RubyGems - berrycrawl - Versions diffs - 0.1.0 - Mend

berrycrawl 0.1.0

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.

Files changed (136) hide show

checksums.yaml +7 -0
data/.fern/metadata.json +12 -0
data/.rubocop.yml +103 -0
data/CONTRIBUTING.md +120 -0
data/LICENSE +17 -0
data/README.md +183 -0
data/Rakefile +20 -0
data/custom.gemspec.rb +16 -0
data/lib/Berrycrawl/account/client.rb +44 -0
data/lib/Berrycrawl/brand/client.rb +48 -0
data/lib/Berrycrawl/brand/types/brand_dto.rb +15 -0
data/lib/Berrycrawl/client.rb +268 -0
data/lib/Berrycrawl/environment.rb +7 -0
data/lib/Berrycrawl/errors/api_error.rb +8 -0
data/lib/Berrycrawl/errors/client_error.rb +17 -0
data/lib/Berrycrawl/errors/redirect_error.rb +8 -0
data/lib/Berrycrawl/errors/response_error.rb +42 -0
data/lib/Berrycrawl/errors/server_error.rb +11 -0
data/lib/Berrycrawl/errors/timeout_error.rb +8 -0
data/lib/Berrycrawl/internal/errors/constraint_error.rb +10 -0
data/lib/Berrycrawl/internal/errors/type_error.rb +10 -0
data/lib/Berrycrawl/internal/http/base_request.rb +51 -0
data/lib/Berrycrawl/internal/http/raw_client.rb +252 -0
data/lib/Berrycrawl/internal/iterators/cursor_item_iterator.rb +28 -0
data/lib/Berrycrawl/internal/iterators/cursor_page_iterator.rb +63 -0
data/lib/Berrycrawl/internal/iterators/item_iterator.rb +65 -0
data/lib/Berrycrawl/internal/iterators/offset_item_iterator.rb +30 -0
data/lib/Berrycrawl/internal/iterators/offset_page_iterator.rb +103 -0
data/lib/Berrycrawl/internal/json/request.rb +41 -0
data/lib/Berrycrawl/internal/json/serializable.rb +25 -0
data/lib/Berrycrawl/internal/multipart/multipart_encoder.rb +141 -0
data/lib/Berrycrawl/internal/multipart/multipart_form_data.rb +78 -0
data/lib/Berrycrawl/internal/multipart/multipart_form_data_part.rb +51 -0
data/lib/Berrycrawl/internal/multipart/multipart_request.rb +40 -0
data/lib/Berrycrawl/internal/types/array.rb +47 -0
data/lib/Berrycrawl/internal/types/boolean.rb +34 -0
data/lib/Berrycrawl/internal/types/enum.rb +56 -0
data/lib/Berrycrawl/internal/types/hash.rb +36 -0
data/lib/Berrycrawl/internal/types/model/field.rb +38 -0
data/lib/Berrycrawl/internal/types/model.rb +208 -0
data/lib/Berrycrawl/internal/types/type.rb +35 -0
data/lib/Berrycrawl/internal/types/union.rb +161 -0
data/lib/Berrycrawl/internal/types/unknown.rb +15 -0
data/lib/Berrycrawl/internal/types/utils.rb +116 -0
data/lib/Berrycrawl/jobs/client.rb +127 -0
data/lib/Berrycrawl/jobs/types/cancel_jobs_request.rb +11 -0
data/lib/Berrycrawl/jobs/types/get_jobs_request.rb +15 -0
data/lib/Berrycrawl/jobs/types/list_jobs_request.rb +17 -0
data/lib/Berrycrawl/jobs/types/list_jobs_request_status.rb +17 -0
data/lib/Berrycrawl/jobs/types/list_jobs_request_type.rb +14 -0
data/lib/Berrycrawl/types/account_response.rb +11 -0
data/lib/Berrycrawl/types/account_response_data.rb +21 -0
data/lib/Berrycrawl/types/account_response_data_plan.rb +17 -0
data/lib/Berrycrawl/types/account_response_data_queue.rb +11 -0
data/lib/Berrycrawl/types/action_dto.rb +21 -0
data/lib/Berrycrawl/types/action_dto_direction.rb +12 -0
data/lib/Berrycrawl/types/action_dto_type.rb +18 -0
