farcasclaudiu/Flowise
1
0
Fork 0
mirror of https://github.com/farcasclaudiu/Flowise.git synced 2026-06-28 13:00:56 +03:00
Code Issues Packages Projects Releases Wiki Activity

Use selected links if available when scraping in cheerio, puppeteer, and playwright nodes

Browse Source
This commit is contained in:
Ilango
2024-01-19 14:25:04 +05:30
parent 43fa1166df
commit bfa26a72c4
3 changed files with 33 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/components/nodes/documentloaders/Cheerio/Cheerio.ts
+11 -1
View File
@@ -90,6 +90,7 @@ class Cheerio_DocumentLoaders implements INode {
const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
const metadata = nodeData.inputs?.metadata
const relativeLinksMethod = nodeData.inputs?.relativeLinksMethod as string
const selectedLinks = nodeData.inputs?.selectedLinks as string[]
let limit = nodeData.inputs?.limit as string
let url = nodeData.inputs?.url as string
@@ -127,13 +128,22 @@ class Cheerio_DocumentLoaders implements INode {
if (!limit) limit = '10'
else if (parseInt(limit) < 0) throw new Error('Limit cannot be less than 0')
const pages: string[] =
relativeLinksMethod === 'webCrawl' ? await webCrawl(url, parseInt(limit)) : await xmlScrape(url, parseInt(limit))
selectedLinks && selectedLinks.length > 0
? selectedLinks.slice(0, parseInt(limit))
: relativeLinksMethod === 'webCrawl'
? await webCrawl(url, parseInt(limit))
: await xmlScrape(url, parseInt(limit))
if (process.env.DEBUG === 'true') console.info(`pages: ${JSON.stringify(pages)}, length: ${pages.length}`)
if (!pages || pages.length === 0) throw new Error('No relative links found')
for (const page of pages) {
docs.push(...(await cheerioLoader(page)))
}
if (process.env.DEBUG === 'true') console.info(`Finish ${relativeLinksMethod}`)
} else if (selectedLinks && selectedLinks.length > 0) {
if (process.env.DEBUG === 'true') console.info(`pages: ${JSON.stringify(selectedLinks)}, length: ${selectedLinks.length}`)
for (const page of selectedLinks) {
docs.push(...(await cheerioLoader(page)))
}
} else {
docs = await cheerioLoader(url)
}
packages/components/nodes/documentloaders/Playwright/Playwright.ts
+11 -1
View File
@@ -118,6 +118,7 @@ class Playwright_DocumentLoaders implements INode {
const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
const metadata = nodeData.inputs?.metadata
const relativeLinksMethod = nodeData.inputs?.relativeLinksMethod as string
const selectedLinks = nodeData.inputs?.selectedLinks as string[]
let limit = nodeData.inputs?.limit as string
let waitUntilGoToOption = nodeData.inputs?.waitUntilGoToOption as 'load' | 'domcontentloaded' | 'networkidle' | 'commit' | undefined
let waitForSelector = nodeData.inputs?.waitForSelector as string
@@ -168,13 +169,22 @@ class Playwright_DocumentLoaders implements INode {
if (!limit) limit = '10'
else if (parseInt(limit) < 0) throw new Error('Limit cannot be less than 0')
const pages: string[] =
relativeLinksMethod === 'webCrawl' ? await webCrawl(url, parseInt(limit)) : await xmlScrape(url, parseInt(limit))
selectedLinks && selectedLinks.length > 0
? selectedLinks.slice(0, parseInt(limit))
: relativeLinksMethod === 'webCrawl'
? await webCrawl(url, parseInt(limit))
: await xmlScrape(url, parseInt(limit))
if (process.env.DEBUG === 'true') console.info(`pages: ${JSON.stringify(pages)}, length: ${pages.length}`)
if (!pages || pages.length === 0) throw new Error('No relative links found')
for (const page of pages) {
docs.push(...(await playwrightLoader(page)))
}
if (process.env.DEBUG === 'true') console.info(`Finish ${relativeLinksMethod}`)
} else if (selectedLinks && selectedLinks.length > 0) {
if (process.env.DEBUG === 'true') console.info(`pages: ${JSON.stringify(selectedLinks)}, length: ${selectedLinks.length}`)
for (const page of selectedLinks) {
docs.push(...(await playwrightLoader(page)))
}
} else {
docs = await playwrightLoader(url)
}
packages/components/nodes/documentloaders/Puppeteer/Puppeteer.ts
+11 -1
View File
@@ -119,6 +119,7 @@ class Puppeteer_DocumentLoaders implements INode {
const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
const metadata = nodeData.inputs?.metadata
const relativeLinksMethod = nodeData.inputs?.relativeLinksMethod as string
const selectedLinks = nodeData.inputs?.selectedLinks as string[]
let limit = nodeData.inputs?.limit as string
let waitUntilGoToOption = nodeData.inputs?.waitUntilGoToOption as PuppeteerLifeCycleEvent
let waitForSelector = nodeData.inputs?.waitForSelector as string
@@ -169,13 +170,22 @@ class Puppeteer_DocumentLoaders implements INode {
if (!limit) limit = '10'
else if (parseInt(limit) < 0) throw new Error('Limit cannot be less than 0')
const pages: string[] =
relativeLinksMethod === 'webCrawl' ? await webCrawl(url, parseInt(limit)) : await xmlScrape(url, parseInt(limit))
selectedLinks && selectedLinks.length > 0
? selectedLinks.slice(0, parseInt(limit))
: relativeLinksMethod === 'webCrawl'
? await webCrawl(url, parseInt(limit))
: await xmlScrape(url, parseInt(limit))
if (process.env.DEBUG === 'true') console.info(`pages: ${JSON.stringify(pages)}, length: ${pages.length}`)
if (!pages || pages.length === 0) throw new Error('No relative links found')
for (const page of pages) {
docs.push(...(await puppeteerLoader(page)))
}
if (process.env.DEBUG === 'true') console.info(`Finish ${relativeLinksMethod}`)
} else if (selectedLinks && selectedLinks.length > 0) {
if (process.env.DEBUG === 'true') console.info(`pages: ${JSON.stringify(selectedLinks)}, length: ${selectedLinks.length}`)
for (const page of selectedLinks) {
docs.push(...(await puppeteerLoader(page)))
}
} else {
docs = await puppeteerLoader(url)
}