【Java开发记录】Java POI解析Word提取数据存储在Excel（二）

<dependency>            <groupId>org.apache.poi</groupId>            <artifactId>poi</artifactId>            <version>3.17</version>        </dependency>
        <dependency>            <groupId>org.apache.poi</groupId>            <artifactId>poi-ooxml</artifactId>            <version>3.17</version>        </dependency>        <dependency>            <groupId>org.apache.poi</groupId>            <artifactId>poi-scratchpad</artifactId>            <version>3.17</version>        </dependency>        <dependency>            <groupId>org.apache.poi</groupId>            <artifactId>ooxml-schemas</artifactId>            <version>1.1</version>        </dependency>        <dependency>            <groupId>org.apache.poi</groupId>            <artifactId>poi-ooxml-schemas</artifactId>            <version>3.17</version>        </dependency>

public class GetWord {public static void main(String[] args) {        try {            InputStream is = new FileInputStream(new File("path"));  //需要将文件路更改为word文档所在路径。            POIFSFileSystem fs = new POIFSFileSystem(is);            HWPFDocument document = new HWPFDocument(fs);            Range range = document.getRange();
            CharacterRun run1 = null;//用来存储第一行内容的属性            CharacterRun run2 = null;//用来存储第二行内容的属性            int q=1;            for (int i = 0; i < range.numParagraphs()-2; i++) {                Paragraph para1 = range.getParagraph(i);// 获取第i段                Paragraph para2 = range.getParagraph(i+1);// 获取第i段                int t=i;              //记录当前分析的段落数
                String paratext1 = para1.text();   //当前段落和下一段                String paratext2 = para2.text();                run1=para1.getCharacterRun(0);                run2=para2.getCharacterRun(0);                if (paratext1.length() > 0&&paratext2.length() > 0) {                    //这个if语句为的是去除大标题，连续三个段落字体大小递减就跳过                    if(run1.getFontSize()>run2.getFontSize()&&run2.getFontSize()>range.getParagraph(i+2).getCharacterRun(0).getFontSize()) {                        break;                    }                    //连续两段字体格式不同                    if(run1.getFontSize()>run2.getFontSize()) {                        content=paratext2;                        run1=run2;  //从新定位run1  run2                        run2=range.getParagraph(t+2).getCharacterRun(0);                        t=t+1;                        while(run1.getFontSize()==run2.getFontSize()) {                            //连续的相同                            Content+=range.getParagraph(t+1).text();                            if(content.matches("是否系统自身渗透结果")) break;                                                        if(content.contains(":")||content.contains("/")){//如果是http或者是IP+端口形式                                word.setName(getDomain(content));//ip
                            }else{//纯IP形式                                word.setName(content);//ip                            }                            word.setAsset_name(paratext1);//标题                            run1=run2;                            run2=range.getParagraph(t+i).getCharacterRun(0);                            t++;        ……..                              }                  ………                    }                        if(paratext1.matches("中危")||paratext1.matches("很高")||paratext1.matches("低危")){                           list2.add(paratext1);                        }                }            }                    if(word1.getAsset_name()==wordname.getAsset_name())){…..                        wordend.setId(num);                        wordend.setName(word1.getName());                        wordend.setAsset_name(word1.getAsset_name());
                        if(wordname.getAvailability_assignment().equals("很高")){                            wordend.setAvailability_assignment("5");                        }                        if(wordname.getAvailability_assignment().equals("高危")){                            wordend.setAvailability_assignment("4");                        }                        if(wordname.getAvailability_assignment().equals("中危")){                            wordend.setAvailability_assignment("3");                        }                        if(wordname.getAvailability_assignment().equals("低危")){                            wordend.setAvailability_assignment("2");                        }                        wordend.setRisk("网络攻击");                        wordmax.add(wordend);                        num++;      ……                    }                }            }            System.out.println("------------------Finished-详情查看-中间文档转excel.xlsx------------------");            //Excel无模版导出            ExcelUtil.getInstar ().exportl(wordmax, Word.class, "中间文档转excel.xlsx");        } catch (Exception e) {            e.printStackTrace();        }    }   } }

public class Test{    public static void main(String[] args){        String url = "www.abc.def.com.cn/123456 ";        String url1 = "192.168.1.100/admin";        System.out.println(getDomain(url));        System.out.println(getDomain(url1));    }    private static String getDomain(String url){        String regex = "^(?:[a-zA-Z]+[.])?(\w+([.]\w+)*)/.*$";        Matcher matcher = Pattern.compile(regex).matcher(url);        String result = null;        if(matcher.find()){            result = matcher.group(1);        }        return result;    }}

个人知乎：https://www.zhihu.com/people/fu-wei-43-69/columns个人简书：https://www.jianshu.com/u/bf0e38a8d400个人CSDN：https://blog.csdn.net/qq_37602797/category_10169006.html个人博客园：https://www.cnblogs.com/thelostworld/FREEBUF主页：https://www.freebuf.com/author/thelostworld?type=article语雀博客主页：https://www.yuque.com/thelostworld