data/lib/Berrycrawl/types/agent_config_dto.rb +11 -0
data/lib/Berrycrawl/types/agent_config_dto_mode.rb +12 -0
data/lib/Berrycrawl/types/brand_asset.rb +17 -0
data/lib/Berrycrawl/types/brand_profile.rb +27 -0
data/lib/Berrycrawl/types/brand_profile_colors_item.rb +11 -0
data/lib/Berrycrawl/types/brand_profile_fonts_item.rb +11 -0
data/lib/Berrycrawl/types/brand_profile_socials_item.rb +11 -0
data/lib/Berrycrawl/types/brand_response.rb +11 -0
data/lib/Berrycrawl/types/brand_response_data.rb +11 -0
data/lib/Berrycrawl/types/brand_response_data_meta.rb +15 -0
data/lib/Berrycrawl/types/cancel_job_response.rb +11 -0
data/lib/Berrycrawl/types/cancel_job_response_data.rb +11 -0
data/lib/Berrycrawl/types/change_tracking_format_dto.rb +15 -0
data/lib/Berrycrawl/types/change_tracking_format_dto_type.rb +11 -0
data/lib/Berrycrawl/types/crawl_dto.rb +41 -0
data/lib/Berrycrawl/types/crawl_dto_sitemap.rb +13 -0
data/lib/Berrycrawl/types/extract_dto.rb +29 -0
data/lib/Berrycrawl/types/extract_webhook_config_dto.rb +15 -0
data/lib/Berrycrawl/types/job_created_response.rb +15 -0
data/lib/Berrycrawl/types/job_response.rb +11 -0
data/lib/Berrycrawl/types/job_response_data.rb +37 -0
data/lib/Berrycrawl/types/job_response_data_errors_item.rb +11 -0
data/lib/Berrycrawl/types/job_summary.rb +29 -0
data/lib/Berrycrawl/types/job_summary_type.rb +12 -0
data/lib/Berrycrawl/types/json_format_dto.rb +13 -0
data/lib/Berrycrawl/types/json_format_dto_type.rb +11 -0
data/lib/Berrycrawl/types/list_jobs_response.rb +11 -0
data/lib/Berrycrawl/types/list_jobs_response_data.rb +11 -0
data/lib/Berrycrawl/types/list_webhooks_response.rb +11 -0
data/lib/Berrycrawl/types/location_dto.rb +11 -0
data/lib/Berrycrawl/types/map_dto.rb +23 -0
data/lib/Berrycrawl/types/map_dto_sitemap.rb +13 -0
data/lib/Berrycrawl/types/map_link.rb +13 -0
data/lib/Berrycrawl/types/map_response.rb +15 -0
data/lib/Berrycrawl/types/message_response.rb +11 -0
data/lib/Berrycrawl/types/pagination.rb +15 -0
data/lib/Berrycrawl/types/parse_dto.rb +11 -0
data/lib/Berrycrawl/types/scrape_dto.rb +49 -0
data/lib/Berrycrawl/types/scrape_dto_formats_item.rb +17 -0
data/lib/Berrycrawl/types/scrape_dto_formats_item_zero.rb +18 -0
data/lib/Berrycrawl/types/scrape_dto_proxy.rb +16 -0
data/lib/Berrycrawl/types/scrape_metadata.rb +17 -0
data/lib/Berrycrawl/types/scrape_response.rb +17 -0
data/lib/Berrycrawl/types/scrape_response_credits.rb +9 -0
data/lib/Berrycrawl/types/screenshot_clip_dto.rb +15 -0
data/lib/Berrycrawl/types/screenshot_cookie_dto.rb +21 -0
data/lib/Berrycrawl/types/screenshot_cookie_dto_same_site.rb +13 -0
data/lib/Berrycrawl/types/screenshot_dto.rb +79 -0
data/lib/Berrycrawl/types/screenshot_dto_color_scheme.rb +12 -0
data/lib/Berrycrawl/types/screenshot_dto_device.rb +15 -0
data/lib/Berrycrawl/types/screenshot_dto_format.rb +13 -0
data/lib/Berrycrawl/types/screenshot_dto_full_page_algorithm.rb +13 -0
data/lib/Berrycrawl/types/screenshot_dto_proxy.rb +16 -0
data/lib/Berrycrawl/types/screenshot_dto_response_format.rb +12 -0
data/lib/Berrycrawl/types/screenshot_dto_scale.rb +12 -0
data/lib/Berrycrawl/types/screenshot_dto_wait_until.rb +13 -0
