static void Main(string[] args)
{
string testFile = null;
try
{
// ** Make sure an api key has been entered
if (API_KEY == string.Empty)
{
Console.WriteLine("[ERROR] Please update the sample code and enter the API Key that came with your subscription.");
return;
}
// ** Was a 'file to OCR' specified on the command line?
if (args.Count() == 0)
{
Console.WriteLine("[INFO] No file to OCR specified, using default file.");
testFile = Directory.GetFiles(".", "*.tif")[0];
}
else
{
testFile = args[0];
}
// ** Specify the API key associated with your subscription.
Configuration.Default.AddApiKey("api_key", API_KEY);
// ** Accept all SSL Certificates, this makes life under mono a lot easier. This line is not needed on Windows
ServicePointManager.ServerCertificateValidationCallback = delegate { return(true); };
// ** The service's host name is already set, but for debugging purposes you may want to switch between 'http' and 'https'.'
Configuration.Default.ApiClient.RestClient.BaseUrl = new Uri("https://api.muhimbi.com/api");
// ** We are dealing with OCR, so instantiate the relevant class
OCRApi ocrApi = new OCRApi();
// ** Read the file we wish to OCR
byte[] sourceFile = File.ReadAllBytes(testFile);
// ** Fill out the data for the OCR operation.
OcrTextData inputData = new OcrTextData(
SourceFileName: testFile, // ** The name of the file to OCR. Always include the correct extension
SourceFileContent: sourceFile, // ** The content of the file to OCR
Language: OcrTextData.LanguageEnum.English, // ** The document's primary language
Performance: OcrTextData.PerformanceEnum.Slowbutaccurate, // ** Unless you have a good reason not to, always use the 'Slow' option.
CharactersOption: OcrTextData.CharactersOptionEnum.Blacklist, // ** Any characters to black list or white list (e.g. 1234567890 to deal with numerical data)
Characters: "|", // ** In this example we blacklist the '|' (pipe) as it looks similar to l (L) 1 (one) and I (capital I)
Paginate: false, // ** Only 'paginate' when your documents have images that span multiple pages.
X: "36", // ** By default the entire page is OCRed, optionally specify an area (in pt., 1/72nd of an inch)
Y: "72",
Width: "400",
Height: "30",
PageNumber: "1"
);
// ** Carry out the OCR operation
Console.WriteLine("[INFO] Running OCR...");
var response = ocrApi.OcrText(inputData);
// ** Writing the recognised text to the console
Console.OutputEncoding = System.Text.Encoding.UTF8;
Console.Write("[INFO] Extracted text: ");
Console.ForegroundColor = ConsoleColor.Yellow;
Console.WriteLine(response.OutText);
Console.ResetColor();
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
}
static void Main(string[] args)
{
string testFile = null;
try
{
// ** Make sure an api key has been entered
if (API_KEY == string.Empty)
{
Console.WriteLine("[ERROR] Please update the sample code and enter the API Key that came with your subscription.");
return;
}
// ** Was a 'file to OCR' specified on the command line?
if (args.Count() == 0)
{
Console.WriteLine("[INFO] No file to OCR specified, using default file.");
testFile = Directory.GetFiles(".", "*.tif")[0];
}
else
{
testFile = args[0];
}
// ** Specify the API key associated with your subscription.
Configuration.Default.AddApiKey("api_key", API_KEY);
// ** Accept all SSL Certificates, this makes life under mono a lot easier. This line is not needed on Windows
ServicePointManager.ServerCertificateValidationCallback = delegate { return(true); };
// ** The service's host name is already set, but for debugging purposes you may want to switch between 'http' and 'https'.'
Configuration.Default.ApiClient.RestClient.BaseUrl = new Uri("https://api.muhimbi.com/api");
// ** We are dealing with OCR, so instantiate the relevant class
OCRApi ocrApi = new OCRApi();
// ** Read the file we wish to OCR
byte[] sourceFile = File.ReadAllBytes(testFile);
// ** Fill out the data for the OCR operation.
