1 #region 字段
 2 protected FileStream m_stream;
 3 protected Package m_package;
 4 #endregion
 5
 6 #region 构造函数
 7 /// <summary>
 8 /// 初始化OfficeOpenXMLFile
 9 /// </summary>
10 /// <param name="filePath">文件路径</param>
11 public OfficeOpenXMLFile(String filePath)
12 {
13     try
14     {
15         this.m_stream = new FileStream(filePath, FileMode.Open, FileAccess.Read);
16         this.m_package = Package.Open(this.m_stream);
17
18         this.ReadProperties();
19         this.ReadCoreProperties();
20         this.ReadContent();
21     }
22     finally
23     {
24         if (this.m_package != null)
25         {
26             this.m_package.Close();
27         }
28
29         if (this.m_stream != null)
30         {
31             this.m_stream.Close();
32         }
33     }
34 }
35 #endregion

 1 #region 常量
 2 private const String PropertiesNameSpace = "http://schemas.openxmlformats.org/officeDocument/2006/extended-properties";
 3 private const String CorePropertiesNameSpace = "http://schemas.openxmlformats.org/package/2006/metadata/core-properties";
 4 #endregion
 5
 6 #region 字段
 7 protected Dictionary<String, String> m_properties;
 8 protected Dictionary<String, String> m_coreProperties;
 9 #endregion
10
11 #region 属性
12 /// <summary>
13 /// 获取DocumentSummaryInformation
14 /// </summary>
15 public override Dictionary<String, String> DocumentSummaryInformation
16 {
17     get
18     {
19         return this.m_properties;
20     }
21 }
22
23 /// <summary>
24 /// 获取SummaryInformation
25 /// </summary>
26 public override Dictionary<String, String> SummaryInformation
27 {
28     get
29     {
30         return this.m_coreProperties;
31     }
32 }
33 #endregion
34
35 #region 读取Properties
36 private void ReadProperties()
37 {
38     if (this.m_package == null)
39     {
40         return;
41     }
42
43     PackagePart part = this.m_package.GetPart(new Uri("/docProps/app.xml", UriKind.Relative));
44     if (part == null)
45     {
46         return;
47     }
48
49     XmlDocument doc = new XmlDocument();
50     doc.Load(part.GetStream());
51
52     XmlNodeList nodes = doc.GetElementsByTagName("Properties", PropertiesNameSpace);
53     if (nodes.Count < 1)
54     {
55         return;
56     }
57
58     this.m_properties = new Dictionary<String, String>();
59     foreach (XmlElement element in nodes[0])
60     {
61         this.m_properties.Add(element.LocalName, element.InnerText);
62     }
63 }
64 #endregion
65
66 #region 读取CoreProperties
67 private void ReadCoreProperties()
68 {
69     if (this.m_package == null)
70     {
71         return;
72     }
73
74     PackagePart part = this.m_package.GetPart(new Uri("/docProps/core.xml", UriKind.Relative));
75     if (part == null)
76     {
77         return;
78     }
79
80     XmlDocument doc = new XmlDocument();
81     doc.Load(part.GetStream());
82
83     XmlNodeList nodes = doc.GetElementsByTagName("coreProperties", CorePropertiesNameSpace);
84     if (nodes.Count < 1)
85     {
86         return;
87     }
88
89     this.m_coreProperties = new Dictionary<String, String>();
90     foreach (XmlElement element in nodes[0])
91     {
92         this.m_coreProperties.Add(element.LocalName, element.InnerText);
93     }
94 }
95 #endregion

 1 /// <summary>
 2 /// 抽取Node中的文字
 3 /// </summary>
 4 /// <param name="node">XmlNode</param>
 5 /// <returns>Node中的文字</returns>
 6 public static String ReadNode(XmlNode node)
 7 {
 8     if ((node == null) || (node.NodeType != XmlNodeType.Element))//如果node为空
 9     {
10         return String.Empty;
11     }
12
13     StringBuilder nodeContent = new StringBuilder();
14
15     foreach (XmlNode child in node.ChildNodes)
16     {
17         if (child.NodeType != XmlNodeType.Element)
18         {
19             continue;
20         }
21
22         switch (child.LocalName)
23         {
24             case "t"://正文
25                 nodeContent.Append(child.InnerText.TrimEnd());
26
27                 String space = ((XmlElement)child).GetAttribute("xml:space");
28                 if ((!String.IsNullOrEmpty(space)) && (space == "preserve")) nodeContent.Append(' ');
29                 break;
30             case "cr"://换行符
31             case "br"://换页符
32                 nodeContent.Append(Environment.NewLine);
33                 break;
34             case "tab"://Tab
35                 nodeContent.Append("\t");
36                 break;
37             case "p"://段落
38                 nodeContent.Append(ReadNode(child));
39                 nodeContent.Append(Environment.NewLine);
40                 break;
41             default://其他情况
42                 nodeContent.Append(ReadNode(child));
43                 break;
44         }
45     }
46
47     return nodeContent.ToString();
48 }

