File size: 3,603 Bytes
4114d85 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
import { INode, INodeData, INodeParams } from '../../../src/Interface'
import { TextSplitter } from 'langchain/text_splitter'
import { CheerioWebBaseLoader } from 'langchain/document_loaders/web/cheerio'
import { test } from 'linkifyjs'
import { getAvailableURLs } from '../../../src'
class Cheerio_DocumentLoaders implements INode {
label: string
name: string
description: string
type: string
icon: string
category: string
baseClasses: string[]
inputs: INodeParams[]
constructor() {
this.label = 'Cheerio Web Scraper'
this.name = 'cheerioWebScraper'
this.type = 'Document'
this.icon = 'cheerio.svg'
this.category = 'Document Loaders'
this.description = `Load data from webpages`
this.baseClasses = [this.type]
this.inputs = [
{
label: 'URL',
name: 'url',
type: 'string'
},
{
label: 'Text Splitter',
name: 'textSplitter',
type: 'TextSplitter',
optional: true
},
{
label: 'Web Scrap for Relative Links',
name: 'webScrap',
type: 'boolean',
optional: true,
additionalParams: true
},
{
label: 'Web Scrap Links Limit',
name: 'limit',
type: 'number',
default: 10,
optional: true,
additionalParams: true
},
{
label: 'Metadata',
name: 'metadata',
type: 'json',
optional: true,
additionalParams: true
}
]
}
async init(nodeData: INodeData): Promise<any> {
const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
const metadata = nodeData.inputs?.metadata
const webScrap = nodeData.inputs?.webScrap as boolean
let limit = nodeData.inputs?.limit as string
let url = nodeData.inputs?.url as string
url = url.trim()
if (!test(url)) {
throw new Error('Invalid URL')
}
const cheerioLoader = async (url: string): Promise<any> => {
let docs = []
const loader = new CheerioWebBaseLoader(url)
if (textSplitter) {
docs = await loader.loadAndSplit(textSplitter)
} else {
docs = await loader.load()
}
return docs
}
let availableUrls: string[]
let docs = []
if (webScrap) {
if (!limit) limit = '10'
availableUrls = await getAvailableURLs(url, parseInt(limit))
for (let i = 0; i < availableUrls.length; i++) {
docs.push(...(await cheerioLoader(availableUrls[i])))
}
} else {
docs = await cheerioLoader(url)
}
if (metadata) {
const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata)
let finaldocs = []
for (const doc of docs) {
const newdoc = {
...doc,
metadata: {
...doc.metadata,
...parsedMetadata
}
}
finaldocs.push(newdoc)
}
return finaldocs
}
return docs
}
}
module.exports = { nodeClass: Cheerio_DocumentLoaders }
|