开发中相关读取pdf,html,word,rtf,txt,powerpoint,excel等文档的操作

开发中有关读取pdf,html,word,rtf,txt,powerpoint,excel等文档的操作

?

关于这七种文档，我相信应该是最常用的文档了

在以下的介绍中会提到POI，现介绍下POI吧

poi处理WORD,EXCEL比较好:http://jakarta.apache.org/poi/

poi处理至少需要如下几个JAR包

?
PDFbox处理PDF比较好：http://pdfbox.apache.org/download.html

下面一一介绍了

第一和第二是只支持03版的word和excel文档

?? 第一、首先来看WORD文档：
我这里用的是poi，相关jar包自己去下载，然后加到工程中（以下所要用的jar包也是，不再重复说）

Java代码??

1. <span?style="font-size:?medium;"><span?style="font-size:?large;">public?static?String?readWord(String?path)?throws?Exception?{??
2. String?bodyText?=?null;??
3. try?{??
4. FileInputStream?is?=?new?FileInputStream(path);??
5. bodyText?=?new?WordExtractor(is).getText();??
6. }?catch?(Exception?e)?{??
7. System.out.println("=======");??
8. }??
9. return?bodyText;??
10. }</span></span>??

?

? 第二、Exel的文档

?

?

Java代码??

1. <span?style="font-size:?medium;"><span?style="font-size:?large;">public?static?String?ReadExcel(String?path)?throws?IOException?{??
2. InputStream?inputStream?=?null;??
3. String?content?=?null;??
4. try?{??
5. inputStream?=?new?FileInputStream(path);??
6. HSSFWorkbook?wb?=?new?HSSFWorkbook(inputStream);??
7. ExcelExtractor?extractor?=?new?ExcelExtractor(wb);??
8. extractor.setFormulasNotResults(true);??
9. extractor.setIncludeSheetNames(false);??
10. content?=?extractor.getText();??
11. }?catch?(FileNotFoundException?e)?{??
12. e.printStackTrace();??
13. }??
14. return?content;??
15. }</span></span>??

?

??

?针对07版的word和excel的操作

???package com.test;

Java代码??

