Class: ContextDev::Models::WebWebScrapeMdParams

Inherits:
Internal::Type::BaseModel show all
Extended by:
Internal::Type::RequestParameters::Converter
Includes:
Internal::Type::RequestParameters
Defined in:
lib/context_dev/models/web_web_scrape_md_params.rb,
sig/context_dev/models/web_web_scrape_md_params.rbs

Overview

See Also:

  • ContextDev::Resources::Web#web_scrape_md

Defined Under Namespace

Modules: Action, Country, IncludeFrames, IncludeImages, IncludeLinks, SettleAnimations, ShortenBase64Images, UseMainContentOnly, Zdr Classes: Pdf

Constant Summary

Constants included from Internal::Type::RequestParameters

Internal::Type::RequestParameters::ContextDev

Instance Attribute Summary collapse

Attributes included from Internal::Type::RequestParameters

#request_options

Class Method Summary collapse

Instance Method Summary collapse

Methods included from Internal::Type::RequestParameters::Converter

dump_request

Methods included from Internal::Type::RequestParameters

included

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(action:, do_: :perform) ⇒ Object

Resolve and perform one natural-language browser action.

Parameters:

  • action (String)
  • do_ (Symbol, :perform) (defaults to: :perform) 



# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 144

Instance Attribute Details

#actions ⇒ Array<ContextDev::Models::WebWebScrapeMdParams::Action::Wait, ContextDev::Models::WebWebScrapeMdParams::Action::Perform>?

Optional browser actions executed in array order after the page loads and before content is captured. Requires a paid plan. Send a JSON array in the query parameter. Maximum: 5 actions.

Parameters:

  • value (::Array[ContextDev::Models::WebWebScrapeMdParams::action], nil)

Returns:



23
24
25
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 23

optional :actions,
-> { ContextDev::Internal::Type::ArrayOf[union: ContextDev::WebWebScrapeMdParams::Action] },
nil?: true

#country ⇒ Symbol, ...

Fetch the target page through a residential proxy in this country (ISO 3166-1 alpha-2).

Returns:



32
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 32

optional :country, enum: -> { ContextDev::WebWebScrapeMdParams::Country }

#exclude_selectors ⇒ Array<String>?

CSS selectors to remove before conversion to Markdown. Applied after includeSelectors. Exclusion takes precedence: an element matching both is removed. Examples: "nav", "footer", ".ad-banner", "[aria-hidden=true]".

Parameters:

  • value (::Array[String], nil)

Returns:

  • (Array<String>, nil) 


40
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 40

optional :exclude_selectors, ContextDev::Internal::Type::ArrayOf[String], nil?: true

#headers ⇒ Hash{Symbol=>String}?

Optional outbound HTTP headers forwarded only to the target URL, sent as deep-object query params such as headers=value. When provided, caching is bypassed: the result is neither read from nor written to cache.

Parameters:

  • (::Hash[Symbol, String])

Returns:

  • (Hash{Symbol=>String}, nil) 


48
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 48

optional :headers, ContextDev::Internal::Type::HashOf[String]

#include_frames ⇒ Boolean, ...

When true, the contents of iframes are rendered to Markdown.

Returns:



54
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 54

optional :include_frames, union: -> { ContextDev::WebWebScrapeMdParams::IncludeFrames }

#include_images ⇒ Boolean, ...

Include image references in Markdown output

Returns:



60
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 60

optional :include_images, union: -> { ContextDev::WebWebScrapeMdParams::IncludeImages }

#include_links ⇒ Boolean, ...

Preserve hyperlinks in Markdown output

Returns:



66
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 66

optional :include_links, union: -> { ContextDev::WebWebScrapeMdParams::IncludeLinks }

#include_selectors ⇒ Array<String>?

CSS selectors. When provided, only matching HTML subtrees (and their descendants) are kept before conversion to Markdown. When omitted, the entire document is kept. Examples: "article.main", "#content", "[role=main]".

