Class: ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata
- Inherits:
-
Internal::Type::BaseModel
- Object
- Internal::Type::BaseModel
- ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata
- Defined in:
- lib/context_dev/models/web_web_crawl_md_response.rb,
sig/context_dev/models/web_web_crawl_md_response.rbs
Overview
Defined Under Namespace
Modules: AdditionalMeta, OpenGraph, Twitter Classes: Alternate, Heading
Instance Attribute Summary collapse
-
#additional_meta ⇒ Hash{Symbol=>String, Array<String>}?
Additional non-social meta tags not promoted to top-level metadata fields.
-
#alternates ⇒ Array<ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata::Alternate>?
Resolved alternate links from link rel=alternate tags.
-
#author ⇒ String?
Author metadata, when present.
-
#canonical_url ⇒ String?
Resolved canonical URL, when present.
-
#crawl_depth ⇒ Integer
Depth relative to the start URL.
-
#description ⇒ String?
Best description extracted from standard, Open Graph, or Twitter metadata.
-
#favicon ⇒ String?
Resolved favicon URL, when present.
-
#final_url ⇒ String
Final URL scraped after redirects or scraper fallback, when known.
-
#headings ⇒ Array<ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata::Heading>?
Page headings (h1–h6) in document order, extracted from the unfiltered document.
-
#image ⇒ String?
Primary resolved preview image from Open Graph, Twitter, or image metadata.
-
#json_ld ⇒ Array<Hash{Symbol=>Object}>?
JSON-LD structured data blocks parsed from the page.
-
#keywords ⇒ Array<String>?
Keywords extracted from the page's keywords meta tag.
-
#language ⇒ String?
Language extracted from html lang or language meta tags.
-
#modified_time ⇒ String?
Modified timestamp/date from page metadata, when present.
-
#open_graph ⇒ Hash{Symbol=>String, Array<String>}?
Open Graph metadata with the og: prefix removed and keys camel-cased.
-
#published_time ⇒ String?
Published timestamp/date from page metadata, when present.
-
#robots ⇒ String?
Robots meta directive, when present.
-
#site_name ⇒ String?
Site or application name from page metadata.
-
#source_url ⇒ String
Original URL requested by the caller.
-
#status_code ⇒ Integer
HTTP status code of the response.
-
#success ⇒ Boolean
true if the page was fetched and parsed successfully.
-
#title ⇒ String
Best page title extracted from the page (empty string if unavailable).
-
#twitter ⇒ Hash{Symbol=>String, Array<String>}?
Twitter card metadata with the twitter: prefix removed and keys camel-cased.
-
#url ⇒ String
The crawl URL fetched for this page.
Instance Method Summary collapse
- #initialize(level:, text:) ⇒ Object constructor
- #to_hash ⇒ {
Methods inherited from Internal::Type::BaseModel
==, #==, #[], coerce, #deconstruct_keys, #deep_to_h, dump, fields, hash, #hash, inherited, inspect, #inspect, known_fields, optional, recursively_to_h, required, #to_h, #to_json, #to_s, to_sorbet_type, #to_yaml
Methods included from Internal::Type::Converter
#coerce, coerce, #dump, dump, #inspect, inspect, meta_info, new_coerce_state, type_info
Methods included from Internal::Util::SorbetRuntimeSupport
#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type
Constructor Details
#initialize(level:, text:) ⇒ Object
|
|
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 401
|
Instance Attribute Details
#additional_meta ⇒ Hash{Symbol=>String, Array<String>}?
Additional non-social meta tags not promoted to top-level metadata fields.
202 203 204 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 202 optional :additional_meta, -> { ContextDev::Internal::Type::HashOf[union: ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata::AdditionalMeta] }, api_name: :additionalMeta |
#alternates ⇒ Array<ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata::Alternate>?
Resolved alternate links from link rel=alternate tags.
210 211 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 210 optional :alternates, -> { ContextDev::Internal::Type::ArrayOf[ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata::Alternate] } |
#author ⇒ String?
