Пример #1
0
        static void RecognizePdf2SearchableFromContent(Configuration conf)
        {
            string name = "TheCall.pdf";

            using (FileStream fs = File.OpenRead(name))
            {
                OcrApi api     = new OcrApi(conf);
                var    request = new OCRRequestData()
                {
                    DsrMode = DsrMode.NoDsrNoFilter, ResultType = ResultType.Pdf, Language = LanguageEnum.Arabic
                };
                OCRPDFResponse response = api.OcrPdfFromContent(request, fs);
                File.WriteAllBytes(@"result.pdf", Convert.FromBase64String(response.ResultData[0].ImageOcrResults.First().ResultPdf));
            }
        }
Пример #2
0
        static string RecognizePdfFromContent(Configuration conf)
        {
            string name = "TheCall.pdf";

            using (FileStream fs = File.OpenRead(name))
            {
                OcrApi api     = new OcrApi(conf);
                var    request = new OCRRequestData()
                {
                    DsrMode = DsrMode.NoDsrNoFilter
                };
                OCRPDFResponse response = api.OcrPdfFromContent(request, fs);

                var all_text = response.ResultData.Aggregate(
                    "", (s, page) =>
                    s += page.OriginalText + "\n\n" + page.ImageOcrResults.Aggregate("", (s1, singleImageResult) => s1 += singleImageResult.ResultText + "\n\n") + "\n\n");

                return(all_text);
            }
        }