上传doc,pdf,ppt,png,jpg,html文件并解析内容

依赖:

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>4.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>4.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>4.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.12</version>
        </dependency>

 controller:

@DataLog(operationName = "批量新增人才", operationDesc = "上传文件", methodType = MethodTypeEnum.ADD_TYPE)
    @ApiOperation(value = "批量新增人才", notes = "批量新增人才")
    @PostMapping(Urls.RecA01.uploadFileAddA01)
    @ApiImplicitParams({
            @ApiImplicitParam(name = "state", value = "人才库类型", required = true)
    })
    public JsonObject<Object> uploadFileAddA01(@RequestParam(value = "file") MultipartFile[] file, String state, HttpServletRequest request) throws IOException {
        String result = "";
        Map<String, String> param = new HashMap<>();
        param.put("state", state);
        userDir = fileConfigProperties.getResources();
        // 存放文件目录
        //TODO 此处获取了配置文件信息的值  需在配置文件新增属性
        String folderSources = userDir + File.separator + "temp" + File.separator + "rckfile";
        // 设置日期为文件夹名称
        SimpleDateFormat df = new SimpleDateFormat("yyyyMMddHHmmss");
        String folderName = df.format(new Date()).toString();
        String folderPath = folderSources + File.separator + folderName;
        File rmbFile = new File(folderPath);
        // 文件夹如果不存在就创建该文件夹
        if (!rmbFile.exists()) {
            rmbFile.mkdirs();
        }
        for (int i = 0; file != null && i < file.length; i++) {
            // 获得文件名：
            String name = file[i].getOriginalFilename();
            // 获得文件名,不带后缀
            String filename = name.substring(0, name.lastIndexOf('.'));
            // 获得输入流：
            InputStream streamList = file[i].getInputStream();
            File newPhotoFile = new File(folderPath + File.separator + name);
            OutputStream out = new FileOutputStream(newPhotoFile);
            // 保存文件
            boolean writeFlag = this.write(streamList, out);
            if (writeFlag) {
                out.flush();
                out.close();
            }
        }
        // 处理文件夹中文件数据
        result = recA01Service.uploadFileAddA01(folderPath, param, request);
        return new JsonSuccessObject<>(result);
    }

    public boolean write(InputStream in, OutputStream out) {
        boolean flag = true;
        int BUFSIZE = 65536;
        int s;
        try {
            byte[] buf = new byte[BUFSIZE];
            while ((s = in.read(buf)) > -1) {
                out.write(buf, 0, s);
            }
        } catch (IOException e) {
            flag = false;
            e.printStackTrace();
            logger.error("异常信息：" + e.getMessage());
        }
        return flag;
    }

impl:

@Value("${ocrServe.url}")
    private String ocrUrl;

