openXML获取world文件标题及所需的关键字

最近有个需求&＃xff0c;使用c#操作world文件&＃xff0c;并获取其中的标题及其他所需引导词后面的内容&＃xff0c;如下图&＃xff0c;获取文件中的标题&＃xff0c;引导词后面的内容

采用的是open xml将world文件转换成xml(open xml只支持docx文件格式,如果不是docx格式的&＃xff0c;可以先通过world转换过来)&＃xff0c;可以获取每个段落中的所有文字喝标签样式&＃xff0c;已知标题的字体最大&＃xff0c;根据标签样式属性&＃xff0c;获取最大的样式的那个段落既是标题&＃xff0c;其他内容可以通过indexOf查询关键词进行获取
先看看完成效果

代码如下&＃xff08;初学C#一周&＃xff0c;如果有写的不好的地方&＃xff0c;望大佬指正&＃xff09;&＃xff1a;

所需插件&＃xff1a;

引入

using System;
using System.Collections.Generic;
using System.Data;
using System.Linq;
using System.Text;
using System.Windows.Forms;
using System.Collections;
using System.Xml;
using DocumentFormat.OpenXml.Packaging;


定义

public class objList{public string title;public string biaoji1;public string number;public string biaoji3;}public class textObjectAll{public int index;public string innerXml;public string innerText;public int indexof;}public class textObjectCh{public int index;public string innerXml;public string innerText;public int indexof;}public enum WordKind{Title,biaoji1,number,biaoji3,}


方法&＃xff1a;&＃xff08;这是测试文件&＃xff0c;所以定义的少&＃xff0c;实际文件中会有很多引导词&＃xff09;

