使用OpenXML(C#)解析*.docx文档时遇到一个问题.
所以,这是我的步骤:
1.加载*.docx文档
2.接收段落列表
3.在每个段落中查找文本,图像和表格元素
4.为每个文本和图像元素创建html标签
5.将输出保存为*. html文件
我已经找到了如何在文档中找到图像文件并将其解压缩.现在还有一步 - 找到文本中的表位置(段落).
如果有人知道如何使用OpenXML在*.docx文档中找到表格请帮忙.谢谢.
附加:好的,可能是我不清楚解释我的意思.如果我们获得段落的内容,您可以找到chield对象作为文本块,图片等.所以,如果段落包含Run包含Picture那就意味着在这个地方放置Word文档放置图像.
我的功能样本:
public static string ParseDocxDocument(string pathToFile)
{
StringBuilder result = new StringBuilder();
WordprocessingDocument wordProcessingDoc = WordprocessingDocument.Open(pathToFile, true);
List<ImagePart> imgPart = wordProcessingDoc.MainDocumentPart.ImageParts.ToList();
IEnumerable<Paragraph> paragraphElement = wordProcessingDoc.MainDocumentPart.Document.Descendants<Paragraph>();
int imgCounter = 0;
foreach (Paragraph par in paragraphElement)
{
//Add new paragraph tag
result.Append("<div style=\"width:100%; text-align:");
//Append anchor style
if (par.ParagraphProperties != null && par.ParagraphProperties.Justification != null)
switch (par.ParagraphProperties.Justification.Val.Value)
{
case JustificationValues.Left:
result.Append("left;");
break;
case JustificationValues.Center:
result.Append("center;");
break;
case JustificationValues.Both:
result.Append("justify;");
break;
case JustificationValues.Right:
default:
result.Append("right;");
break;
}
else
result.Append("left;");
//Append text decoration style
if (par.ParagraphProperties != null && par.ParagraphProperties.ParagraphMarkRunProperties != null && par.ParagraphProperties.ParagraphMarkRunProperties.HasChildren)
foreach (OpenXmlElement chield in par.ParagraphProperties.ParagraphMarkRunProperties.ChildElements)
{
switch (chield.GetType().Name)
{
case "Bold":
result.Append("font-weight:bold;");
break;
case "Underline":
result.Append("text-decoration:underline;");
break;
case "Italic":
result.Append("font-style:italic;");
break;
case "FontSize":
result.Append("font-size:" + ((FontSize)chield).Val.Value + "px;");
break;
default: break;
}
}
result.Append("\">");
//Add image tag
IEnumerable<Run> runs = par.Descendants<Run>();
foreach (Run run in runs)
{
if (run.HasChildren)
{
foreach (OpenXmlElement chield in run.ChildElements.Where(o => o.GetType().Name == "Picture"))
{
result.Append(string.Format("<img style=\"{1}\" src=\"data:image/jpeg;base64,{0}\" />", GetBase64Image(imgPart[imgCounter].GetStream()),
((DocumentFormat.OpenXml.Vml.Shape)chield.ChildElements.Where(o => o.GetType().Name == "Shape").FirstOrDefault()).Style
));
imgCounter++;
}
}
}
//Append inner text
IEnumerable<Text> textElement = par.Descendants<Text>();
if (par.Descendants<Text>().Count() == 0)
result.Append("<br />");
foreach (Text t in textElement)
{
result.Append(t.Text);
}
result.Append("</div>");
result.Append(Environment.NewLine);
}
wordProcessingDoc.Close();
return result.ToString();
}
现在我想在文本中指定表格位置(因为它出现在Word中).
最后:
好的,大家,我发现了.在我的示例函数中有一个大错误.我列举了文件Body的Paragraph元素.表与Paragraph处于同一级别,因此函数忽略表.所以我们需要枚举文档Body的元素.