data/lib/Berrycrawl/types/screenshot_location_dto.rb +11 -0
data/lib/Berrycrawl/types/screenshot_viewport_dto.rb +11 -0
data/lib/Berrycrawl/types/search_dto.rb +23 -0
data/lib/Berrycrawl/types/search_response.rb +19 -0
data/lib/Berrycrawl/types/search_response_provider.rb +11 -0
data/lib/Berrycrawl/types/search_result.rb +19 -0
data/lib/Berrycrawl/types/search_result_provider.rb +11 -0
data/lib/Berrycrawl/types/summary_format_dto.rb +11 -0
data/lib/Berrycrawl/types/summary_format_dto_type.rb +11 -0
data/lib/Berrycrawl/types/test_webhook_response.rb +15 -0
data/lib/Berrycrawl/types/webhook.rb +23 -0
data/lib/Berrycrawl/types/webhook_config_dto.rb +15 -0
data/lib/Berrycrawl/types/webhook_response.rb +11 -0
data/lib/Berrycrawl/version.rb +5 -0
data/lib/Berrycrawl/webhooks/client.rb +214 -0
data/lib/Berrycrawl/webhooks/types/create_webhook_dto.rb +13 -0
data/lib/Berrycrawl/webhooks/types/delete_webhooks_request.rb +11 -0
data/lib/Berrycrawl/webhooks/types/get_webhooks_request.rb +11 -0
data/lib/Berrycrawl/webhooks/types/test_webhook_dto.rb +15 -0
data/lib/Berrycrawl/webhooks/types/update_webhook_dto.rb +17 -0
data/lib/Berrycrawl.rb +130 -0
data/reference.md +1759 -0
metadata +179 -0

data/reference.md ADDED Viewed

@@ -0,0 +1,1759 @@
+# Reference
+<details><summary><code>client.<a href="/lib/Berrycrawl/client.rb">crawl</a>(request) -> Berrycrawl::Types::JobCreatedResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.crawl(url: "https://example.com")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**allow_external_links:** `Internal::Types::Boolean` — Whether to allow crawling external domains
+</dd>
+</dl>
+<dl>
+<dd>
+**allow_subdomains:** `Internal::Types::Boolean` — Whether to allow crawling subdomains
+</dd>
+</dl>
+<dl>
+<dd>
+**crawl_entire_domain:** `Internal::Types::Boolean` — Whether to crawl entire domain or just subtree
+</dd>
+</dl>
+<dl>
+<dd>
+**deduplicate_similar_ur_ls:** `Internal::Types::Boolean` — Deduplicate similar URLs using intelligent matching
+</dd>
+</dl>
+<dl>
+<dd>
+**delay:** `Integer` — Delay between page scrapes in milliseconds
+</dd>
+</dl>
+<dl>
+<dd>
+**exclude_paths:** `Internal::Types::Array[String]` — Regex patterns to exclude paths
+</dd>
+</dl>
+<dl>
+<dd>
+**ignore_query_parameters:** `Internal::Types::Boolean` — Ignore query parameters when deduplicating URLs
+</dd>
+</dl>
+<dl>
+<dd>
+**include_paths:** `Internal::Types::Array[String]` — Regex patterns to include paths
+</dd>
+</dl>
+<dl>
+<dd>
+**limit:** `Integer` — Maximum number of pages to crawl
+</dd>
+</dl>
+<dl>
+<dd>
+**max_concurrency:** `Integer` — Maximum number of concurrent scrapes for this crawl
+</dd>
+</dl>
+<dl>
+<dd>
+**max_discovery_depth:** `Integer` — Maximum depth for URL discovery
+</dd>
+</dl>
+<dl>
+<dd>
+**prompt:** `String` — Natural language instructions for crawl configuration
+</dd>
+</dl>
+<dl>
+<dd>
+**scrape_options:** `Internal::Types::Hash[String, Object]` — Scrape options to apply to each page. actions accepts at most 25 bounded browser actions. zeroDataRetention: true is currently rejected with 400 ZERO_DATA_RETENTION_NOT_SUPPORTED.
