n8n-nodes-parse-pdf/dist/nodes/ParsePdf/actions/parsePdf.js

Extract text, tables, and structured data from PDF files using PDF API Hub

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.description = void 0;
exports.execute = execute;
const helpers_1 = require("../helpers");
exports.description = [
    {
        displayName: 'Input Type',
        name: 'parse_input_type',
        type: 'options',
        options: [
            { name: 'URL (Default)', value: 'url' },
            { name: 'File (Binary)', value: 'file' },
        ],
        default: 'url',
        description: 'How to provide the PDF to parse',
        displayOptions: {
            show: {
                operation: ['parsePdf'],
            },
        },
    },
    {
        displayName: 'PDF URL',
        name: 'parse_url',
        type: 'string',
        default: '',
        description: 'URL of the PDF to parse',
        placeholder: 'https://pdfapihub.com/sample.pdf',
        displayOptions: {
            show: {
                operation: ['parsePdf'],
                parse_input_type: ['url'],
            },
        },
    },
    {
        displayName: 'Binary Property Name',
        name: 'parse_file_binary_property',
        type: 'string',
        default: 'data',
        description: 'Binary property containing the PDF file',
        displayOptions: {
            show: {
                operation: ['parsePdf'],
                parse_input_type: ['file'],
            },
        },
    },
    {
        displayName: 'Parse Mode',
        name: 'parse_mode',
        type: 'options',
        options: [
            { name: 'Text Only (Default)', value: 'text', description: 'Extract text only' },
            { name: 'Layout', value: 'layout', description: 'Text + text blocks with bounding boxes' },
            { name: 'Tables', value: 'tables', description: 'Text + table blocks' },
            { name: 'Full', value: 'full', description: 'Text + blocks + tables + images' },
        ],
        default: 'text',
        description: 'What to extract from the PDF',
        displayOptions: {
            show: {
                operation: ['parsePdf'],
            },
        },
    },
    {
        displayName: 'Pages',
        name: 'parse_pages',
        type: 'string',
        default: 'all',
        description: 'Page selection: "all" or a range like "1-3" or single page like "2"',
        displayOptions: {
            show: {
                operation: ['parsePdf'],
            },
        },
    },
];
async function execute(index, returnData) {
    const parseInputType = this.getNodeParameter('parse_input_type', index);
    const pdfUrl = this.getNodeParameter('parse_url', index, '');
    const mode = this.getNodeParameter('parse_mode', index);
    const pages = this.getNodeParameter('parse_pages', index);
    const body = { mode, pages };
    if (parseInputType === 'url') {
        body.url = (0, helpers_1.normalizeUrl)(pdfUrl);
    }
    const requestOptions = parseInputType === 'file'
        ? await helpers_1.createSingleFileMultipart.call(this, index, this.getNodeParameter('parse_file_binary_property', index), body)
        : { body, json: true };
    const responseData = await this.helpers.httpRequestWithAuthentication.call(this, 'pdfapihubApi', {
        method: 'POST',
        url: 'https://pdfapihub.com/api/v1/pdf/parse',
        ...requestOptions,
        returnFullResponse: true,
        ignoreHttpStatusErrors: true,
    });
    (0, helpers_1.checkApiResponse)(this, responseData.statusCode, responseData.body, index);
    returnData.push((0, helpers_1.parseJsonResponseBody)(responseData.body, index));
}
//# sourceMappingURL=parsePdf.js.map