    public String getocrUrl() {
        return ocrUrl;
    }

@Override
    public String uploadFileAddA01(String path, Map<String, String> param, HttpServletRequest request) throws IOException {
        // 获取文件夹下文件
        File file = new File(path);
        File[] files = file.listFiles();
        // 循环处理文件
        for (File f : files) {
            //文件名称
            String fileName = f.getName();
            //文件类型
            String suffix = fileName.substring(fileName.lastIndexOf('.') + 1);
            //人才库类型
            String state = param.get("state");
            String text = "";
            // 解析简历
            if (("doc").equals(suffix) || ("docx").equals(suffix)) {
                try {
                    if (("doc").equals(suffix)) {
                        // 根据文件流获得文档对象
                        InputStream is = new FileInputStream(f);
                        WordExtractor re = new WordExtractor(is);
                        text = re.getText();
                        re.close();
                    } else if (("docx").equals(suffix)) {
                        OPCPackage opcPackage = POIXMLDocument.openPackage(f.getPath());
                        POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
                        text = extractor.getText();
                        extractor.close();
                    }
                } catch (Exception e1) {
                    e1.printStackTrace();
                }
            } else if (("pdf").equals(suffix)) {
                PDDocument document = null;
                try {
                    document = PDDocument.load(f);
                    int pageSize = document.getNumberOfPages();
                    // 一页一页读取
                    for (int i = 0; i < pageSize; i++) {
                        // 文本内容
                        PDFTextStripper stripper = new PDFTextStripper();
                        // 设置按顺序输出
                        stripper.setSortByPosition(true);
                        stripper.setStartPage(i + 1);
                        stripper.setEndPage(i + 1);
                        text = text + stripper.getText(document);
                    }
                } catch (IOException e) {
                } finally {
                    document.close();
                }
            } else if (("htm").equals(suffix) || ("html").equals(suffix)) {
                // 获取HTML文件流
                StringBuffer htmlSb = new StringBuffer();
                try {
                    BufferedReader br = new BufferedReader(new InputStreamReader(
                            new FileInputStream(f), "utf-8"));
                    while (br.ready()) {
                        htmlSb.append(br.readLine());
                    }
                    br.close();
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                }
                // HTML文件字符串
                text = htmlSb.toString();
            } else if (("png").equals(suffix) || ("jpg").equals(suffix) || ("jpeg").equals(suffix)) {
                // post请求 http://192.168.4.188:8869/paddle_ocr
                HttpClient client = new HttpClient();
                PostMethod postMethod = new PostMethod(getocrUrl());
                try {
                    // FilePart：用来上传文件的类,file即要上传的文件
                    FilePart fp = new FilePart("file", f);
                    Part[] parts = {fp};
                    // 对于MIME类型的请求，httpclient建议全用MulitPartRequestEntity进行包装
                    MultipartRequestEntity mre = new MultipartRequestEntity(parts, postMethod.getParams());
                    postMethod.setRequestEntity(mre);
                    // 由于要上传的文件可能比较大 , 因此在此设置最大的连接超时时间
                    client.getHttpConnectionManager().getParams().setConnectionTimeout(50000);
                    int status = client.executeMethod(postMethod);
                    if (status == HttpStatus.SC_OK) {
                        // 获取返回数据
                        InputStream inputStream = postMethod.getResponseBodyAsStream();
                        BufferedReader br = new BufferedReader(new InputStreamReader(inputStream));
                        //<1>创建字节数组输出流，用来输出读取到的内容
                        ByteArrayOutputStream baos = new ByteArrayOutputStream();
                        //<2>创建缓存大小
                        byte[] buffer = new byte[1024]; // 1KB
                        //每次读取到内容的长度
                        int len = -1;
                        //<3>开始读取输入流中的内容
                        while ((len = inputStream.read(buffer)) != -1) { //当等于-1说明没有数据可以读取了
                            baos.write(buffer, 0, len);   //把读取到的内容写到输出流中
                        }
                        //<4> 把字节数组转换为字符串
                        String json = baos.toString();
                        // 获取"text": "女，17302731183", "text_region":中间的信息
                        String regEx = "(\"text\": \")(.*?)(\", \"text_region\")";
                        Pattern p = Pattern.compile(regEx);
                        Matcher m = p.matcher(json);
                        while (m.find()) {
                            text = text + m.group(2);
                        }
                    }
                } catch (Exception e) {
                    e.printStackTrace();
                } finally {
                    // 释放连接
                    postMethod.releaseConnection();
                }
            } else if (("ppt").equals(suffix) || ("pptx").equals(suffix)) {
                StringBuilder sb = new StringBuilder();
                FileInputStream in = new FileInputStream(f.getPath());
                try {
                    XMLSlideShow xmlSlideShow = new XMLSlideShow(in);
                    List<XSLFSlide> slides = xmlSlideShow.getSlides();
                    for (XSLFSlide slide : slides) {
                        CTSlide rawSlide = slide.getXmlObject();
                        CTGroupShape gs = rawSlide.getCSld().getSpTree();
                        CTShape[] shapes = gs.getSpArray();
                        for (CTShape shape : shapes) {
                            CTTextBody tb = shape.getTxBody();
                            if (null == tb) {
                                continue;
                            }
                            CTTextParagraph[] paras = tb.getPArray();
                            for (CTTextParagraph textParagraph : paras) {
                                CTRegularTextRun[] textRuns = textParagraph.getRArray();
                                for (CTRegularTextRun textRun : textRuns) {
                                    sb.append(textRun.getT());
                                }
                            }
                        }
                    }
                    text = sb.toString();
                    xmlSlideShow.close();
                } catch (Exception e) {
                    e.printStackTrace();
                }
            }
            // 提取姓名
            String name = getName(text);
            // 提取手机号
            String phone = getPhoneNo(text);
            // 提取邮箱
            String email = getEmail(text);
            if (name != null && name != "") {
                // 添加人才库方法
                this.saveRecA01(name, phone, email, null, state, request);
            } else {
                return "该简历中不存在用户姓名!";
            }