+</dd>
+</dl>
+<dl>
+<dd>
+**sitemap:** `Berrycrawl::Types::CrawlDtoSitemap` — Sitemap handling strategy
+</dd>
+</dl>
+<dl>
+<dd>
+**url:** `String` — Starting URL to crawl
+</dd>
+</dl>
+<dl>
+<dd>
+**webhook:** `Berrycrawl::Types::WebhookConfigDto` — Webhook configuration
+</dd>
+</dl>
+<dl>
+<dd>
+**zero_data_retention:** `Internal::Types::Boolean` — Reserved for a future zero-data-retention mode. true is currently rejected with 400 ZERO_DATA_RETENTION_NOT_SUPPORTED; omit or use false.
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.<a href="/lib/Berrycrawl/client.rb">extract</a>(request) -> Berrycrawl::Types::JobCreatedResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.extract(prompt: "Extract all product names, prices, and descriptions from these pages")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**agent:** `Berrycrawl::Types::AgentConfigDto` — Agent configuration
+</dd>
+</dl>
+<dl>
+<dd>
+**enable_web_search:** `Internal::Types::Boolean` — Enable web search for URL discovery
+</dd>
+</dl>
+<dl>
+<dd>
+**ignore_invalid_ur_ls:** `Internal::Types::Boolean` — Ignore invalid URLs and process remaining valid ones
+</dd>
+</dl>
+<dl>
+<dd>
+**ignore_sitemap:** `Internal::Types::Boolean` — Ignore sitemap during URL discovery
+</dd>
+</dl>
+<dl>
+<dd>
+**include_subdomains:** `Internal::Types::Boolean` — Include subdomains in extraction
+</dd>
+</dl>
+<dl>
+<dd>
+**prompt:** `String` — Natural language prompt describing what to extract. Maximum 16384 UTF-8 bytes.
+</dd>
+</dl>
+<dl>
+<dd>
+**schema:** `Internal::Types::Hash[String, Object]` — JSON Schema for structured output. Serialized schema is limited to 65536 UTF-8 bytes.
+</dd>
+</dl>
+<dl>
+<dd>
+**scrape_options:** `Internal::Types::Hash[String, Object]` — Scrape options for each URL. zeroDataRetention: true is currently rejected with 400 ZERO_DATA_RETENTION_NOT_SUPPORTED.
+</dd>
+</dl>
+<dl>
+<dd>
+**show_sources:** `Internal::Types::Boolean` — Include source citations in response
+</dd>
+</dl>
+<dl>
+<dd>
+**urls:** `Internal::Types::Array[String]` — 1–20 unique public HTTP(S) URLs. May be omitted only when enableWebSearch is true. Each URL is limited to 2048 UTF-8 bytes.
