add cheerio web scraper

packages/components/nodes/documentloaders/Cheerio/Cheerio.ts

@@ -0,0 +1,64 @@
+import { INode, INodeData, INodeParams } from '../../../src/Interface'
+import { TextSplitter } from 'langchain/text_splitter'
+import { CheerioWebBaseLoader } from 'langchain/document_loaders/web/cheerio'
+
+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
+            }
+        ]
+    }
+
+    async init(nodeData: INodeData): Promise<any> {
+        const textSplitter = nodeData.inputs?.textSplitter as TextSplitter
+        let url = nodeData.inputs?.url as string
+
+        var urlPattern = new RegExp(
+            '^(https?:\\/\\/)?' + // validate protocol
+                '((([a-z\\d]([a-z\\d-]*[a-z\\d])*)\\.)+[a-z]{2,}|' + // validate domain name
+                '((\\d{1,3}\\.){3}\\d{1,3}))' + // validate OR ip (v4) address
+                '(\\:\\d+)?(\\/[-a-z\\d%_.~+]*)*' + // validate port and path
+                '(\\?[;&a-z\\d%_.~+=-]*)?' + // validate query string
+                '(\\#[-a-z\\d_]*)?$',
+            'i'
+        ) // validate fragment locator
+
+        const loader = new CheerioWebBaseLoader(urlPattern.test(url.trim()) ? url.trim() : '')
+
+        if (textSplitter) {
+            const docs = await loader.loadAndSplit(textSplitter)
+            return docs
+        } else {
+            const docs = await loader.load()
+            return docs
+        }
+    }
+}
+
+module.exports = { nodeClass: Cheerio_DocumentLoaders }

packages/components/nodes/documentloaders/Cheerio/cheerio.svg

@@ -0,0 +1,5 @@
+<svg xmlns="http://www.w3.org/2000/svg" class="icon icon-tabler icon-tabler-circle-letter-c" width="24" height="24" viewBox="0 0 24 24" stroke-width="2" stroke="currentColor" fill="none" stroke-linecap="round" stroke-linejoin="round">
+   <path stroke="none" d="M0 0h24v24H0z" fill="none"></path>
+   <path d="M12 12m-9 0a9 9 0 1 0 18 0a9 9 0 1 0 -18 0"></path>
+   <path d="M14 10a2 2 0 1 0 -4 0v4a2 2 0 1 0 4 0"></path>
+</svg>

packages/components/package.json

@@ -20,6 +20,7 @@
         "@huggingface/inference": "^1.6.3",
         "@pinecone-database/pinecone": "^0.0.12",
         "axios": "^0.27.2",
+        "cheerio": "^1.0.0-rc.12",
         "chromadb": "^1.3.1",
         "d3-dsv": "2",
         "dotenv": "^16.0.0",