OcrPdfData inputData = new OcrPdfData(
SourceFileName: testFile, // ** The name of the file to OCR. Always include the correct extension
SourceFileContent: sourceFile, // ** The content of the file to OCR
Language: OcrPdfData.LanguageEnum.English, // ** The document's primary language
Performance: OcrPdfData.PerformanceEnum.Slowbutaccurate, // ** Unless you have a good reason not to, always use the 'Slow' option.
CharactersOption: OcrPdfData.CharactersOptionEnum.None, // ** Any characters to black list or white list (e.g. 1234567890 to deal with numerical data)
Characters: null, // ** The characters to black or white list.
Paginate: false, // ** Only 'paginate' when your documents have images that span multiple pages.
Regions: null // ** We want to OCR the entire document, not just specific areas.
);
// ** Carry out the OCR operation
Console.WriteLine("[INFO] Running OCR...");
var response = ocrApi.OcrPdf(inputData);
// ** Write the results back to the file system
File.WriteAllBytes(@"result.pdf", response.ProcessedFileContent);
Console.WriteLine("[INFO] 'result.pdf' written to output folder.");
// ** On Windows open the generated file in the system PDF viewer
Process.Start(@"result.pdf");
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
}
static string UseImage(string url, string path)
{
HttpWebRequest webReq = (HttpWebRequest)WebRequest.Create(new System.Uri(url));
Stream memStream = new MemoryStream();
webReq.Method = "POST";
string boundary = "--------------" + DateTime.Now.Ticks.ToString("x");// 边界符
webReq.ContentType = "multipart/form-data; boundary=" + boundary;
byte[] enter = Encoding.ASCII.GetBytes("\r\n"); //换行
memStream.Write(enter, 0, enter.Length);
Dictionary <string, string> dic = new Dictionary <string, string>()
{
{ "appid", config.appid },
{ "bucket", config.bucket }
};
//写入文本字段
string inputPartHeaderFormat = "--" + boundary + "\r\n" + "Content-Disposition:form-data;name=\"{0}\";" + "\r\n\r\n{1}\r\n";
foreach (var kv in dic)
{
string inputPartHeader = string.Format(inputPartHeaderFormat, kv.Key, kv.Value);
var inputPartHeaderBytes = Encoding.ASCII.GetBytes(inputPartHeader);
memStream.Write(inputPartHeaderBytes, 0, inputPartHeaderBytes.Length);
}
var fileStream = new FileStream(path, FileMode.Open, FileAccess.Read);
// 写入文件
//压缩图片
string imagePartHeader = "--" + boundary + "\r\n" +
"Content-Disposition: form-data; name=\"{0}\"; filename=\"{1}\"\r\n" +
"Content-Type: image/jpeg\r\n\r\n";
var header = string.Format(imagePartHeader, "image", "1.jpg");
var headerbytes = Encoding.UTF8.GetBytes(header);
memStream.Write(headerbytes, 0, headerbytes.Length);
var buffer = new byte[1024];
int bytesRead;
while ((bytesRead = fileStream.Read(buffer, 0, buffer.Length)) != 0)
{
memStream.Write(buffer, 0, bytesRead);
}
// 最后的结束符
byte[] endBoundary = Encoding.ASCII.GetBytes("xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" + "\r\n" + boundary + "--\r\n");
memStream.Write(endBoundary, 0, endBoundary.Length);
webReq.ContentLength = memStream.Length;
webReq.Headers.Add(HttpRequestHeader.Authorization, OCRApi.HmacSha1Sign());
webReq.Host = config.Host;
var requestStream = webReq.GetRequestStream();
memStream.Position = 0;
memStream.CopyTo(requestStream);
HttpWebResponse response = (HttpWebResponse)webReq.GetResponse();
StreamReader sr = new StreamReader(response.GetResponseStream(), Encoding.UTF8);
var ret = sr.ReadToEnd();
sr.Close();
response.Close();
requestStream.Close();
memStream.Close();
return(ret);
}