+</dd>
+</dl>
+<dl>
+<dd>
+**webhook:** `Berrycrawl::Types::ExtractWebhookConfigDto` — Webhook configuration
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.<a href="/lib/Berrycrawl/client.rb">map</a>(request) -> Berrycrawl::Types::MapResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.map(url: "https://example.com")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**ignore_query_parameters:** `Internal::Types::Boolean` — Ignore query parameters when discovering URLs
+</dd>
+</dl>
+<dl>
+<dd>
+**include_subdomains:** `Internal::Types::Boolean` — Include subdomains in the map
+</dd>
+</dl>
+<dl>
+<dd>
+**limit:** `Integer` — Maximum number of URLs to return
+</dd>
+</dl>
+<dl>
+<dd>
+**location:** `Berrycrawl::Types::LocationDto` — Location configuration
+</dd>
+</dl>
+<dl>
+<dd>
+**search:** `String` — Search filter for URLs
+</dd>
+</dl>
+<dl>
+<dd>
+**sitemap:** `Berrycrawl::Types::MapDtoSitemap` — How to handle sitemaps
+</dd>
+</dl>
+<dl>
+<dd>
+**timeout:** `Integer` — Timeout for map operation in milliseconds
+</dd>
+</dl>
+<dl>
+<dd>
+**url:** `String` — URL to map
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.<a href="/lib/Berrycrawl/client.rb">parse</a>(request) -> Berrycrawl::Types::ScrapeResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.parse(url: "https://example.com/report.pdf")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**timeout:** `Integer`
+</dd>
+</dl>
+<dl>
+<dd>
+**url:** `String` — Public PDF, Word document, or spreadsheet URL
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.<a href="/lib/Berrycrawl/client.rb">scrape</a>(request) -> Berrycrawl::Types::ScrapeResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.scrape
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**actions:** `Internal::Types::Array[Berrycrawl::Types::ActionDto]` — Browser actions to execute
+</dd>
+</dl>
+<dl>
+<dd>
+**block_ads:** `Internal::Types::Boolean` — Enable ad-blocking and cookie popup blocking
+</dd>
+</dl>
+<dl>
+<dd>
+**domain:** `String` — Domain to scrape. Normalized to https://domain when url is omitted.
+</dd>
+</dl>
+<dl>
+<dd>
+**exclude_tags:** `Internal::Types::Array[String]` — CSS selectors to exclude
+</dd>
+</dl>
+<dl>
+<dd>
+**extraction_schema:** `Internal::Types::Hash[String, Object]` — Schema for structured data extraction (used with json format)
+</dd>
+</dl>
+<dl>
+<dd>
+**formats:** `Internal::Types::Array[Berrycrawl::Types::ScrapeDtoFormatsItem]` — Output formats - can be simple strings or format objects with options
+</dd>
+</dl>
+<dl>
+<dd>
+**headers:** `Internal::Types::Hash[String, Object]` — Custom headers
+</dd>
+</dl>
+<dl>
+<dd>
+**include_tags:** `Internal::Types::Array[String]` — CSS selectors to include
+</dd>
+</dl>
+<dl>
+<dd>
+**location:** `Berrycrawl::Types::LocationDto` — Location settings
+</dd>
+</dl>
+<dl>
+<dd>
+**max_age:** `Integer` — Cache max age in milliseconds
+</dd>
+</dl>
+<dl>
+<dd>
+**mobile:** `Internal::Types::Boolean` — Emulate mobile device for scraping
+</dd>
+</dl>
+<dl>
+<dd>
+**only_main_content:** `Internal::Types::Boolean` — Extract only main content
+</dd>
+</dl>
+<dl>
+<dd>
+**proxy:** `Berrycrawl::Types::ScrapeDtoProxy` — Proxy mode. auto starts direct and escalates only when blocked. basic is an alias for none.
+</dd>
+</dl>
+<dl>
+<dd>
+**remove_base64_images:** `Internal::Types::Boolean` — Remove base64 images from output (keeps alt text)
+</dd>
+</dl>
+<dl>
+<dd>
+**screenshot_as_base64:** `Internal::Types::Boolean` — Return screenshot/PDF output inline as a base64 data URL instead of an uploaded CDN URL. Default false (a CDN URL is returned).
+</dd>
+</dl>
+<dl>
+<dd>
+**skip_tls_verification:** `Internal::Types::Boolean` — Skip TLS certificate verification
+</dd>
+</dl>
+<dl>
+<dd>
+**store_in_cache:** `Internal::Types::Boolean` — Store result in cache
+</dd>
+</dl>
+<dl>
+<dd>
+**timeout:** `Integer` — Request timeout in milliseconds
+</dd>
+</dl>
+<dl>
+<dd>
+**url:** `String` — URL to scrape. Either url or domain is required.
+</dd>
+</dl>
+<dl>
+<dd>
+**wait_for:** `Integer` — Wait time before scraping (ms)
+</dd>
+</dl>
+<dl>
+<dd>
+**zero_data_retention:** `Internal::Types::Boolean` — Reserved for a future zero-data-retention mode. true is currently rejected with 400 ZERO_DATA_RETENTION_NOT_SUPPORTED; omit or use false.