1. <span?style="font-size:?large;">?????
2. /**????
3. ?*?需要的jar包：????
4. ?*?poi-3.0.2-FINAL-20080204.jar????
5. ?*?poi-contrib-3.0.2-FINAL-20080204.jar????
6. ?*?poi-scratchpad-3.0.2-FINAL-20080204.jar????
7. ?*?poi-3.5-beta6-20090622.jar????
8. ?*?geronimo-stax-api_1.0_spec-1.0.jar????
9. ?*?ooxml-schemas-1.0.jar????
10. ?*?openxml4j-bin-beta.jar????
11. ?*?poi-ooxml-3.5-beta6-20090622.jar????
12. ?*?xmlbeans-2.3.0.jar????
13. ?*?dom4j-1.6.1.jar????
14. ?*/?????
15. ?????
16. import?java.io.FileInputStream;??????
17. import?java.io.IOException;??????
18. import?java.io.InputStream;??????
19. ?????
20. import?org.apache.poi.POIXMLDocument;??????
21. import?org.apache.poi.POIXMLTextExtractor;??????
22. import?org.apache.poi.hssf.usermodel.HSSFCell;??????
23. import?org.apache.poi.hssf.usermodel.HSSFRow;??????
24. import?org.apache.poi.hssf.usermodel.HSSFSheet;??????
25. import?org.apache.poi.hssf.usermodel.HSSFWorkbook;??????
26. import?org.apache.poi.hwpf.extractor.WordExtractor;??????
27. import?org.apache.poi.openxml4j.exceptions.OpenXML4JException;??????
28. import?org.apache.poi.openxml4j.opc.OPCPackage;??????
29. import?org.apache.poi.xssf.usermodel.XSSFCell;??????
30. import?org.apache.poi.xssf.usermodel.XSSFRow;??????
31. import?org.apache.poi.xssf.usermodel.XSSFSheet;??????
32. import?org.apache.poi.xssf.usermodel.XSSFWorkbook;??????
33. import?org.apache.poi.xwpf.extractor.XWPFWordExtractor;??????
34. import?org.apache.xmlbeans.XmlException;??????
35. ?????
36. public?class?WordAndExcelExtractor?{??????
37. ?public?static?void?main(String[]?args){??????
38. ??try{??????
39. ???String?wordFile?=?"D:/松山血战.docx";??????
40. ???String?wordText2007?=?WordAndExcelExtractor.extractTextFromDOC2007(wordFile);??????
41. ???System.out.println("wordText2007======="+wordText2007);??????
42. ?????????
43. ???InputStream?is?=?new?FileInputStream("D:/XXX研发中心技术岗位职位需求.xls");?????????
44. ???String?excelText?=?WordAndExcelExtractor.extractTextFromXLS(is);?????????
45. ???System.out.println("text2003=========="?+?excelText);??????
46. ?????????
47. ???String?excelFile?=?"D:/Hello2007.xlsx";?????????
48. ???String?excelText2007?=?WordAndExcelExtractor.extractTextFromXLS2007(excelFile);??????
49. ???System.out.println("excelText2007=========="?+?excelText2007);??????
50. ?????
51. ?????????
52. ??}catch(Exception?e?){??????
53. ???e.printStackTrace();??????
54. ??}??????
55. ?}??????
56. ???????
57. ?/**????
58. ??*?@Method:?extractTextFromDOCX????
59. ??*?@Description:?从word?2003文档中提取纯文本????
60. ??*????
61. ??*?@param?????
62. ??*?@return?String????
63. ??*?@throws????
64. ??*/?????
65. ????public?static?String?extractTextFromDOC(InputStream?is)?throws?IOException?{??????
66. ????????WordExtractor?ex?=?new?WordExtractor(is);?//is是WORD文件的InputStream???????
67. ?????
68. ????????return?ex.getText();??????
69. ????}??????
70. ???????
71. ?/**????
72. ??*?@Method:?extractTextFromDOCX????
73. ??*?@Description:?从word?2007文档中提取纯文本????
74. ??*????
75. ??*?@param?????
76. ??*?@return?String????
77. ??*?@throws????
78. ??*/?????
79. ????public?static?String?extractTextFromDOC2007(String?fileName)?throws?IOException,?OpenXML4JException,?XmlException?{??????
80. ?????OPCPackage?opcPackage?=?POIXMLDocument.openPackage(fileName);??????
81. ?????POIXMLTextExtractor?ex?=?new?XWPFWordExtractor(opcPackage);?????????
82. ?????
83. ????????return?ex.getText();??????
84. ????}??????
85. ???????
86. ?/**????
87. ??*?@Method:?extractTextFromXLS????
88. ??*?@Description:?从excel?2003文档中提取纯文本????
89. ??*????
90. ??*?@param?????
91. ??*?@return?String????
92. ??*?@throws????
93. ??*/?????
94. ????@SuppressWarnings("deprecation")??????
95. ?private?static?String?extractTextFromXLS(InputStream?is)??????
96. ????????throws?IOException?{??????
97. ????????StringBuffer?content??=?new?StringBuffer();??????
98. ????????HSSFWorkbook?workbook?=?new?HSSFWorkbook(is);?//创建对Excel工作簿文件的引用???????
99. ?????
100. ????????for?(int?numSheets?=?0;?numSheets?<?workbook.getNumberOfSheets();?numSheets++)?{??????
101. ????????????if?(null?!=?workbook.getSheetAt(numSheets))?{??????
102. ????????????????HSSFSheet?aSheet?=?workbook.getSheetAt(numSheets);?//获得一个sheet??????
103. ?????
104. ????????????????for?(int?rowNumOfSheet?=?0;?rowNumOfSheet?<=?aSheet.getLastRowNum();?rowNumOfSheet++)?{??????
105. ????????????????????if?(null?!=?aSheet.getRow(rowNumOfSheet))?{??????
106. ????????????????????????HSSFRow?aRow?=?aSheet.getRow(rowNumOfSheet);?//获得一行??????
107. ?????
108. ????????????????????????for?(short?cellNumOfRow?=?0;?cellNumOfRow?<=?aRow.getLastCellNum();?cellNumOfRow++)?{??????
109. ????????????????????????????if?(null?!=?aRow.getCell(cellNumOfRow))?{??????
110. ????????????????????????????????HSSFCell?aCell?=?aRow.getCell(cellNumOfRow);?//获得列值??????
111. ??????????????????????????????????????????????????????????????????????
112. ????????????????????????????????if(aCell.getCellType()?==?HSSFCell.CELL_TYPE_NUMERIC){??????
113. ?????????????????????????????????content.append(aCell.getNumericCellValue());??????
114. ????????????????????????????????}else?if(aCell.getCellType()?==?HSSFCell.CELL_TYPE_BOOLEAN){??????
115. ?????????????????????????????????content.append(aCell.getBooleanCellValue());??????
116. ????????????????????????????????}else?{??????
117. ?????????????????????????????????content.append(aCell.getStringCellValue());??????
118. ????????????????????????????????}??????
119. ????????????????????????????}??????
120. ????????????????????????}??????
121. ????????????????????}??????
122. ????????????????}??????
123. ????????????}??????
124. ????????}??????
125. ?????
126. ????????return?content.toString();??????
127. ????}??????
128. ??????????
129. ????/**????
130. ?????*?@Method:?extractTextFromXLS2007????
131. ?????*?@Description:?从excel?2007文档中提取纯文本????
132. ?????*????
133. ?????*?@param?????
134. ?????*?@return?String????
135. ?????*?@throws????
136. ?????*/?????
137. ????private?static?String?extractTextFromXLS2007(String?fileName)?throws?Exception{??????
138. ?????StringBuffer?content?=?new?StringBuffer();??????
139. ???????????
140. ?????//构造?XSSFWorkbook?对象，strPath?传入文件路径??????????
141. ??XSSFWorkbook?xwb?=?new?XSSFWorkbook(fileName);??????
142. ????????
143. ??//循环工作表Sheet??????
144. ??for(int?numSheet?=?0;?numSheet?<?xwb.getNumberOfSheets();?numSheet++){??????
145. ???XSSFSheet?xSheet?=?xwb.getSheetAt(numSheet);???????
146. ???if(xSheet?==?null){??????
147. ????continue;??????
148. ???}??????
149. ?????????
150. ???//循环行Row??????
151. ???for(int?rowNum?=?0;?rowNum?<=?xSheet.getLastRowNum();?rowNum++){??????
152. ????XSSFRow?xRow?=?xSheet.getRow(rowNum);??????
153. ????if(xRow?==?null){??????
154. ?????continue;??????
155. ????}??????
156. ??????????
157. ????//循环列Cell??????
158. ????for(int?cellNum?=?0;?cellNum?<=?xRow.getLastCellNum();?cellNum++){??????
159. ?????XSSFCell?xCell?=?xRow.getCell(cellNum);??????
160. ?????if(xCell?==?null){??????
161. ??????continue;??????
162. ?????}??????
163. ???????????
164. ?????if(xCell.getCellType()?==?XSSFCell.CELL_TYPE_BOOLEAN){??????
165. ??????content.append(xCell.getBooleanCellValue());??????
166. ?????}else?if(xCell.getCellType()?==?XSSFCell.CELL_TYPE_NUMERIC){??????
167. ??????content.append(xCell.getNumericCellValue());??????
168. ?????}else{??????
169. ??????content.append(xCell.getStringCellValue());??????
170. ?????}??????
171. ????}??????
172. ???}??????
173. ??}??????
174. ????????
175. ??return?content.toString();??????
176. ????}??????
177. ??????????
178. }??????
179. </span>??