public static object GetContentFromWord(string docPath, string[] Kind){const string wordmlNamespace &＃61; "http://schemas.openxmlformats.org/wordprocessingml/2006/main";string text &＃61; null;string keyword &＃61; null;string keyworda &＃61; null;string abstracta &＃61; null;string biaoji1 &＃61; "";string number &＃61; "";string biaoji3 &＃61; "";int num &＃61; 0;int numa &＃61; 0;int numb &＃61; 0;int numx &＃61; 0;ArrayList list &＃61; new ArrayList();ArrayList lista &＃61; new ArrayList();ArrayList listb &＃61; new ArrayList();objList objList &＃61; new objList();StringBuilder textBuilder &＃61; new StringBuilder();using (WordprocessingDocument wdDoc &＃61; WordprocessingDocument.Open(docPath, false)){NameTable nt &＃61; new NameTable();XmlNamespaceManager nsManager &＃61; new XmlNamespaceManager(nt);nsManager.AddNamespace("w", wordmlNamespace);XmlDocument xdoc &＃61; new XmlDocument(nt);xdoc.Load(wdDoc.MainDocumentPart.GetStream());XmlNodeList paragraphNodes &＃61; xdoc.SelectNodes("//w:p ", nsManager);List<textObjectCh> listCh &＃61; new List<textObjectCh>();List<textObjectAll> listAll &＃61; new List<textObjectAll>();for (var i &＃61; 0; i < paragraphNodes.Count; i&＃43;&＃43;){if (!string.IsNullOrEmpty(paragraphNodes[i].InnerText)){XmlNodeList textNodes &＃61; paragraphNodes[i].SelectNodes(".//w:pStyle", nsManager);XmlNodeList textNodesa &＃61; paragraphNodes[i].SelectNodes(".//w:sz", nsManager);textObjectCh TextObjCh &＃61; new textObjectCh();textObjectAll TextObjAll &＃61; new textObjectAll();TextObjAll.index &＃61; i;TextObjAll.innerText &＃61; paragraphNodes[i].InnerText;TextObjAll.innerXml &＃61; paragraphNodes[i].InnerXml;TextObjAll.indexof &＃61; numb;listAll.Add(TextObjAll);string AllinnerText &＃61; null;if (paragraphNodes[i].InnerText&＃61;&＃61;null){}elseAllinnerText &＃61; paragraphNodes[i].InnerText.ToString();for (int v &＃61; 0; v < Kind.Length; v&＃43;&＃43;){switch (Kind[v].ToString()){case "biaoji1":if (AllinnerText.IndexOf("标记1") > -1 && AllinnerText.IndexOf("号码") > -1){biaoji1 &＃61; AllinnerText.Substring(AllinnerText.IndexOf("标记1") &＃43; 4, AllinnerText.IndexOf("号码")- (AllinnerText.IndexOf("标记1")&＃43;4));}break;case "number":if (AllinnerText.IndexOf("号码") > -1)number &＃61; AllinnerText.Substring(AllinnerText.IndexOf("号码") &＃43; 3);break;case "biaoji3":if (AllinnerText.IndexOf("标记3") >-1){biaoji3 &＃61; AllinnerText.Substring(AllinnerText.IndexOf("DOI") &＃43; 4);}break;}}if (textNodes.Count > 0)//标题字体样式有两种可能&＃xff0c;一种是直接的字体大小(w:sz)&＃xff0c;这里获取最大的字体&＃xff0c;还有一种是使用的标题&＃xff0c;例如 标题1&＃xff0c;标题2,这里是截取标题后面的数字&＃xff0c;取最小的{try{text &＃61; textNodes[0].OuterXml;}catch { }num &＃61; text.IndexOf("w:val");numa &＃61; text.IndexOf("http://");if (numa - num > 20 && numa - num < 25){keyworda &＃61; text.Substring(num);keyword &＃61; text.Substring(num &＃43; 9, numa - num - 20);numx &＃61; 1;}}else{if (textNodesa.Count > 0){try{text &＃61; textNodesa[0].OuterXml;}catch { }num &＃61; text.IndexOf("w:val");numa &＃61; text.IndexOf("xmlns:w");if (numa - num > 9 && numa - num < 20){keyword &＃61; text.Substring(num &＃43; 7, numa - num - 9);numx &＃61; 2;}}}try{if (int.TryParse(keyword, out numb)){TextObjCh.index &＃61; i;TextObjCh.innerText &＃61; paragraphNodes[i].InnerText;TextObjCh.innerXml &＃61; paragraphNodes[i].InnerXml;TextObjCh.indexof &＃61; numb;listCh.Add(TextObjCh);}}catch{}}//}//textBuilder.Append(Environment.NewLine);}if (numx &＃61;&＃61; 1){//如果标题采用的是标题1&＃xff0c;标题2 这种&＃xff0c;采用升序&＃xff0c;取第一个List<textObjectCh> listA &＃61; listCh.OrderBy(item &＃61;> item.indexof).ToList();objList.title &＃61; listA[0].innerText;if (biaoji1.Length > 0){objList.biaoji1 &＃61; biaoji1;}if (number.Length>0){objList.number &＃61; number;}if (biaoji3.Length>0){objList.biaoji3 &＃61; biaoji3;}return objList;}else{List<textObjectCh> listA &＃61; listCh.OrderByDescending(item &＃61;> item.indexof).ToList();objList.title &＃61; listA[0].innerText;if (biaoji1.Length > 0){objList.biaoji1 &＃61; biaoji1;}if (number.Length > 0){objList.number &＃61; number;}if (biaoji3.Length > 0){objList.biaoji3 &＃61; biaoji3;}return objList;}};}


调用方法&＃xff1a;

private void button1_Click(object sender, EventArgs e){OpenFileDialog openFileDialog1 &＃61; new OpenFileDialog(); //显示选择文件对话框openFileDialog1.InitialDirectory &＃61; "c:\\";openFileDialog1.Filter &＃61; "txt files (*.docx)|*.docx|All files (*.docx)|*.docx"; //注意&＃xff1a;open xml只支持docx文件格式openFileDialog1.FilterIndex &＃61; 2;openFileDialog1.RestoreDirectory &＃61; true;string[] strText &＃61; {WordKind.Title.ToString(),WordKind.biaoji1.ToString(),WordKind.number.ToString(),WordKind.biaoji3.ToString(),};if (openFileDialog1.ShowDialog() &＃61;&＃61; DialogResult.OK){this.FilePath.Text &＃61; openFileDialog1.FileName; //显示文件路径objList objList &＃61; (objList)GetContentFromWord(openFileDialog1.FileName, strText);this.Title.Text &＃61; objList.title;this.biaoji1.Text &＃61; objList.biaoji1;this.number.Text &＃61; objList.number;this.biaoji3.Text &＃61; objList.biaoji3;}}