Author metadata, when present.
217 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 217 optional :author, String |
#canonical_url ⇒ String?
Resolved canonical URL, when present.
223 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 223 optional :canonical_url, String, api_name: :canonicalUrl |
#crawl_depth ⇒ Integer
Depth relative to the start URL. 0 = start URL, 1 = one link away.
159 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 159 required :crawl_depth, Integer, api_name: :crawlDepth |
#description ⇒ String?
Best description extracted from standard, Open Graph, or Twitter metadata.
229 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 229 optional :description, String |
#favicon ⇒ String?
Resolved favicon URL, when present.
235 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 235 optional :favicon, String |
#final_url ⇒ String
Final URL scraped after redirects or scraper fallback, when known. Falls back to sourceUrl when unavailable.
166 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 166 required :final_url, String, api_name: :finalUrl |
#headings ⇒ Array<ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata::Heading>?
Page headings (h1–h6) in document order, extracted from the unfiltered document. Capped at the first 500 headings. Omitted when the page has none.
242 243 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 242 optional :headings, -> { ContextDev::Internal::Type::ArrayOf[ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata::Heading] } |
#image ⇒ String?
Primary resolved preview image from Open Graph, Twitter, or image metadata.
249 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 249 optional :image, String |
#json_ld ⇒ Array<Hash{Symbol=>Object}>?
JSON-LD structured data blocks parsed from the page.
255 256 257 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 255 optional :json_ld, ContextDev::Internal::Type::ArrayOf[ContextDev::Internal::Type::HashOf[ContextDev::Internal::Type::Unknown]], api_name: :jsonLd |
#keywords ⇒ Array<String>?
Keywords extracted from the page's keywords meta tag.
263 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 263 optional :keywords, ContextDev::Internal::Type::ArrayOf[String] |
#language ⇒ String?
Language extracted from html lang or language meta tags.
269 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 269 optional :language, String |
#modified_time ⇒ String?
Modified timestamp/date from page metadata, when present.
275 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 275 optional :modified_time, String, api_name: :modifiedTime |
#open_graph ⇒ Hash{Symbol=>String, Array<String>}?
Open Graph metadata with the og: prefix removed and keys camel-cased.
281 282 283 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 281 optional :open_graph, -> { ContextDev::Internal::Type::HashOf[union: ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata::OpenGraph] }, api_name: :openGraph |
#published_time ⇒ String?
Published timestamp/date from page metadata, when present.
289 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 289 optional :published_time, String, api_name: :publishedTime |
#robots ⇒ String?
Robots meta directive, when present.
295 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 295 optional :robots, String |
#site_name ⇒ String?
Site or application name from page metadata.
301 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 301 optional :site_name, String, api_name: :siteName |
#source_url ⇒ String
Original URL requested by the caller.
172 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 172 required :source_url, String, api_name: :sourceUrl |
#status_code ⇒ Integer
HTTP status code of the response
178 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 178 required :status_code, Integer, api_name: :statusCode |
#success ⇒ Boolean
true if the page was fetched and parsed successfully
184 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 184 required :success, ContextDev::Internal::Type::Boolean |
#title ⇒ String
Best page title extracted from the page (empty string if unavailable).
190 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 190 required :title, String |
#twitter ⇒ Hash{Symbol=>String, Array<String>}?
Twitter card metadata with the twitter: prefix removed and keys camel-cased.
307 308 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 307 optional :twitter, -> { ContextDev::Internal::Type::HashOf[union: ContextDev::Models::WebWebCrawlMdResponse::Result::Metadata::Twitter] } |
#url ⇒ String
The crawl URL fetched for this page.
196 |
# File 'lib/context_dev/models/web_web_crawl_md_response.rb', line 196 required :url, String |
Instance Method Details
#to_hash ⇒ {
280 |
# File 'sig/context_dev/models/web_web_crawl_md_response.rbs', line 280
def to_hash: -> {
|