private void fnOCR(string v_strImgPath)
{
//获取图片的Base64编码
FileInfo file = new FileInfo(v_strImgPath);
using (MemoryStream ms = new MemoryStream())
{
Bitmap bp = new Bitmap(v_strImgPath);
switch (file.Extension.ToLower())
{
case ".jpg":
bp.Save(ms, ImageFormat.Jpeg);
break;
case ".jpeg":
bp.Save(ms, ImageFormat.Jpeg);
break;
case ".gif":
bp.Save(ms, ImageFormat.Gif);
break;
case ".bmp":
bp.Save(ms, ImageFormat.Bmp);
break;
case ".tiff":
bp.Save(ms, ImageFormat.Tiff);
break;
case ".png":
bp.Save(ms, ImageFormat.Png);
break;
case ".emf":
bp.Save(ms, ImageFormat.Emf);
break;
default:
this.labMsg.Content = "不支持的图片格式。";
return;
}
byte[] buffer = ms.GetBuffer();
string _Base64 = Convert.ToBase64String(buffer);
//向Onenote2010中插入图片
var onenoteApp = new Microsoft.Office.Interop.OneNote.Application();
/*string sectionID; Console.WriteLine("wang");
onenoteApp.OpenHierarchy(AppDomain.CurrentDomain.BaseDirectory + "tmpPath/" + "newfile.one",
null, out sectionID, Microsoft.Office.Interop.OneNote.CreateFileType.cftSection);
string pageID = "{A975EE72-19C3-4C80-9C0E-EDA576DAB5C6}{1}{B0}"; // 格式 {guid}{tab}{??}
onenoteApp.CreateNewPage(sectionID, out pageID, Microsoft.Office.Interop.OneNote.NewPageStyle.npsBlankPageNoTitle);
*/
var existingPageId = "";
//var pageNode;
string notebookXml;
if (existingPageId == "")
{
onenoteApp.GetHierarchy(null, Microsoft.Office.Interop.OneNote.HierarchyScope.hsPages, out notebookXml);
//onenoteApp.GetHierarchy(pageID, HierarchyScope.hsPages, out notebookXml);
var doc = XDocument.Parse(notebookXml);
var ns = doc.Root.Name.Namespace;
var sectionNode = doc.Descendants(ns + "Section").FirstOrDefault();
var sectionID = sectionNode.Attribute("ID").Value;
onenoteApp.CreateNewPage(sectionID, out existingPageId);
var pageNode = doc.Descendants(ns + "Page").FirstOrDefault();
if (pageNode != null)
{
//Image Type 只支持这些类型：auto|png|emf|jpg
string ImgExtension = file.Extension.ToLower().Substring(1);
switch (ImgExtension)
{
case "jpg":
ImgExtension = "jpg";
break;
case "png":
ImgExtension = "png";
break;
case "emf":
ImgExtension = "emf";
break;
default:
ImgExtension = "auto";
break;
}
var page = new XDocument(new XElement(ns + "Page", new XAttribute("ID", existingPageId),
new XElement(ns + "Outline",
new XElement(ns + "OEChildren",
new XElement(ns + "OE",
new XElement(ns + "Image",
new XAttribute("format", ImgExtension), new XAttribute("originalPageNumber", "0"),
new XElement(ns + "Position",
new XAttribute("x", "0"), new XAttribute("y", "0"), new XAttribute("z", "0")),
new XElement(ns + "Size",
new XAttribute("width", bp.Width.ToString()), new XAttribute("height", bp.Height.ToString())),
new XElement(ns + "Data", _Base64)))))));
//page.Root.SetAttributeValue("ID", existingPageId);
onenoteApp.UpdatePageContent(page.ToString(), DateTime.MinValue);
//线程休眠时间，单位毫秒，若图片很大，则延长休眠时间，保证Onenote OCR完毕
System.Threading.Thread.Sleep(Int32.Parse(System.Configuration.ConfigurationManager.AppSettings["WaitTIme"]));
string pageXml;
onenoteApp.GetPageContent(existingPageId, out pageXml, Microsoft.Office.Interop.OneNote.PageInfo.piBinaryData);//piAll