?

? 第三、PowerPoint的文档

?

Java代码??

1. <span?style="font-size:?medium;"><span?style="font-size:?large;">public?static?String?readPowerPoint(String?path)?{??
2. StringBuffer?content?=?new?StringBuffer("");??
3. try?{??
4. SlideShow?ss?=?new?SlideShow(new?HSLFSlideShow(new?FileInputStream(??
5. path)));//?is??
6. //?为文件的InputStream，建立SlideShow??
7. Slide[]?slides?=?ss.getSlides();//?获得每一张幻灯片??
8. for?(int?i?=?0;?i?<?slides.length;?i++)?{??
9. TextRun[]?t?=?slides[i].getTextRuns();//?为了取得幻灯片的文字内容，建立TextRun??
10. for?(int?j?=?0;?j?<?t.length;?j++)?{??
11. content.append(t[j].getText());//?这里会将文字内容加到content中去??
12. }??
13. }??
14. }?catch?(Exception?ex)?{??
15. System.out.println(ex.toString());??
16. }??
17. return?content.toString();??
18. }</span></span>??

?

?

?第四、PDF的文档

?

Java代码??

1. <span?style="font-size:?medium;"><span?style="font-size:?large;">public?static?String?readPdf(String?path)?throws?Exception?{??
2. StringBuffer?content?=?new?StringBuffer("");??
3. FileInputStream?fis?=?new?FileInputStream(path);??
4. PDFParser?p?=?new?PDFParser(fis);??
5. p.parse();??
6. PDFTextStripper?ts?=?new?PDFTextStripper();??
7. content.append(ts.getText(p.getPDDocument()));??
8. fis.close();??
9. return?content.toString().trim();??
10. }</span></span>??

?

??

