[英]Extracting field values from a Word Document using openxml SDK
我正在嘗試從Word文檔中提取表單字段。 Word文檔使用一些文本框和復選框來創建一種類型的表單。 我想以編程方式能夠使用C#提取控件中的值。 我以為OpenXML可能允許這樣做,但我一直無法弄清楚。
這是MS Word文檔中的示例表單的屏幕截圖:
使用DocumentFormat.OpenXml Nuget包;
樣例代碼:
using (var doc = WordprocessingDocument.Open("OpenXMLTest.docx", false))
{
Console.WriteLine("Title = " + doc.ExtendedFilePropertiesPart.Properties.TitlesOfParts.InnerText);
Console.WriteLine("Subject = " + doc.PackageProperties.Subject);
{
foreach (var control in doc.ContentControls())
{
Console.WriteLine( control.Title + "==>" + control.Value);
}
}
}
並包括擴展名:
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;
public static class ContentControlExtensions
{
public static IEnumerable<ContentControl> ContentControls(this OpenXmlPart part)
{
var results = new List<ContentControl>();
IEnumerable<OpenXmlElement> parents = part.RootElement
.Descendants()
.Where(e => e is SdtProperties)
.Select(p => p.Parent);
foreach(var parent in parents)
{
ParseContentControl(results, parent);
}
return results;
}
private static void ParseContentControl(List<ContentControl> results, OpenXmlElement parent)
{
var sdtAlias = parent.ChildElements.Where(p => p is SdtProperties).FirstOrDefault()
.ChildElements.Where(c => c is SdtAlias).FirstOrDefault();
if (sdtAlias != null)
{
string value = string.Empty;
var name = ((SdtAlias)sdtAlias).Val;
var sdtContentCell = parent.ChildElements.Where(p => p is SdtContentCell).FirstOrDefault();
if (sdtContentCell != null)
{
value = sdtContentCell.InnerText;
if (value == "Click or tap here to enter text.")
{
value = null;
}
}
var sdtid = parent.ChildElements.Where(p => p is SdtProperties).FirstOrDefault()
.ChildElements.Where(c => c is SdtId).FirstOrDefault();
var id = ((SdtId)sdtid).Val;
var sdtTag = parent.ChildElements.Where(p => p is SdtProperties).FirstOrDefault()
.ChildElements.Where(c => c is Tag).FirstOrDefault();
var tag = ((Tag)sdtTag).Val;
results.Add(new ContentControl() { Title = name, Value = value, id = id, Tag = tag });
}
}
public static IEnumerable<ContentControl> ContentControls(
this WordprocessingDocument doc)
{
foreach (var cc in doc.MainDocumentPart.ContentControls())
yield return cc;
foreach (var header in doc.MainDocumentPart.HeaderParts)
foreach (var cc in header.ContentControls())
yield return cc;
foreach (var footer in doc.MainDocumentPart.FooterParts)
foreach (var cc in footer.ContentControls())
yield return cc;
if (doc.MainDocumentPart.FootnotesPart != null)
foreach (var cc in doc.MainDocumentPart.FootnotesPart.ContentControls())
yield return cc;
if (doc.MainDocumentPart.EndnotesPart != null)
foreach (var cc in doc.MainDocumentPart.EndnotesPart.ContentControls())
yield return cc;
}
public class ContentControl
{
public string Title {get; set; }
public string Value { get; set; }
public string Tag { get; set; }
public string id { get; set; }
}
}
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.