Skip to content

fix: check deny list in webscrappers #6559

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
0xi4o wants to merge 2 commits into
base: main
Choose a base branch
from
+70 −0
Open

fix: check deny list in webscrappers #6559

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
86c0c26
fix: check deny list in webscrappers
0xi4o Jun 24, 2026
d7744ac
fix: review feedback
0xi4o Jul 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions packages/components/nodes/documentloaders/Cheerio/Cheerio.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@ import { parse } from 'css-what'
import { SelectorType } from 'cheerio'
import { ICommonObject, INodeOutputsValue, IDocument, INode, INodeData, INodeParams } from '../../../src/Interface'
import { handleEscapeCharacters, webCrawl, xmlScrape } from '../../../src/utils'
import { checkDenyList, secureFetch } from '../../../src/httpSecurity'

class Cheerio_DocumentLoaders implements INode {
label: string
Expand Down Expand Up @@ -148,13 +149,23 @@ class Cheerio_DocumentLoaders implements INode {

async function cheerioLoader(url: string): Promise<any> {
try {
await checkDenyList(url)
let docs: IDocument[] = []
if (url.endsWith('.pdf')) {
if (process.env.DEBUG === 'true')
options.logger.info(`[${orgId}]: CheerioWebBaseLoader does not support PDF files: ${url}`)
return docs
}
const loader = new CheerioWebBaseLoader(url, params)
loader.scrape = async () => {
const { load } = await CheerioWebBaseLoader.imports()
const response = await secureFetch(url, {
signal: loader.timeout ? AbortSignal.timeout(loader.timeout) : undefined,
headers: loader.headers
} as any)
const html = loader.textDecoder?.decode(await response.arrayBuffer()) ?? (await response.text())
return load(html)
}
if (textSplitter) {
docs = await loader.load()
docs = await textSplitter.splitDocuments(docs)
Expand Down
28 changes: 28 additions & 0 deletions packages/components/nodes/documentloaders/Playwright/Playwright.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ import { test } from 'linkifyjs'
import { omit } from 'lodash'
import { handleEscapeCharacters, INodeOutputsValue, webCrawl, xmlScrape } from '../../../src'
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { checkDenyList } from '../../../src/httpSecurity'

class Playwright_DocumentLoaders implements INode {
label: string
Expand Down Expand Up @@ -189,6 +190,7 @@ class Playwright_DocumentLoaders implements INode {

async function playwrightLoader(url: string): Promise<Document[] | undefined> {
try {
await checkDenyList(url)
Comment thread
0xi4o marked this conversation as resolved.
let docs = []

const executablePath = process.env.PLAYWRIGHT_EXECUTABLE_PATH
Expand Down Expand Up @@ -224,6 +226,32 @@ class Playwright_DocumentLoaders implements INode {
}
}
const loader = new PlaywrightWebBaseLoader(url, config)
loader.scrape = async (): Promise<string> => {
const { chromium } = await PlaywrightWebBaseLoader.imports()
const browser = await chromium.launch({
headless: true,
...config.launchOptions
})
try {
const page = await browser.newPage()
await page.route('**', async (route, request) => {
try {
await checkDenyList(request.url())
await route.continue()
} catch {
await route.abort('blockedbyclient')
}
})
const response = await page.goto(url, {
timeout: 180000,
waitUntil: 'domcontentloaded',
...config.gotoOptions
})
return config.evaluate ? await config.evaluate(page, browser, response) : await page.content()
} finally {
await browser.close()
}
}
if (textSplitter) {
docs = await loader.load()
docs = await textSplitter.splitDocuments(docs)
Expand Down
31 changes: 31 additions & 0 deletions packages/components/nodes/documentloaders/Puppeteer/Puppeteer.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@ import { omit } from 'lodash'
import { PuppeteerLifeCycleEvent } from 'puppeteer'
import { handleEscapeCharacters, INodeOutputsValue, webCrawl, xmlScrape } from '../../../src'
import { ICommonObject, INode, INodeData, INodeParams } from '../../../src/Interface'
import { checkDenyList } from '../../../src/httpSecurity'

class Puppeteer_DocumentLoaders implements INode {
label: string
Expand Down Expand Up @@ -180,6 +181,7 @@ class Puppeteer_DocumentLoaders implements INode {

async function puppeteerLoader(url: string): Promise<Document[] | undefined> {
try {
await checkDenyList(url)
Comment thread
0xi4o marked this conversation as resolved.
let docs: Document[] = []

const executablePath = process.env.PUPPETEER_EXECUTABLE_PATH
Expand Down Expand Up @@ -215,6 +217,35 @@ class Puppeteer_DocumentLoaders implements INode {
}
}
const loader = new PuppeteerWebBaseLoader(url, config)
loader.scrape = async (): Promise<string> => {
const { launch } = await PuppeteerWebBaseLoader.imports()
const browser = await launch({
headless: true,
defaultViewport: null,
ignoreDefaultArgs: ['--disable-extensions'],
...config.launchOptions
})
try {
const page = await browser.newPage()
await page.setRequestInterception(true)
page.on('request', async (interceptedRequest) => {
try {
await checkDenyList(interceptedRequest.url())
await interceptedRequest.continue()
} catch {
await interceptedRequest.abort('blockedbyclient')
}
})
await page.goto(url, {
timeout: 180000,
waitUntil: 'domcontentloaded',
...config.gotoOptions
})
return config.evaluate ? await config.evaluate(page, browser) : await page.evaluate(() => document.body.innerHTML)
} finally {
await browser.close()
}
}
if (textSplitter) {
docs = await loader.load()
docs = await textSplitter.splitDocuments(docs)
Expand Down
Loading