//获取OCR后的内容
FileStream tmpXml = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Create, FileAccess.ReadWrite);
StreamWriter sw = new StreamWriter(tmpXml);
sw.Write(pageXml);
sw.Flush();
sw.Close();
tmpXml.Close();
FileStream tmpOnenote = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Open, FileAccess.ReadWrite);
XmlReader reader = XmlReader.Create(tmpOnenote);
XElement rdlc = XElement.Load(reader);
XmlNameTable nameTable = reader.NameTable;
XmlNamespaceManager mgr = new XmlNamespaceManager(nameTable);
mgr.AddNamespace("one", ns.ToString());
StringReader sr = new StringReader(pageXml);
XElement onenote = XElement.Load(sr);
var xml = from o in onenote.XPathSelectElements("//one:Image", mgr)
select o.XPathSelectElement("//one:OCRText", mgr).Value;
this.txtOCRed.Text = (xml.First().ToString()).Replace(" ", "");
sr.Close();
reader.Close();
tmpOnenote.Close();
onenoteApp.DeleteHierarchy(existingPageId);
//onenoteApp.DeleteHierarchy(sectionID, DateTime.MinValue, true); // 摧毁原始页面
}
}
/*Onenote 2010 中图片的XML格式
<one:Image format="" originalPageNumber="0" lastModifiedTime="" objectID="">
<one:Position x="" y="" z=""/>
<one:Size width="" height=""/>
<one:Data>Base64</one:Data>
//以下标签由Onenote 2010自动生成，不要在程序中处理，目标是获取OCRText中的内容。
<one:OCRData lang="en-US">
<one:OCRText>
<![CDATA[ OCR后的文字 ]]>
</one:OCRText>
<one:OCRToken startPos="0" region="0" line="0" x="4.251968383789062" y="3.685039281845092" width="31.18110275268555" height="7.370078563690185"/>
<one:OCRToken startPos="7" region="0" line="0" x="39.40157318115234" y="3.685039281845092" width="13.32283401489258" height="8.78740119934082"/>
<one:OCRToken startPos="12" region="0" line="1" x="4.251968383789062" y="17.85826683044434" width="23.52755928039551" height="6.803150177001953"/>
<one:OCRToken startPos="18" region="0" line="1" x="32.031494140625" y="17.85826683044434" width="41.10236358642578" height="6.803150177001953"/>
<one:OCRToken startPos="28" region="0" line="1" x="77.66928863525391" y="17.85826683044434" width="31.46456718444824" height="6.803150177001953"/>
................
</one:Image>
*/
/*ObjectID格式
The representation of an object to be used for identification of objects on a page. Not unique through OneNote, but unique on the page and the hierarchy.
<xsd:simpleType name="ObjectID" ">
<xsd:restriction base="xsd:string">
<xsd:pattern value="\{[a-fA-F0-9]{8}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{4}-[a-fA-F0-9]{12}\}\{[0-9]+\}\{[A-Z][0-9]+\}" />
</xsd:restriction>
</xsd:simpleType>
*/
}
}
/// <summary>
/// onenote 2010，注意需要先在onenote中创建笔记本，并且将至转换为onenote2007格式
/// 推荐使用onenote2016（个人版即可），API与2010类似，（去掉XMLSchema.xs2007参数即可）其他可参考API参数命名。
/// 注意1：一定要将dll属性中的“嵌入互操作类型”属性关闭
/// </summary>
/// <param name="imgPath"></param>
/// <returns></returns>
public string Ocr_2010(string imgPath)
{
try
{
#region 确定section_path存在
section_path = @"C:\Users\zhensheng\Desktop\打杂\ocr\ocr.one";
if (string.IsNullOrEmpty(section_path))
{
Console.WriteLine("请先建立笔记本");
File.AppendAllText(AppDomain.CurrentDomain.BaseDirectory + @"\log.txt", "需要先在onenote中创建笔记本，并且将至转换为onenote2007格式，且将.one文件得路径赋值给section_path");
