shovel/com.earthapp.shovel

Package-level declarations

Types

Document

class Document

Represents an HTML document.

Element

class Element

Represents an HTML element.

Properties

engine

actual val engine: HttpClientEngine

Functions

clearCache

fun clearCache()

Clears the document cache.

closeClient

fun closeClient()

Closes the client. This should be called when the API is no longer needed.

fetch

@JvmOverloads

suspend fun fetch(url: String, request: HttpRequestBuilder.() -> Unit = {}): Document

Fetches a document from the given URL.

fetchBytes

@JvmOverloads

suspend fun String.fetchBytes(request: HttpRequestBuilder.() -> Unit = {}): ByteArray

Fetches the bytes from the given URL.

fetchBytesOrNull

@JvmOverloads

suspend fun String.fetchBytesOrNull(request: HttpRequestBuilder.() -> Unit = {}): ByteArray?

Fetches the bytes from the given URL, returning null if an error occurs.

fetchDocument

@JvmOverloads

suspend fun String.fetchDocument(request: HttpRequestBuilder.() -> Unit = {}): Document

Fetches a document from the given URL.

fetchDocumentOrNull

@JvmOverloads

suspend fun String.fetchDocumentOrNull(request: HttpRequestBuilder.() -> Unit = {}): Document?

Fetches a document from the given URL, returning null if an error occurs.

fetchText

@JvmOverloads

suspend fun String.fetchText(request: HttpRequestBuilder.() -> Unit = {}): String

Fetches the text content from the given URL.

fetchTextOrNull

@JvmOverloads

suspend fun String.fetchTextOrNull(request: HttpRequestBuilder.() -> Unit = {}): String?

Fetches the text content from the given URL, returning null if an error occurs.

getBodyText

fun Document.getBodyText(): String

Gets the full text content of the document's body.

getCanonicalUrl

fun Document.getCanonicalUrl(): String?

Gets the canonical URL of the document based on the <link rel="canonical"> tag.

getCharset

fun Document.getCharset(): String?

Gets the charset of the document based on the <meta charset> or <meta http-equiv="Content-Type"> tag.

getDescription

fun Document.getDescription(): String?

Gets the description of the document based on the <meta name="description"> tag.

getElementById

fun Document.getElementById(id: String): Element?

Gets the first element with the specified ID.

fun Element.getElementById(id: String): Element?

Gets the first element with the specified ID within the element.

getElementsByClassName

fun Document.getElementsByClassName(className: String): List<Element>

Gets all elements with the specified class name.

fun Element.getElementsByClassName(className: String): List<Element>

Gets all elements with the specified class name within the element.

getFaviconUrl

fun Document.getFaviconUrl(): String?

Gets the favicon URL from the document. This checks for common favicon link types such as:

getIconLinks

fun Document.getIconLinks(): List<String>

Gets the icon links from the document. This includes both <link rel="icon"> and <link rel="shortcut icon">.

getLanguage

fun Document.getLanguage(): String?

Gets the language of the document. This checks for the <html lang="..."> attribute first, then falls back to the <meta http-equiv="Content-Language"> tag.

getMainText

fun Document.getMainText(): String

Gets the main text content of the document. This is typically the content inside the <main> tag or the body if no main tag exists.

getOpenGraphMetadata

fun Document.getOpenGraphMetadata(): Map<String, String>

Gets the Open Graph metadata from the document.

getStyleSheets

fun Document.getStyleSheets(): List<String>

Gets the stylesheets linked in the document. This includes <link rel='stylesheet'> tags.

getTitle

fun Document.getTitle(): String?

Gets the title of the document.

getTwitterCardMetadata

fun Document.getTwitterCardMetadata(): Map<String, String>

Gets the Twitter Card metadata from the document.

getViewport

fun Document.getViewport(): String?

Gets the viewport settings of the document based on the <meta name="viewport"> tag.

inputValue

fun Document.inputValue(name: String): String?

Gets the value of an input element.

fun Element.inputValue(name: String): String?

Gets the value of an input element within the element.

querySelector

fun Document.querySelector(selector: String, filter: (Element) -> Boolean = { true }): Element?

Gets the first element that matches the specified CSS selector.

fun Element.querySelector(selector: String, filter: (Element) -> Boolean = { true }): Element?

Gets the first element that matches the specified CSS selector within the element.

querySelectorAll

actual fun Document.querySelectorAll(selector: String): List<Element>

actual fun Element.querySelectorAll(selector: String): List<Element>

actual fun Document.querySelectorAll(selector: String): List<Element>

actual fun Element.querySelectorAll(selector: String): List<Element>

expect fun Document.querySelectorAll(selector: String): List<Element>

Gets all elements that match the specified CSS selector.

expect fun Element.querySelectorAll(selector: String): List<Element>

Gets all elements that match the specified CSS selector within the element.

actual fun Document.querySelectorAll(selector: String): List<Element>

actual fun Element.querySelectorAll(selector: String): List<Element>

actual fun Document.querySelectorAll(selector: String): List<Element>

actual fun Element.querySelectorAll(selector: String): List<Element>

actual fun Document.querySelectorAll(selector: String): List<Element>

actual fun Element.querySelectorAll(selector: String): List<Element>

transformClassName

fun <T> Document.transformClassName(className: String, transformer: (List<Element>) -> T): T

Transforms a class name into an object.

transformId

fun <T> Document.transformId(id: String, transformer: (Element) -> T): T

Transforms an ID into an object.

transformQuerySelector

fun <T> Document.transformQuerySelector(selector: String, transformer: (Element) -> T): T

Transforms a query selector into an object.

transformQuerySelectorAll

fun <T> Document.transformQuerySelectorAll(selector: String, transformer: (List<Element>) -> T): T

Transforms a query selector into an object.