java POI解析获取word文件内容

1、需要的pom文件依赖

<dependency>
	<groupId>org.apache.poi</groupId>
	<artifactId>poi</artifactId>
	<version>4.1.2</version>
</dependency>
 <dependency>
	<groupId>org.apache.poi</groupId>
	<artifactId>poi-ooxml</artifactId>
	<version>4.1.0</version>
</dependency>
<!-- POI-word文件处理需要 -->
<dependency>
	<groupId>org.apache.poi</groupId>
	<artifactId>poi-scratchpad</artifactId>
	<version>4.1.2</version>
</dependency>

2、word分为2003版本(.doc)，和2007版本（.docx），所对应读取的方式不一样。

/**
     * 获取正文文件内容，docx方法
     *
     * @param path
     * @return
     */
    public Map<String, String> getContentDocx(String path) {
        Map<String, String> map = new HashMap();
        StringBuffer content = new StringBuffer("");
        String result = "0";  // 0表示获取正常，1表示获取异常
        InputStream is = null;
        try {
            is = new FileInputStream(new File(path));
            // 2007版本的word
            XWPFDocument xwpf = new XWPFDocument(is);    // 2007版本，仅支持docx文件处理
            List<XWPFParagraph> paragraphs = xwpf.getParagraphs();
            if (paragraphs != null && paragraphs.size() > 0) {
                for (XWPFParagraph paragraph : paragraphs) {
                    if (!paragraph.getParagraphText().startsWith("    ")) {
                        content.append("    ").append(paragraph.getParagraphText().trim()).append("\r\n");
                    } else {
                        content.append(paragraph.getParagraphText());
                    }
                }
            }
        } catch (Exception e) {
            logger.error("docx解析正文异常:" + e);
            result = "1"; // 出现异常
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch (IOException e) {
                    logger.error("" + e);
                }
            }
            map.put("result", result);
            map.put("content", content.toString());
        }
        return map;
    }

    /**
     * 获取正文文件内容，doc方法
     *
     * @param path
     * @return
     */
    public Map<String, String> getContentDoc(String path) {
        Map<String, String> map = new HashMap();
        StringBuffer content = new StringBuffer("");
        String result = "0";  // 0表示获取正常，1表示获取异常
        InputStream is = null;
        try {
            is = new FileInputStream(new File(path));
            // 2003版本的word
            WordExtractor extractor = new WordExtractor(is);  // 2003版本 仅doc格式文件可处理，docx文件不可处理
            String[] paragraphText = extractor.getParagraphText();   // 获取段落，段落缩进无法获取，可以在前添加空格填充
            if (paragraphText != null && paragraphText.length > 0) {
                for (String paragraph : paragraphText) {
                    if (!paragraph.startsWith("    ")) {
                        content.append("    ").append(paragraph.trim()).append("\r\n");
                    } else {
                        content.append(paragraph);
                    }
                }
            }
        } catch (Exception e) {
            logger.error("doc解析正文异常:" + e);
            result = "1"; // 出现异常
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch (IOException e) {
                    logger.error("" + e);
                }
            }
            map.put("result", result);
            map.put("content", content.toString());
        }
        return map;
    }

    /**
     * 获取正文文件内容，wps方法
     *
     * @param path
     * @return
     */
    public Map<String, String> getContentWps(String path) {
        Map<String, String> map = new HashMap();
        StringBuffer content = new StringBuffer("");
        String result = "0";  // 0表示获取正常，1表示获取异常
        InputStream is = null;
        try {
            is = new FileInputStream(new File(path));
            // wps版本word
            HWPFDocument hwpf = new HWPFDocument(is);
            WordExtractor wordExtractor = new WordExtractor(hwpf);
            // 文档文本内容
            String[] paragraphText1 = wordExtractor.getParagraphText();
            if (paragraphText1 != null && paragraphText1.length > 0) {
                for (String paragraph : paragraphText1) {
                    if (!paragraph.startsWith("    ")) {
                        content.append("     ").append(paragraph.trim()).append("\r\n");
                    } else {
                        content.append(paragraph);
                    }
                }
            }
        } catch (Exception e) {
            logger.error("wps解析正文异常:" + e);
            result = "1"; // 出现异常
        } finally {
            if (is != null) {
                try {
                    is.close();
                } catch (IOException e) {
                    logger.error("" + e);
                }
            }
            map.put("result", result);
            map.put("content", content.toString());
        }
        return map;
    }

3、上面的代码示例获取到的仅是word文件中的文字内容，不包含图片，表格等数据。下方的示例代码可以获取word内容，包含获取页眉，页脚，图片，表格等进行操作。具体可以查看下源码或者搜索查看。

            XWPFDocument doc = new XWPFDocument(is);
            List<XWPFParagraph> paras = doc.getParagraphs();
            if (!CollectionUtils.isEmpty(paras)) {
               for (XWPFParagraph para : paras) {
                    //当前段落的属性
                    //CTPPr pr = para.getCTP().getPPr();
                    System.out.println(para.getText());
                }
            }

学海无涯苦作舟！！！