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.<a href="/lib/Berrycrawl/client.rb">screenshot</a>(request) -> Berrycrawl::Types::ScrapeResponse</code></summary>
+<dl>
+<dd>
+#### 📝 Description
+<dl>
+<dd>
+<dl>
+<dd>
+Cookie banners, blocking overlays, chat widgets, and lazy loading are handled by default. Every cleanup pass can be controlled per request.
+</dd>
+</dl>
+</dd>
+</dl>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.screenshot(url: "https://example.com")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**block_ads:** `Internal::Types::Boolean` — Block common advertising and analytics requests
+</dd>
+</dl>
+<dl>
+<dd>
+**click_selector:** `String` — Click this CSS selector before capture
+</dd>
+</dl>
+<dl>
+<dd>
+**clip:** `Berrycrawl::Types::ScreenshotClipDto` — Capture an exact pixel rectangle instead of the page
+</dd>
+</dl>
+<dl>
+<dd>
+**color_scheme:** `Berrycrawl::Types::ScreenshotDtoColorScheme`
+</dd>
+</dl>
+<dl>
+<dd>
+**cookies:** `Internal::Types::Array[Berrycrawl::Types::ScreenshotCookieDto]` — Cookies to set before loading the page
+</dd>
+</dl>
+<dl>
+<dd>
+**delay:** `Integer` — Extra settling time after the page is ready, in milliseconds
+</dd>
+</dl>
+<dl>
+<dd>
+**device:** `Berrycrawl::Types::ScreenshotDtoDevice` — Named viewport preset
+</dd>
+</dl>
+<dl>
+<dd>
+**disable_animations:** `Internal::Types::Boolean`
+</dd>
+</dl>
+<dl>
+<dd>
+**format:** `Berrycrawl::Types::ScreenshotDtoFormat`
+</dd>
+</dl>
+<dl>
+<dd>
+**full_page:** `Internal::Types::Boolean` — Capture the complete page instead of only the viewport
+</dd>
+</dl>
+<dl>
+<dd>
+**full_page_algorithm:** `Berrycrawl::Types::ScreenshotDtoFullPageAlgorithm` — auto uses native capture for normal pages and stitched slices for very tall pages
+</dd>
+</dl>
+<dl>
+<dd>
+**headers:** `Internal::Types::Hash[String, Object]` — Headers sent while loading the page
+</dd>
+</dl>
+<dl>
+<dd>
+**hide_fixed_elements:** `Internal::Types::Boolean` — Show fixed/sticky UI once instead of repeating it in stitched captures
+</dd>
+</dl>
+<dl>
+<dd>
+**hide_selectors:** `Internal::Types::Array[String]` — Hide matching elements before capture
+</dd>
+</dl>
+<dl>
+<dd>
+**location:** `Berrycrawl::Types::ScreenshotLocationDto`
+</dd>
+</dl>
+<dl>
+<dd>
+**mask_color:** `String`
+</dd>
+</dl>
+<dl>
+<dd>
+**mask_selectors:** `Internal::Types::Array[String]` — Cover matching elements with a solid privacy mask
+</dd>
+</dl>
+<dl>
+<dd>
+**max_height:** `Integer` — Maximum full-page height. Prevents endless captures on infinite pages.