Parameters:

  • value (::Array[String], nil)

Returns:

  • (Array<String>, nil) 


74
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 74

optional :include_selectors, ContextDev::Internal::Type::ArrayOf[String], nil?: true

#max_age_ms ⇒ Integer?

Return a cached result if a prior scrape for the same parameters exists and is younger than this many milliseconds. Defaults to 1 day (86400000 ms) when omitted. Max is 30 days (2592000000 ms). Set to 0 to always scrape fresh.

Parameters:

  • value (Integer, nil)

Returns:

  • (Integer, nil) 


82
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 82

optional :max_age_ms, Integer, nil?: true

#pdf ⇒ ContextDev::Models::WebWebScrapeMdParams::Pdf?

PDF parsing controls. Use start/end to limit text extraction and embedded-image detection/OCR to an inclusive 1-based page range.

Returns:



89
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 89

optional :pdf, -> { ContextDev::WebWebScrapeMdParams::Pdf }

#settle_animations ⇒ Boolean, ...

When true, waits briefly for CSS and transition animations to settle before converting to Markdown. Defaults to false. This adds a bit of latency in exchange for more stable output on animated pages.

Returns:



97
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 97

optional :settle_animations, union: -> { ContextDev::WebWebScrapeMdParams::SettleAnimations }

#shorten_base64_images ⇒ Boolean, ...

Shorten base64-encoded image data in the Markdown output

Returns:



103
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 103

optional :shorten_base64_images, union: -> { ContextDev::WebWebScrapeMdParams::ShortenBase64Images }

#tags ⇒ Array<String>?

Optional comma-separated caller-defined tags for tracking this request. Tags are recorded on the request's usage log and can be used to filter usage on the dashboard usage page. Up to 20 tags, each 1-50 characters.

Parameters:

  • (::Array[String])

Returns:

  • (Array<String>, nil) 


111
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 111

optional :tags, ContextDev::Internal::Type::ArrayOf[String]

#timeout_ms ⇒ Integer?

Optional timeout in milliseconds for the request. If the request takes longer than this value, it will be aborted with a 408 status code. Maximum allowed value is 300000ms (5 minutes).

Parameters:

  • (Integer)

Returns:

  • (Integer, nil) 


119
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 119

optional :timeout_ms, Integer

#url ⇒ String

Full URL to scrape into LLM usable Markdown (must include http:// or https:// protocol)

Parameters:

  • value (String)

Returns:

  • (String) 


15
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 15

required :url, String

#use_main_content_only ⇒ Boolean, ...

Extract only the main content of the page, excluding headers, footers, sidebars, and navigation

Returns:



126
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 126

optional :use_main_content_only, union: -> { ContextDev::WebWebScrapeMdParams::UseMainContentOnly }

#wait_for_ms ⇒ Integer?

Optional browser wait time in milliseconds after initial page load before converting the page to Markdown. Min: 0. Max: 30000 (30 seconds).

Parameters:

  • value (Integer, nil)

Returns:

  • (Integer, nil) 


133
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 133

optional :wait_for_ms, Integer, nil?: true

#zdr ⇒ Symbol, ...

Set to enabled to bypass shared caches and omit request and response content from retained usage logs. Requires zero data retention to be enabled for your organization (contact support@context.dev), otherwise the request fails with ZDR_NOT_ENABLED. Successful ZDR responses include X-Context-ZDR: true.

Returns:



142
 
# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 142

optional :zdr, enum: -> { ContextDev::WebWebScrapeMdParams::Zdr }

Class Method Details

.values ⇒ Array<Symbol>

Returns:

  • (Array<Symbol>) 



# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 449

.variants ⇒ Array(ContextDev::Models::WebWebScrapeMdParams::Action::Wait, ContextDev::Models::WebWebScrapeMdParams::Action::Perform)

Returns:




# File 'lib/context_dev/models/web_web_scrape_md_params.rb', line 235

Instance Method Details

#to_hash ⇒ {

Returns:

  • ({) 


130
 
# File 'sig/context_dev/models/web_web_scrape_md_params.rbs', line 130

def to_hash: -> {