Ctrl K

Page HTML by URL

Published Nov 5, 2024

Returns the full HTML content of a webpage specified by the URL. The response is in plain text. Proxies and Chromium JavaScript rendering are used for page retrieval and processing.

Script webscrapingai Verified

Use in Windmill

The script

Submitted by hugo697 Bun

Verified 581 days ago

All edits

Permalink

//native
type Webscrapingai = {
	apiKey: string
}
/**
 * Page HTML by URL
 * Returns the full HTML content of a webpage specified by the URL. The response is in plain text. Proxies and Chromium JavaScript rendering are used for page retrieval and processing.
 */
export async function main(
	auth: Webscrapingai,
	url: string | undefined,
	headers: any,
	timeout: string | undefined,
	js: string | undefined,
	js_timeout: string | undefined,
	wait_for: string | undefined,
	proxy: 'datacenter' | 'residential' | undefined,
	country: 'us' | 'gb' | 'de' | 'it' | 'fr' | 'ca' | 'es' | 'ru' | 'jp' | 'kr' | 'in' | undefined,
	custom_proxy: string | undefined,
	device: 'desktop' | 'mobile' | 'tablet' | undefined,
	error_on_404: string | undefined,
	error_on_redirect: string | undefined,
	js_script: string | undefined,
	return_script_result: string | undefined,
	format: 'json' | 'text' | undefined
) {
	const url_ = new URL(`https://api.webscraping.ai/html`)

	url_.searchParams.append('api_key', auth.apiKey)

	for (const [k, v] of [
		['url', url],
		['timeout', timeout],
		['js', js],
		['js_timeout', js_timeout],
		['wait_for', wait_for],
		['proxy', proxy],
		['country', country],
		['custom_proxy', custom_proxy],
		['device', device],
		['error_on_404', error_on_404],
		['error_on_redirect', error_on_redirect],
		['js_script', js_script],
		['return_script_result', return_script_result],
		['format', format]
	]) {
		if (v !== undefined && v !== '' && k !== undefined) {
			url_.searchParams.append(k, v)
		}
	}
	encodeParams({ headers }).forEach((v, k) => {
		if (v !== undefined && v !== '') {
			url_.searchParams.append(k, v)
		}
	})
	const response = await fetch(url_, {
		method: 'GET',
		body: undefined
	})
	if (!response.ok) {
		const text = await response.text()
		throw new Error(`${response.status} ${text}`)
	}
	return await response.text()
}

function encodeParams(o: any) {
	function iter(o: any, path: string) {
		if (Array.isArray(o)) {
			o.forEach(function (a) {
				iter(a, path + '[]')
			})
			return
		}
		if (o !== null && typeof o === 'object') {
			Object.keys(o).forEach(function (k) {
				iter(o[k], path + '[' + k + ']')
			})
			return
		}
		data.push(path + '=' + o)
	}
	const data: string[] = []
	Object.keys(o).forEach(function (k) {
		if (o[k] !== undefined) {
			iter(o[k], k)
		}
	})
	return new URLSearchParams(data.join('&'))
}


`1`	`//native`
`2`	`type Webscrapingai = {`
`3`	`apiKey: string`
`4`	`}`
`5`	`/**`
`6`	`* Page HTML by URL`
`7`	`* Returns the full HTML content of a webpage specified by the URL. The response is in plain text. Proxies and Chromium JavaScript rendering are used for page retrieval and processing.`
`8`	`*/`
`9`	`export async function main(`
`10`	`auth: Webscrapingai,`
`11`	`url: string \| undefined,`
`12`	`headers: any,`
`13`	`timeout: string \| undefined,`
`14`	`js: string \| undefined,`
`15`	`js_timeout: string \| undefined,`
`16`	`wait_for: string \| undefined,`
`17`	`proxy: 'datacenter' \| 'residential' \| undefined,`
`18`	`country: 'us' \| 'gb' \| 'de' \| 'it' \| 'fr' \| 'ca' \| 'es' \| 'ru' \| 'jp' \| 'kr' \| 'in' \| undefined,`
`19`	`custom_proxy: string \| undefined,`
`20`	`device: 'desktop' \| 'mobile' \| 'tablet' \| undefined,`
`21`	`error_on_404: string \| undefined,`
`22`	`error_on_redirect: string \| undefined,`
`23`	`js_script: string \| undefined,`
`24`	`return_script_result: string \| undefined,`
`25`	`format: 'json' \| 'text' \| undefined`
`26`	`) {`
`27`	const url_ = new URL(`https://api.webscraping.ai/html`)
`28`
`29`	`url_.searchParams.append('api_key', auth.apiKey)`
`30`
`31`	`for (const [k, v] of [`
`32`	`['url', url],`
`33`	`['timeout', timeout],`
`34`	`['js', js],`
`35`	`['js_timeout', js_timeout],`
`36`	`['wait_for', wait_for],`
`37`	`['proxy', proxy],`
`38`	`['country', country],`
`39`	`['custom_proxy', custom_proxy],`
`40`	`['device', device],`
`41`	`['error_on_404', error_on_404],`
`42`	`['error_on_redirect', error_on_redirect],`
`43`	`['js_script', js_script],`
`44`	`['return_script_result', return_script_result],`
`45`	`['format', format]`
`46`	`]) {`
`47`	`if (v !== undefined && v !== '' && k !== undefined) {`
`48`	`url_.searchParams.append(k, v)`
`49`	`}`
`50`	`}`
`51`	`encodeParams({ headers }).forEach((v, k) => {`
`52`	`if (v !== undefined && v !== '') {`
`53`	`url_.searchParams.append(k, v)`
`54`	`}`
`55`	`})`
`56`	`const response = await fetch(url_, {`
`57`	`method: 'GET',`
`58`	`body: undefined`
`59`	`})`
`60`	`if (!response.ok) {`
`61`	`const text = await response.text()`
`62`	throw new Error(`${response.status} ${text}`)
`63`	`}`
`64`	`return await response.text()`
`65`	`}`
`66`
`67`	`function encodeParams(o: any) {`
`68`	`function iter(o: any, path: string) {`
`69`	`if (Array.isArray(o)) {`
`70`	`o.forEach(function (a) {`
`71`	`iter(a, path + '[]')`
`72`	`})`
`73`	`return`
`74`	`}`
`75`	`if (o !== null && typeof o === 'object') {`
`76`	`Object.keys(o).forEach(function (k) {`
`77`	`iter(o[k], path + '[' + k + ']')`
`78`	`})`
`79`	`return`
`80`	`}`
`81`	`data.push(path + '=' + o)`
`82`	`}`
`83`	`const data: string[] = []`
`84`	`Object.keys(o).forEach(function (k) {`
`85`	`if (o[k] !== undefined) {`
`86`	`iter(o[k], k)`
`87`	`}`
`88`	`})`
`89`	`return new URLSearchParams(data.join('&'))`
`90`	`}`
`91`