dtamind-components
Version:
Apps integration for Dtamind. Contain Nodes and Credentials.
202 lines • 8.29 kB
JavaScript
;
Object.defineProperty(exports, "__esModule", { value: true });
const lodash_1 = require("lodash");
const utils_1 = require("../../../src/utils");
const apify_dataset_1 = require("@langchain/community/document_loaders/web/apify_dataset");
const documents_1 = require("@langchain/core/documents");
class ApifyWebsiteContentCrawler_DocumentLoaders {
constructor() {
this.label = 'Apify Website Content Crawler';
this.name = 'apifyWebsiteContentCrawler';
this.type = 'Document';
this.icon = 'apify-symbol-transparent.svg';
this.version = 3.0;
this.category = 'Document Loaders';
this.description = 'Load data from Apify Website Content Crawler';
this.baseClasses = [this.type];
this.credential = {
label: 'Connect Apify API',
name: 'credential',
type: 'credential',
credentialNames: ['apifyApi']
};
this.inputs = [
{
label: 'Text Splitter',
name: 'textSplitter',
type: 'TextSplitter',
optional: true
},
{
label: 'Start URLs',
name: 'urls',
type: 'string',
description: 'One or more URLs of pages where the crawler will start, separated by commas.',
placeholder: 'https://js.langchain.com/docs/'
},
{
label: 'Crawler type',
type: 'options',
name: 'crawlerType',
options: [
{
label: 'Headless web browser (Chrome+Playwright)',
name: 'playwright:chrome'
},
{
label: 'Stealthy web browser (Firefox+Playwright)',
name: 'playwright:firefox'
},
{
label: 'Raw HTTP client (Cheerio)',
name: 'cheerio'
},
{
label: 'Raw HTTP client with JavaScript execution (JSDOM) [experimental]',
name: 'jsdom'
}
],
description: 'Select the crawling engine, see <a target="_blank" href="https://apify.com/apify/website-content-crawler#crawling">documentation</a> for additional information.',
default: 'playwright:firefox'
},
{
label: 'Max crawling depth',
name: 'maxCrawlDepth',
type: 'number',
optional: true,
default: 1,
additionalParams: true
},
{
label: 'Max crawl pages',
name: 'maxCrawlPages',
type: 'number',
optional: true,
default: 3,
additionalParams: true
},
{
label: 'Additional input',
name: 'additionalInput',
type: 'json',
default: JSON.stringify({}),
description: 'For additional input options for the crawler see <a target="_blank" href="https://apify.com/apify/website-content-crawler/input-schema">documentation</a>.',
optional: true,
additionalParams: true
},
{
label: 'Additional Metadata',
name: 'metadata',
type: 'json',
description: 'Additional metadata to be added to the extracted documents',
optional: true,
additionalParams: true
},
{
label: 'Omit Metadata Keys',
name: 'omitMetadataKeys',
type: 'string',
rows: 4,
description: 'Each document loader comes with a default set of metadata keys that are extracted from the document. You can use this field to omit some of the default metadata keys. The value should be a list of keys, seperated by comma. Use * to omit all metadata keys execept the ones you specify in the Additional Metadata field',
placeholder: 'key1, key2, key3.nestedKey1',
optional: true,
additionalParams: true
}
];
this.outputs = [
{
label: 'Document',
name: 'document',
description: 'Array of document objects containing metadata and pageContent',
baseClasses: [...this.baseClasses, 'json']
},
{
label: 'Text',
name: 'text',
description: 'Concatenated string from pageContent of documents',
baseClasses: ['string', 'json']
}
];
}
async init(nodeData, _, options) {
const textSplitter = nodeData.inputs?.textSplitter;
const metadata = nodeData.inputs?.metadata;
const _omitMetadataKeys = nodeData.inputs?.omitMetadataKeys;
const output = nodeData.outputs?.output;
let omitMetadataKeys = [];
if (_omitMetadataKeys) {
omitMetadataKeys = _omitMetadataKeys.split(',').map((key) => key.trim());
}
// Get input options and merge with additional input
const urls = nodeData.inputs?.urls;
const crawlerType = nodeData.inputs?.crawlerType;
const maxCrawlDepth = nodeData.inputs?.maxCrawlDepth;
const maxCrawlPages = nodeData.inputs?.maxCrawlPages;
const additionalInput = typeof nodeData.inputs?.additionalInput === 'object'
? nodeData.inputs?.additionalInput
: JSON.parse(nodeData.inputs?.additionalInput);
const input = {
startUrls: urls.split(',').map((url) => ({ url: url.trim() })),
crawlerType,
maxCrawlDepth: parseInt(maxCrawlDepth, 10),
maxCrawlPages: parseInt(maxCrawlPages, 10),
...additionalInput
};
// Get Apify API token from credential data
const credentialData = await (0, utils_1.getCredentialData)(nodeData.credential ?? '', options);
const apifyApiToken = (0, utils_1.getCredentialParam)('apifyApiToken', credentialData, nodeData);
const loader = await apify_dataset_1.ApifyDatasetLoader.fromActorCall('apify/website-content-crawler', input, {
datasetMappingFunction: (item) => new documents_1.Document({
pageContent: (item.text || ''),
metadata: { source: item.url }
}),
clientOptions: {
token: apifyApiToken
}
});
let docs = [];
if (textSplitter) {
docs = await loader.load();
docs = await textSplitter.splitDocuments(docs);
}
else {
docs = await loader.load();
}
if (metadata) {
const parsedMetadata = typeof metadata === 'object' ? metadata : JSON.parse(metadata);
docs = docs.map((doc) => ({
...doc,
metadata: _omitMetadataKeys === '*'
? {
...parsedMetadata
}
: (0, lodash_1.omit)({
...doc.metadata,
...parsedMetadata
}, omitMetadataKeys)
}));
}
else {
docs = docs.map((doc) => ({
...doc,
metadata: _omitMetadataKeys === '*'
? {}
: (0, lodash_1.omit)({
...doc.metadata
}, omitMetadataKeys)
}));
}
if (output === 'document') {
return docs;
}
else {
let finaltext = '';
for (const doc of docs) {
finaltext += `${doc.pageContent}\n`;
}
return (0, utils_1.handleEscapeCharacters)(finaltext, false);
}
}
}
module.exports = { nodeClass: ApifyWebsiteContentCrawler_DocumentLoaders };
//# sourceMappingURL=ApifyWebsiteContentCrawler.js.map