 1 #region 常量
 2 private const String WordNameSpace = "http://schemas.openxmlformats.org/wordprocessingml/2006/main";
 3 #endregion
 4
 5 #region 字段
 6 private String m_paragraphText;
 7 #endregion
 8
 9 #region 属性
10 /// <summary>
11 /// 获取文档正文内容
12 /// </summary>
13 public String ParagraphText
14 {
15     get { return this.m_paragraphText; }
16 }
17 #endregion
18
19 #region 读取内容
20 protected override void ReadContent()
21 {
22     if (this.m_package == null)
23     {
24         return;
25     }
26
27     PackagePart part = this.m_package.GetPart(new Uri("/word/document.xml", UriKind.Relative));
28     if (part == null)
29     {
30         return;
31     }
32
33     StringBuilder content = new StringBuilder();
34     XmlDocument doc = new XmlDocument();
35     doc.Load(part.GetStream());
36
37     XmlNamespaceManager nsManager = new XmlNamespaceManager(doc.NameTable);
38     nsManager.AddNamespace("w", WordNameSpace);
39
40     XmlNode node = doc.SelectSingleNode("/w:document/w:body", nsManager);
41
42     if (node == null)
43     {
44         return;
45     }
46
47     content.Append(NodeHelper.ReadNode(node));
48
49     this.m_paragraphText = content.ToString();
50 }
51 #endregion

 1 #region 常量
 2 private const String PowerPointNameSpace = "http://schemas.openxmlformats.org/presentationml/2006/main";
 3 #endregion
 4
 5 #region 字段
 6 private StringBuilder m_allText;
 7 #endregion
 8
 9 #region 属性
10 /// <summary>
11 /// 获取PowerPoint幻灯片中所有文本
12 /// </summary>
13 public String AllText
14 {
15     get { return this.m_allText.ToString(); }
16 }
17 #endregion
18
19 #region 构造函数
20 /// <summary>
21 /// 初始化PptxFile
22 /// </summary>
23 /// <param name="filePath">文件路径</param>
24 public PptxFile(String filePath) :
25     base(filePath) { }
26 #endregion
27
28 #region 读取内容
29 protected override void ReadContent()
30 {
31     if (this.m_package == null)
32     {
33         return;
34     }
35
36     this.m_allText = new StringBuilder();
37
38     XmlDocument doc = null;
39     PackagePartCollection col = this.m_package.GetParts();
40     SortedList<Int32, XmlDocument> list = new SortedList<Int32, XmlDocument>();
41
42     foreach (PackagePart part in col)
43     {
44         if (part.Uri.ToString().IndexOf("ppt/slides/slide", StringComparison.OrdinalIgnoreCase) > -1)
45         {
46             doc = new XmlDocument();
47             doc.Load(part.GetStream());
48
49             String pageName = part.Uri.ToString().Replace("/ppt/slides/slide", "").Replace(".xml", "");
50             Int32 index = 0;
51             Int32.TryParse(pageName, out index);
52
53             list.Add(index, doc);
54         }
55     }
56
57     foreach (KeyValuePair<Int32, XmlDocument> pair in list)
58     {
59         XmlNamespaceManager nsManager = new XmlNamespaceManager(doc.NameTable);
60         nsManager.AddNamespace("p", PowerPointNameSpace);
61
62         XmlNode node = pair.Value.SelectSingleNode("/p:sld", nsManager);
63
64         if (node == null)
65         {
66             continue;
67         }
68
69         this.m_allText.Append(NodeHelper.ReadNode(node));
70     }
71 }
72 #endregion