?? 第五、HTML的文档，要说明的是，HTML文档我们要获取其TITLE，BODY中的内容就要先获取源文件，然后再对源文件进行标签上的过滤，很麻烦

?

Html代码??

1. <span?style="font-size:?large;">public?static?String?readHtml(String?urlString)?{??
2. StringBuffer?content?=?new?StringBuffer("");??
3. File?file?=?new?File(urlString);??
4. FileInputStream?fis?=?null;??
5. try?{??
6. fis?=?new?FileInputStream(file);??
7. BufferedReader?reader?=?new?BufferedReader(new?InputStreamReader(??
8. fis,?"utf-8"));??
9. String?line?=?null;??
10. while?((line?=?reader.readLine())?!=?null)?{??
11. content.append(line?+?"\n");??
12. }??
13. reader.close();??
14. }?catch?(Exception?e)?{??
15. e.printStackTrace();??
16. }??
17. String?contentcontentString?=?content.toString();??
18. String?htmlStr?=?contentString;?//?含html标签的字符串??
19. String?textStr?=?"";??
20. java.util.regex.Pattern?p_script;??
21. java.util.regex.Matcher?m_script;??
22. java.util.regex.Pattern?p_style;??
23. java.util.regex.Matcher?m_style;??
24. java.util.regex.Pattern?p_html;??
25. java.util.regex.Matcher?m_html;??
26. try?{??
27. String?regEx_script?=?"<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\??
28. String?regEx_style?=?"<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*??
29. String?regEx_html?=?"<[^>]+>";?//?定义HTML标签的正则表达式??
30. p_script?=?Pattern.compile(regEx_script,?Pattern.CASE_INSENSITIVE);??
31. m_script?=?p_script.matcher(htmlStr);??
32. htmlStr?=?m_script.replaceAll("");?//?过滤script标签??
33. p_style?=?Pattern.compile(regEx_style,?Pattern.CASE_INSENSITIVE);??
34. m_style?=?p_style.matcher(htmlStr);??
35. htmlStr?=?m_style.replaceAll("");?//?过滤style标签??
36. p_html?=?Pattern.compile(regEx_html,?Pattern.CASE_INSENSITIVE);??
37. m_html?=?p_html.matcher(htmlStr);??
38. htmlStr?=?m_html.replaceAll("");?//?过滤html标签??
39. textStr?=?htmlStr;??
40. }?catch?(Exception?e)?{??
41. System.err.println("Html2Text:?"?+?e.getMessage());??
42. }??
43. return?textStr;//?返回文本字符串??
44. }</span>??

?

?

?第六、TXT的文档，给TXT文本建立索引时要注意
?? 本项目实现了组合查询的功能
? //这一步如果不设置为GBK，TXT内容将全部乱码 BufferedReader reader=new BufferedReader(new InputStreamReader(is,"GBK")); 具体代码如下?

?

Java代码??

1. <span?style="font-size:?medium;"><span?style="font-size:?large;">public?static?String?readTxt(String?path)?throws?IOException?{??
2. StringBuffer?sb?=?new?StringBuffer("");??
3. InputStream?is?=?new?FileInputStream(path);??
4. //?必须设置成GBK，否则将出现乱码??
5. BufferedReader?reader?=?new?BufferedReader(new?InputStreamReader(is,??
6. "GBK"));??
7. try?{??
8. String?line?=?"";??
9. while?((line?=?reader.readLine())?!=?null)?{??
10. sb.append(line?+?"\r");??
11. }??
12. }?catch?(FileNotFoundException?e)?{??
13. e.printStackTrace();??
14. }??
15. return?sb.toString().trim();??
16. }</span></span>??

?

??

?

第七、RTF文档，rtf的转换则在javax中就有

?

Java代码??

1. <span?style="font-size:?medium;"><span?style="font-size:?large;">public?static?String?readRtf(String?path)?{??
2. String?result?=?null;??
3. File?file?=?new?File(path);??
4. try?{??
5. DefaultStyledDocument?styledDoc?=?new?DefaultStyledDocument();??
6. InputStream?is?=?new?FileInputStream(file);??
7. new?RTFEditorKit().read(is,?styledDoc,?0);??
8. result?=?new?String(styledDoc.getText(0,?styledDoc.getLength())??
9. .getBytes("iso8859-1"),?"gbk");??
10. //?提取文本，读取中文需要使用gbk编码，否则会出现乱码??
11. }?catch?(IOException?e)?{??
12. e.printStackTrace();??
13. }?catch?(BadLocationException?e)?{??
14. e.printStackTrace();??
15. }??
16. return?result;??
17. }</span></span>??

?

?

查看更多 下一篇