用于脚本的doc到html的Apache POI

时间:2015-05-12 03:51:49

标签: java

我正在使用Apache POI将doc转换为html。但脚注未转换为html。将doc文件转换为html时,doc文件中可用的脚注不存在于html文件/内容中。如何在转换后坚持这些脚注?

1 个答案:

答案 0 :(得分:1)

这样做。我希望它能帮助你......!

public static void readMyDocument(String fileName){  
    POIFSFileSystem fs = null;  
    try {  
        fs = new POIFSFileSystem(new FileInputStream(fileName));  
        HWPFDocument doc = new HWPFDocument(fs);  

        /** Read the content **/  
        readParagraphs(doc);

        int pageNumber=1;

        /** We will try reading the header for page 1**/
        readHeader(doc, pageNumber);

        /** we will try reading the footer for page 1**/
        readFooter(doc, pageNumber);


    } catch (Exception e) {
        e.printStackTrace();
    }
  }  

 public static void readParagraphs(HWPFDocument doc) throws Exception{  
    WordExtractor we = new WordExtractor(doc);  

    /**Get the total number of paragraphs**/  
    String[] paragraphs = we.getParagraphText();  
    System.out.println("Total Paragraphs: "+paragraphs.length);  

    for (int i = 0; i < paragraphs.length; i++) {  

        System.out.println("Length of paragraph "+(i +1)+": "+ paragraphs[i].length());  
        System.out.println(paragraphs[i].toString());  

    }

}

public static void readHeader(HWPFDocument doc, int pageNumber){  
    HeaderStories headerStore = new HeaderStories( doc);  
    String header = headerStore.getHeader(pageNumber);
    System.out.println("Header Is: "+header);

}

public static void readFooter(HWPFDocument doc, int pageNumber){   
    HeaderStories headerStore = new HeaderStories( doc);  
    String footer = headerStore.getFooter(pageNumber);  
    System.out.println("Footer Is: "+footer);  

}