PostProcessors::ParseTime
-
#title Html2rss::Article
-
#title Html2rss::Channel
-
#title Html2rss::AutoSource::Scraper::Schema::Thing
-
#title Html2rss::AutoSource::Scraper::Sitemap::Parser::SitemapEntry
-
title_from Html2rss::AutoSource::Scraper::JsonState::CandidateDetector
-
#title_word_count Html2rss::Scoring::Observation
-
#titleized Html2rss::Url
-
#to_generator_comment Html2rss::Status
-
#to_h Html2rss::Status
-
#to_h Html2rss::Config::RequestHeaders
-
#to_h Html2rss::FeedBuilder::JsonFeed::Item
-
#to_html Html2rss::Html::Rendering::PdfRenderer
-
#to_html Html2rss::Html::Rendering::AudioRenderer
-
#to_html Html2rss::Html::Rendering::ImageRenderer
-
#to_html Html2rss::Html::Rendering::VideoRenderer
-
#to_json_feed Html2rss::FeedResult
-
#to_result Html2rss::FeedPipeline
-
#to_rss Html2rss::FeedResult
-
#to_s Html2rss::Url
-
to_single_feed Html2rss::Config::MultipleFeedsConfig
-
#to_xml Html2rss::FeedBuilder::Rss::Stylesheet
-
top_level_item? Html2rss::AutoSource::Scraper::Microdata
-
#total_timeout_seconds Html2rss::Config
-
#total_timeout_seconds Html2rss::RequestService::Policy
-
#total_timeout_seconds Html2rss::Config::RequestControls
-
#transport_meta Html2rss::RequestService::Response
-
#transport_meta Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
traversable_candidate? Html2rss::AutoSource::Scraper::JsonState::CandidateDetector
-
#ttl Html2rss::Channel
-
#type Html2rss::SST::Attrs
-
#type Html2rss::Article::Enclosure
-
#type Html2rss::FeedBuilder::Rss::Stylesheet
-
#unregister_strategy Html2rss::RequestService
-
#upstream_failure? Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
#upstream_failure_message Html2rss::RequestService::BotasaurusContract::ParsedResponse
-
#url Html2rss::Config
-
#url Html2rss::Article
-
#url Html2rss::Channel
-
#url Html2rss::RequestSession
-
#url Html2rss::Article::Enclosure
-
#url Html2rss::RequestService::Context
-
#url Html2rss::RequestService::Response
-
#url Html2rss::AutoSource::Scraper::Schema::Thing
-
#url Html2rss::AutoSource::Scraper::Sitemap::Parser::SitemapEntry
-
#url Html2rss::LinkDestination::DestinationFacts
-
url_from Html2rss::AutoSource::Scraper::JsonState::CandidateDetector
-
#use_top_selectors Html2rss::AutoSource::Segmenter
-
#utility? Html2rss::LinkDestination::TextClassifier
-
#utility_destination? Html2rss::LinkDestination::PathClassifier
-
#utility_landmark? Html2rss::SST::Node
-
#utility_only_route? Html2rss::LinkDestination::PathClassifier
-
#utility_path Html2rss::Scoring::Observation
-
#utility_path Html2rss::LinkDestination::DestinationFacts
-
#utility_path? Html2rss::LinkDestination::PathClassifier
-
#utility_prefix? Html2rss::LinkDestination::TextClassifier
-
#utility_prefix_text? Html2rss::Scoring::LinkResolver
-
#utility_prefix_title Html2rss::Scoring::Observation
-
#utility_text? Html2rss::Scoring::LinkResolver
-
#valid? Html2rss::Article
-
valid? Html2rss::FeedPipeline::StrategyPlan
-
#validate Html2rss::CLI
-
validate Html2rss::Config
-
validate! Html2rss::RequestService::FaradayStrategy::PeerIpValidator
-
validate_args! Html2rss::Selectors::PostProcessors::Base
-
validate_args! Html2rss::Selectors::PostProcessors::Gsub
-
validate_args! Html2rss::Selectors::PostProcessors::Template
-
validate_args! Html2rss::Selectors::PostProcessors::ParseUri
-
validate_args! Html2rss::Selectors::PostProcessors::Substring
-
validate_args! Html2rss::Selectors::PostProcessors::ParseTime
-
validate_args! Html2rss::Selectors::PostProcessors::SanitizeHtml
-
validate_args! Html2rss::Selectors::PostProcessors::HtmlToMarkdown
-
validate_args! Html2rss::Selectors::PostProcessors::MarkdownToHtml
-
#validate_final! Html2rss::RequestService::PuppetCommander::NavigationGuards
-
#validate_redirect! Html2rss::RequestService::Policy
-
#validate_remote_ip! Html2rss::RequestService::Policy
-
#validate_remote_ip! Html2rss::RequestService::NetworkGuard
-
#validate_request! Html2rss::RequestService::Policy
-
validate_yaml Html2rss::Config
-
#value Html2rss::Selectors::PostProcessors::Base
-
#vanity_path Html2rss::LinkDestination::DestinationFacts
-
#vanity_path? Html2rss::LinkDestination::PathClassifier
-
#version Html2rss::Status
-
#visible_text Html2rss::SST::Node
-
#visited? Html2rss::RequestSession
-
#weak_signals? Html2rss::Scoring::Observation
-
#with_effective_values Html2rss::Config::RequestControls
-
#with_path Html2rss::Url
-
#with_query_values Html2rss::Url
-
#word_count Html2rss::SST::Node