这是我的测试函数从docx生成正确的HTML(它只是测试代码,所以它不干净)
public static string ParseDocxDocument(string pathToFile)
{
StringBuilder result = new StringBuilder();
WordprocessingDocument wordProcessingDoc = WordprocessingDocument.Open(pathToFile, true);
List<ImagePart> imgPart = wordProcessingDoc.MainDocumentPart.ImageParts.ToList();
List<string> tableCellContent = new List<string>();
IEnumerable<Paragraph> paragraphElement = wordProcessingDoc.MainDocumentPart.Document.Descendants<Paragraph>();
int imgCounter = 0;
foreach (OpenXmlElement section in wordProcessingDoc.MainDocumentPart.Document.Body.Elements<OpenXmlElement>())
{
if(section.GetType().Name == "Paragraph")
{
Paragraph par = (Paragraph)section;
//Add new paragraph tag
result.Append("<div style=\"width:100%; text-align:");
//Append anchor style
if (par.ParagraphProperties != null && par.ParagraphProperties.Justification != null)
switch (par.ParagraphProperties.Justification.Val.Value)
{
case JustificationValues.Left:
result.Append("left;");
break;
case JustificationValues.Center:
result.Append("center;");
break;
case JustificationValues.Both:
result.Append("justify;");
break;
case JustificationValues.Right:
default:
result.Append("right;");
break;
}
else
result.Append("left;");
//Append text decoration style
if (par.ParagraphProperties != null && par.ParagraphProperties.ParagraphMarkRunProperties != null && par.ParagraphProperties.ParagraphMarkRunProperties.HasChildren)
foreach (OpenXmlElement chield in par.ParagraphProperties.ParagraphMarkRunProperties.ChildElements)
{
switch (chield.GetType().Name)
{
case "Bold":
result.Append("font-weight:bold;");
break;
case "Underline":
result.Append("text-decoration:underline;");
break;
case "Italic":
result.Append("font-style:italic;");
break;
case "FontSize":
result.Append("font-size:" + ((FontSize)chield).Val.Value + "px;");
break;
default: break;
}
}
result.Append("\">");
//Add image tag
IEnumerable<Run> runs = par.Descendants<Run>();
foreach (Run run in runs)
{
if (run.HasChildren)
{
foreach (OpenXmlElement chield in run.ChildElements.Where(o => o.GetType().Name == "Picture"))
{
result.Append(string.Format("<img style=\"{1}\" src=\"data:image/jpeg;base64,{0}\" />", GetBase64Image(imgPart[imgCounter].GetStream()),
((DocumentFormat.OpenXml.Vml.Shape)chield.ChildElements.Where(o => o.GetType().Name == "Shape").FirstOrDefault()).Style
));
imgCounter++;
}
foreach (OpenXmlElement table in run.ChildElements.Where(o => o.GetType().Name == "Table"))
{
result.Append("<strong>HERE'S TABLE</strong>");
}
}
}
//Append inner text
IEnumerable<Text> textElement = par.Descendants<Text>();
if (par.Descendants<Text>().Count() == 0)
result.Append("<br />");
foreach (Text t in textElement.Where(o=>!tableCellContent.Contains(o.Text.Trim())))
{
result.Append(t.Text);
}
result.Append("</div>");
result.Append(Environment.NewLine);
}
else if (section.GetType().Name=="Table")
{
result.Append("<table>");
Table tab = (Table)section;
foreach (TableRow row in tab.Descendants<TableRow>())
{
result.Append("<tr>");
foreach (TableCell cell in row.Descendants<TableCell>())
{
result.Append("<td>");
result.Append(cell.InnerText);
tableCellContent.Add(cell.InnerText.Trim());
result.Append("</td>");
}
result.Append("</tr>");
}
result.Append("</table>");
}
}
wordProcessingDoc.Close();
return result.ToString();
}
private static string GetBase64Image(Stream inputData)
{
byte[] data = new byte[inputData.Length];
inputData.Read(data, 0, data.Length);
return Convert.ToBase64String(data);
}
尝试按照以下步骤查找文档中的第一个表格。
Table table = doc.MainDocumentPart.Document.Body.Elements<Table>().First();