Class ExtractPDFJob

A job that extracts PDF elements such as text, images, tables in a structured format from a PDF.

Example

Sample Usage:

        const readStream = fs.createReadStream("<SOURCE_PATH>");

        const credentials = new ServicePrincipalCredentials({
            clientId: process.env.PDF_SERVICES_CLIENT_ID,
            clientSecret: process.env.PDF_SERVICES_CLIENT_SECRET
        });

        const pdfServices = new PDFServices({credentials});

        const inputAsset = await pdfServices.upload({
            readStream,
            mimeType: MimeType.PDF
        });

        const params = new ExtractPDFParams({
            elementsToExtract: [ExtractElementType.TEXT]
        });

        const job = new ExtractPDFJob({inputAsset, params});

        const pollingURL = await pdfServices.submit({job});

        const pdfServicesResponse = await pdfServices.getJobResult({
            pollingURL,
            resultType: ExtractPDFResult
        });

        const resultAsset = pdfServicesResponse.result.resource;
        const streamAsset = await pdfServices.getContent({asset: resultAsset});
Copy