        }
        return "导入成功";
    }

application.yml

 提取姓名方法，不确定人名是一位还是两位的情况

public static String getName(String str) {
        // 定义姓名为开头
        String start = "(姓名)([\\s\\S]*)";
        // 定义姓氏开头的正则
        String surname = "(王|李|张|刘|陈|杨|黄|赵|吴|周|徐|孙|马|朱|胡|郭|何|高|林|罗|郑|梁|谢|宋|唐|许|韩|冯|邓|曹|彭|曾" +
                "|养|须|丰|巢|蒯|相|后|红|权逯|盖益|桓|公|万俟|司马|上官|夏侯|诸葛|闻人|东方|赫连|皇甫|尉迟|公羊|澹台" +
                "|公冶|宗政|濮阳|淳于|单于|太叔|申屠|公孙|仲孙|轩辕|令狐|钟离|宇文|长孙|慕容|鲜于|闾丘|司徒|司空|亓官" +
                "|司寇|仉|督|子车|颛孙|端木|巫马|公西|漆雕|乐正|壤驷|公良|拓跋|夹谷|宰父|谷粱|法|汝|钦|段干|百里|东郭" +
                "|南门|呼延|归海|羊舌|微生|帅|缑|亢|况|郈|琴|梁丘|左丘|东门|西门|佘|佴|伯|赏|南宫|墨|哈|谯" +
                "|肖|田|董|袁|潘|于|蒋|蔡|余|杜|叶|程|苏|魏|吕|丁|任|沈|姚|卢|姜|崔|钟|谭|陆|汪|范|金|石|廖|贾|夏|韦|傅" +
                "|方|白|邹|孟|熊|秦|邱|江|尹|薛|闫|段|雷|侯|龙|史|黎|贺|顾|毛|郝|龚|邵|万|钱|覃|武|戴|孔|汤|庞|樊|兰|殷" +
                "|施|陶|洪|翟|安|颜|倪|严|牛|温|芦|季|俞|章|鲁|葛|伍|申|尤|毕|聂|柴|焦|向|柳|邢|岳|齐|沿|梅|莫|庄|辛|管" +
                "|祝|左|涂|谷|祁|时|舒|耿|牟|卜|路|詹|关|苗|凌|费|纪|靳|盛|童|欧|甄|项|曲|成|游|欧阳|裴|席|卫|查|屈|鲍|位" +
                "|覃|霍|翁|隋|植|甘|景|薄|单|包|司|柏|宁|柯|阮|桂|闵|阳|解|强|丛|华|车|冉|房|边|辜|吉|饶|刁|瞿|戚|丘" +
                "|古|米|池|滕|晋|苑|邬|臧|畅|宫|来|嵺|苟|全|褚|廉|简|娄|盖|符|奚|木|穆|党|燕|郎|邸|冀|谈|姬|屠|连|郜|晏" +
                "|栾|郁|商|蒙|计|喻|揭|窦|迟|宇|敖|糜|鄢|冷|卓|花|艾|蓝|都|巩|稽|井|练|仲|乐|虞|卞|封|竺|冼|原|官|衣|楚" +
                "|佟|栗|匡|宗|应|台|巫|鞠|僧|桑|荆|谌|银|扬|明|沙|薄|伏|岑|习|胥|保|和|蔺|水|云|昌|凤|酆|常|皮|康|元|平" +
                "|萧|湛|禹|无|贝|茅|麻|危|骆|支|咎|经|裘|缪|干|宣|贲|杭|诸|钮|嵇|滑|荣|荀|羊|於|惠|家|芮|羿|储|汲|邴|松" +
                "|富|乌|巴|弓|牧|隗|山|宓|蓬|郗|班|仰|秋|伊|仇|暴|钭|厉|戎|祖|束|幸|韶|蓟|印|宿|怀|蒲|鄂|索|咸|籍|赖|乔" +
                "|阴|能|苍|双|闻|莘|贡|逢|扶|堵|宰|郦|雍|却|璩|濮|寿|通|扈|郏|浦|尚|农|别|阎|充|慕|茹|宦|鱼|容|易|慎|戈" +
                "|庚|终|暨|居|衡|步|满|弘|国|文|寇|广|禄|阙|东|殴|殳|沃|利|蔚|越|夔|隆|师|厍|晃|勾|融|訾|阚|那|空|毋|乜" +
                "|笪|年|爱|仝|代)";
        // 中文正则
        String type = "([\u4E00-\u9FA5])";
        // 判断有一个字还是两个字
        // 取到姓名及数据
        for (int i = 0; i < 2; i++) {
            String regEx = "";
            if (i == 0) {
                regEx = start + surname + type + type;
            } else {
                regEx = start + surname + type;
            }
            Pattern p = Pattern.compile(regEx);
            Matcher m = p.matcher(str);
            while (m.find()) {
                // 姓名：张三
                String personName = m.group();
                // 取到数据
                String name = "";
                if (personName != null) {
                    String regEx1 = "";
                    if (i == 0) {
                        regEx1 = surname + type + type;
                    } else {
                        regEx1 = surname + type;
                    }
                    Pattern p1 = Pattern.compile(regEx1);
                    Matcher m1 = p1.matcher(personName);
                    while (m1.find()) {
                        name = m1.group();
                        return name;
                    }
                }
            }
        }
        return null;
    }

提取手机号

public static String getPhoneNo(String text) {
        //手机号正则
        String regExp = "(1[3-9]\\d{9})";
        Pattern phonePattern = Pattern.compile(regExp);
        Matcher matcher = phonePattern.matcher(text);
        while (matcher.find()) {
            return matcher.group();
        }
        return null;
    }

提取邮箱

public static String getEmail(String text) {
        //邮箱正则
        String regex = "[a-za-z0-9_-]+@\\w+\\.[a-z]+(]+)?";
        Pattern phonePattern = Pattern.compile(regex);
        Matcher matcher = phonePattern.matcher(text);
        while (matcher.find()) {
            return matcher.group();
        }
        return null;
    }