html文本,任意位置添加内容,转成doc或者docx文档,输出为页面视图模式
@Test
public void htmlToWord2() throws Exception {
InputStream bodyIs = new FileInputStream("C:\\Users\\32628\\Desktop\\2.html");
String body = this.getContent(bodyIs);
//这段内容加上以后输出格式为页面视图模式
String s = "<html xmlns:v=\"urn:schemas-microsoft-com:vml\" xmlns:o=\"urn:schemas-microsoft-com:office:office\"\n" +
"xmlns:w=\"urn:schemas-microsoft-com:office:word\" xmlns:m=\"http://schemas.microsoft.com/office/2004/12/omml\"\n" +
"xmlns=\"http://www.w3.org/TR/REC-html40\"><head>\n" +
" <!--[if gte mso 9]><xml><w:WordDocument><w:View>Print</w:View><w:TrackMoves>false</w:TrackMoves><w:TrackFormatting/><w:ValidateAgainstSchemas/><w:SaveIfXMLInvalid>false</w:SaveIfXMLInvalid><w:IgnoreMixedContent>false</w:IgnoreMixedContent><w:AlwaysShowPlaceholderText>false</w:AlwaysShowPlaceholderText><w:DoNotPromoteQF/><w:LidThemeOther>EN-US</w:LidThemeOther><w:LidThemeAsian>ZH-CN</w:LidThemeAsian><w:LidThemeComplexScript>X-NONE</w:LidThemeComplexScript><w:Compatibility><w:BreakWrappedTables/><w:SnapToGridInCell/><w:WrapTextWithPunct/><w:UseAsianBreakRules/><w:DontGrowAutofit/><w:SplitPgBreakAndParaMark/><w:DontVertAlignCellWithSp/><w:DontBreakConstrainedForcedTables/><w:DontVertAlignInTxbx/><w:Word11KerningPairs/><w:CachedColBalance/><w:UseFELayout/></w:Compatibility><w:BrowserLevel>MicrosoftInternetExplorer4</w:BrowserLevel><m:mathPr><m:mathFont m:val=\"Cambria Math\"/><m:brkBin m:val=\"before\"/><m:brkBinSub m:val=\"--\"/><m:smallFrac m:val=\"off\"/><m:dispDef/><m:lMargin m:val=\"0\"/> <m:rMargin m:val=\"0\"/><m:defJc m:val=\"centerGroup\"/><m:wrapIndent m:val=\"1440\"/><m:intLim m:val=\"subSup\"/><m:naryLim m:val=\"undOvr\"/></m:mathPr></w:WordDocument></xml><![endif]-->\n" +
"</head>";
//拼一个标准的HTML格式文档
String content = s + body;
StringBuilder stringBuilder2 = new StringBuilder(content);
//获取目标字符串待插入位置前的字符下标
//将目标字符串内容插入到该下标
int index = stringBuilder2.indexOf("name");
StringBuilder builder = stringBuilder2.insert(index, "张三");
String s1 = builder.toString();
System.out.println(s1);
InputStream is = new ByteArrayInputStream(s1.getBytes("GBK"));
OutputStream os = new FileOutputStream("C:\\Users\\32628\\Desktop\\1.docx");
this.inputStreamToWord(is, os);
}
/**
* 把is写入到对应的word输出流os中
* 不考虑异常的捕获,直接抛出
*
* @param is
* @param os
* @throws IOException
*/
private void inputStreamToWord(InputStream is, OutputStream os) throws IOException {
POIFSFileSystem fs = new POIFSFileSystem();
//对应于org.apache.poi.hdf.extractor.WordDocument
fs.createDocument(is, "WordDocument");
fs.writeFilesystem(os);
os.close();
is.close();
}
/**
* 把输入流里面的内容以UTF-8编码当文本取出。
* 不考虑异常,直接抛出
*
* @param ises
* @return
* @throws IOException
*/
private String getContent(InputStream... ises) throws IOException {
if (ises != null) {
StringBuilder result = new StringBuilder();
BufferedReader br;
String line;
for (InputStream is : ises) {
br = new BufferedReader(new InputStreamReader(is, "UTF-8"));
while ((line = br.readLine()) != null) {
result.append(line);
}
}
return result.toString();
}
return null;
}
}
借鉴很多大佬的资料,总结出一份好用的,有需要朋友拿去