Google Cloud Vision APIでPDFにOCRをかけてみた

// Sample vision-quickstart uses the Google Cloud Vision API to label an image.
package main

import (
	"context"
	"fmt"
	"os"
    "io"

	vision "cloud.google.com/go/vision/apiv1"
    visionpb "google.golang.org/genproto/googleapis/cloud/vision/v1"
)

// detectAsyncDocument performs Optical Character Recognition (OCR) on a
// PDF file stored in GCS.
func detectAsyncDocumentURI(w io.Writer, gcsSourceURI, gcsDestinationURI string) error {
	ctx := context.Background()

	client, err := vision.NewImageAnnotatorClient(ctx)
	if err != nil {
		return err
	}

	request := &visionpb.AsyncBatchAnnotateFilesRequest{
		Requests: []*visionpb.AsyncAnnotateFileRequest{
			{
				Features: []*visionpb.Feature{
					{
						Type: visionpb.Feature_DOCUMENT_TEXT_DETECTION,
					},
				},
				InputConfig: &visionpb.InputConfig{
					GcsSource: &visionpb.GcsSource{Uri: gcsSourceURI},
					// Supported MimeTypes are: "application/pdf" and "image/tiff".
					MimeType: "application/pdf",
				},
				OutputConfig: &visionpb.OutputConfig{
					GcsDestination: &visionpb.GcsDestination{Uri: gcsDestinationURI},
					// How many pages should be grouped into each json output file.
					BatchSize: 2,
				},
			},
		},
	}

	operation, err := client.AsyncBatchAnnotateFiles(ctx, request)
	if err != nil {
		return err
	}

	fmt.Fprintf(w, "Waiting for the operation to finish.")

	resp, err := operation.Wait(ctx)
	if err != nil {
		return err
	}

	fmt.Fprintf(w, "%v", resp)

	return nil
}

func main() {

	var w io.Writer
	w = os.Stdout

	src_uri := "gs://path/to/pdf/test.pdf"
	dst_uri := "gs://path/to/result.json"

	detectAsyncDocumentURI(w, src_uri, dst_uri)
}