+</dd>
+</dl>
+<dl>
+<dd>
+**omit_background:** `Internal::Types::Boolean` — Use a transparent background where the page allows it
+</dd>
+</dl>
+<dl>
+<dd>
+**proxy:** `Berrycrawl::Types::ScreenshotDtoProxy` — Proxy mode
+</dd>
+</dl>
+<dl>
+<dd>
+**quality:** `Integer` — JPEG or WebP quality
+</dd>
+</dl>
+<dl>
+<dd>
+**reduced_motion:** `Internal::Types::Boolean`
+</dd>
+</dl>
+<dl>
+<dd>
+**remove_chat_widgets:** `Internal::Types::Boolean` — Hide common support and chat widgets
+</dd>
+</dl>
+<dl>
+<dd>
+**remove_cookie_banners:** `Internal::Types::Boolean` — Accept known consent dialogs, hide remaining cookie banners, and restore page scrolling
+</dd>
+</dl>
+<dl>
+<dd>
+**remove_overlays:** `Internal::Types::Boolean` — Remove newsletter gates, modal backdrops, and blocking overlays
+</dd>
+</dl>
+<dl>
+<dd>
+**response_format:** `Berrycrawl::Types::ScreenshotDtoResponseFormat` — Return a CDN URL or an inline data URL
+</dd>
+</dl>
+<dl>
+<dd>
+**scale:** `Berrycrawl::Types::ScreenshotDtoScale` — Capture at CSS pixel size or the emulated device pixel ratio
+</dd>
+</dl>
+<dl>
+<dd>
+**scroll_delay:** `Integer` — Pause between lazy-load scroll steps, in milliseconds
+</dd>
+</dl>
+<dl>
+<dd>
+**scroll_page:** `Internal::Types::Boolean` — Scroll through the page first so lazy content is loaded
+</dd>
+</dl>
+<dl>
+<dd>
+**selector:** `String` — Capture one element instead of the page
+</dd>
+</dl>
+<dl>
+<dd>
+**styles:** `Internal::Types::Array[String]` — CSS rules to apply before capture
+</dd>
+</dl>
+<dl>
+<dd>
+**timeout:** `Integer`
+</dd>
+</dl>
+<dl>
+<dd>
+**url:** `String` — Public webpage URL to capture
+</dd>
+</dl>
+<dl>
+<dd>
+**viewport:** `Berrycrawl::Types::ScreenshotViewportDto` — Custom viewport. Overrides the named device dimensions.
+</dd>
+</dl>
+<dl>
+<dd>
+**wait_for_selector:** `String` — Wait for this CSS selector before capture
+</dd>
+</dl>
+<dl>
+<dd>
+**wait_until:** `Berrycrawl::Types::ScreenshotDtoWaitUntil` — Page readiness milestone used before capture
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.<a href="/lib/Berrycrawl/client.rb">search</a>(request) -> Berrycrawl::Types::SearchResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.search(query: "machine learning tutorials")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**categories:** `Internal::Types::Array[String]` — Category filters
+</dd>
+</dl>
+<dl>
+<dd>
+**country:** `String` — Country code
+</dd>
+</dl>
+<dl>
+<dd>
+**limit:** `Integer` — Maximum number of results
+</dd>
+</dl>
+<dl>
+<dd>
+**location:** `String` — Location for geo-targeting
+</dd>
+</dl>
+<dl>
+<dd>
+**query:** `String` — Search query
+</dd>
+</dl>
+<dl>
+<dd>
+**sources:** `Internal::Types::Array[String]` — Source types to search
+</dd>
+</dl>
+<dl>
+<dd>
+**tbs:** `String` — Time-based filter (e.g., qdr:d for past day)
+</dd>
+</dl>
+<dl>
+<dd>
+**timeout:** `Integer` — Timeout for search operation in milliseconds
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+## Account
+<details><summary><code>client.account.<a href="/lib/Berrycrawl/account/client.rb">get</a>() -> Berrycrawl::Types::AccountResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.account.get
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Account::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+## Brand
+<details><summary><code>client.brand.<a href="/lib/Berrycrawl/brand/client.rb">retrieve</a>(request) -> Berrycrawl::Types::BrandResponse</code></summary>
+<dl>
+<dd>
+#### 📝 Description
+<dl>
+<dd>
+<dl>
+<dd>
+Send one website URL. BerryCrawl returns the brand identity found on that site.