return("");
}
#endregion
#region 准备数据
//后缀
var imgType = Path.GetExtension(imgPath);
imgPath = imgPath.Replace(".", "");
var data = File.ReadAllBytes(imgPath);
//根据大小确定重试次数
int fileSize = Convert.ToInt32(data.Length / 1024 / 1024); // 文件大小 单位M
string guid = Guid.NewGuid().ToString();
string pageID = "{" + guid + "}{1}{B0}"; // 格式 {guid}{tab}{??}
string pageXml;
XNamespace ns;
var onenoteApp = new Microsoft.Office.Interop.OneNote.Application(); //onenote提供的API
if (onenoteApp == null)
{
File.AppendAllText(AppDomain.CurrentDomain.BaseDirectory + @"\log.txt", "Microsoft.Office.Interop.OneNote.Application()创建失败");
return("");
}
//重试使用
XmlNode xmlNode;
int retry = 0;
#endregion
do
{
#region 创建页面并返回pageID
string sectionID;
onenoteApp.OpenHierarchy(section_path, null, out sectionID, CreateFileType.cftSection);
onenoteApp.CreateNewPage(sectionID, out pageID);
#endregion
#region 获取onenote页面xml结构格式
string notebookXml;
onenoteApp.GetHierarchy(null, HierarchyScope.hsPages, out notebookXml, XMLSchema.xs2007);
var doc = XDocument.Parse(notebookXml);
ns = doc.Root.Name.Namespace;
#endregion
#region 将图片插入页面
Tuple <string, int, int> imgInfo = this.GetBase64(data, imgType);
var page = new XDocument(new XElement(ns + "Page",
new XElement(ns + "Outline",
new XElement(ns + "OEChildren",
new XElement(ns + "OE",
new XElement(ns + "Image",
new XAttribute("format", imgType), new XAttribute("originalPageNumber", "0"),
new XElement(ns + "Position",
new XAttribute("x", "0"), new XAttribute("y", "0"), new XAttribute("z", "0")),
new XElement(ns + "Size",
new XAttribute("width", imgInfo.Item2), new XAttribute("height", imgInfo.Item3)),
new XElement(ns + "Data", imgInfo.Item1)))))));
page.Root.SetAttributeValue("ID", pageID);
onenoteApp.UpdatePageContent(page.ToString(), DateTime.MinValue, XMLSchema.xs2007);
#endregion
#region 通过轮询访问获取OCR识别的结果,轮询超时次数为6次
int count = 0;
do
{
System.Threading.Thread.Sleep(waitTime * (fileSize > 1 ? fileSize : 1)); // 小于1M的都默认1M
onenoteApp.GetPageContent(pageID, out pageXml, PageInfo.piBinaryData, XMLSchema.xs2007);
}while (pageXml == "" && count++ < 6);
#endregion
#region 除页面
onenoteApp.DeleteHierarchy(pageID, DateTime.MinValue);
//onenoteApp = null;
#endregion
#region 从xml中提取OCR识别后的文档信息，然后输出到string中
XmlDocument xmlDoc = new XmlDocument();
xmlDoc.LoadXml(pageXml);
XmlNamespaceManager nsmgr = new XmlNamespaceManager(xmlDoc.NameTable);
nsmgr.AddNamespace("one", ns.ToString());
xmlNode = xmlDoc.SelectSingleNode("//one:Image//one:OCRText", nsmgr);
#endregion
}
//如果OCR没有识别出信息，则重试三次（个人测试2010失败率为0.2~0.3）
while (xmlNode == null && retry++ < 3);
if (xmlNode == null)
{
File.AppendAllText(AppDomain.CurrentDomain.BaseDirectory + @"\log.txt", "OCR没有识别出值");
return("");
}
var localFilePath = AppDomain.CurrentDomain.BaseDirectory + @"\" + Guid.NewGuid().ToString() + ".txt";
File.WriteAllText(localFilePath, xmlNode.InnerText.ToString());
Console.WriteLine(xmlNode.InnerText.ToString());
return(localFilePath);
}
catch (Exception e)
{
File.AppendAllText(AppDomain.CurrentDomain.BaseDirectory + @"\log.txt", e.ToString());
return("");
}
}