+</dd>
+</dl>
+</dd>
+</dl>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.brand.retrieve(url: "https://stripe.com")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**refresh:** `Internal::Types::Boolean` — Ignore a cached profile and fetch the website again
+</dd>
+</dl>
+<dl>
+<dd>
+**timeout:** `Integer` — Maximum time to spend building the profile, in milliseconds
+</dd>
+</dl>
+<dl>
+<dd>
+**url:** `String` — The public website whose brand profile should be extracted
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Brand::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+## Jobs
+<details><summary><code>client.jobs.<a href="/lib/Berrycrawl/jobs/client.rb">list</a>() -> Berrycrawl::Types::ListJobsResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.jobs.list
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**type:** `Berrycrawl::Jobs::Types::ListJobsRequestType`
+</dd>
+</dl>
+<dl>
+<dd>
+**status:** `Berrycrawl::Jobs::Types::ListJobsRequestStatus`
+</dd>
+</dl>
+<dl>
+<dd>
+**page:** `Integer`
+</dd>
+</dl>
+<dl>
+<dd>
+**limit:** `Integer`
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Jobs::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.jobs.<a href="/lib/Berrycrawl/jobs/client.rb">get</a>(id:) -> Berrycrawl::Types::JobResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.jobs.get(id: "id")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**id:** `String`
+</dd>
+</dl>
+<dl>
+<dd>
+**page:** `Integer`
+</dd>
+</dl>
+<dl>
+<dd>
+**limit:** `Integer`
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Jobs::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.jobs.<a href="/lib/Berrycrawl/jobs/client.rb">cancel</a>(id:) -> Berrycrawl::Types::CancelJobResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.jobs.cancel(id: "id")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**id:** `String`
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Jobs::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+## Webhooks
+<details><summary><code>client.webhooks.<a href="/lib/Berrycrawl/webhooks/client.rb">list</a>() -> Berrycrawl::Types::ListWebhooksResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.webhooks.list
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Webhooks::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.webhooks.<a href="/lib/Berrycrawl/webhooks/client.rb">create</a>(request) -> Berrycrawl::Types::WebhookResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.webhooks.create(
+  events: %w[crawl.completed extract.failed],
+  url: "https://api.example.com/webhooks"
+)
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**events:** `Internal::Types::Array[String]` — Event types to subscribe to
+</dd>
+</dl>
+<dl>
+<dd>
+**url:** `String` — Webhook URL to send events to
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Webhooks::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.webhooks.<a href="/lib/Berrycrawl/webhooks/client.rb">get</a>(id:) -> Berrycrawl::Types::WebhookResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.webhooks.get(id: "id")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**id:** `String`
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Webhooks::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.webhooks.<a href="/lib/Berrycrawl/webhooks/client.rb">delete</a>(id:) -> Berrycrawl::Types::MessageResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.webhooks.delete(id: "id")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**id:** `String`
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Webhooks::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.webhooks.<a href="/lib/Berrycrawl/webhooks/client.rb">update</a>(id:, request) -> Berrycrawl::Types::WebhookResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.webhooks.update(id: "id")
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**id:** `String`
+</dd>
+</dl>
+<dl>
+<dd>
+**events:** `Internal::Types::Array[String]` — Event types to subscribe to
+</dd>
+</dl>
+<dl>
+<dd>
+**is_active:** `Internal::Types::Boolean` — Enable or disable webhook
+</dd>
+</dl>
+<dl>
+<dd>
+**url:** `String` — Webhook URL to send events to
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Webhooks::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>
+<details><summary><code>client.webhooks.<a href="/lib/Berrycrawl/webhooks/client.rb">test</a>(id:, request) -> Berrycrawl::Types::TestWebhookResponse</code></summary>
+<dl>
+<dd>
+#### 🔌 Usage
+<dl>
+<dd>
+<dl>
+<dd>
+```ruby
+client.webhooks.test(
+  id: "id",
+  event: "crawl.completed"
+)
+```
+</dd>
+</dl>
+</dd>
+</dl>
+#### ⚙️ Parameters
+<dl>
+<dd>
+<dl>
+<dd>
+**id:** `String`
+</dd>
+</dl>
+<dl>
+<dd>
+**event:** `String` — Event type to test
+</dd>
+</dl>
+<dl>
+<dd>
+**payload:** `Internal::Types::Hash[String, Object]` — Optional custom payload for testing
+</dd>
+</dl>
+<dl>
+<dd>
+**request_options:** `Berrycrawl::Webhooks::RequestOptions`
+</dd>
+</dl>
+</dd>
+</dl>
+</dd>
+</dl>
+</details>