富文本解析

之前做爬虫，写了一个解析word,execl,pdf,ppd获取文本内容的工具类，主要使用到poi,pdfbox。代码献上

 

import java.io.IOException;
import java.io.InputStream;
import java.util.List;

import org.apache.pdfbox.cos.COSDocument;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
import org.apache.poi.POIXMLDocument;
import org.apache.poi.POIXMLTextExtractor;
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.usermodel.SlideShow;
import org.apache.poi.hssf.usermodel.HSSFCell;
import org.apache.poi.hssf.usermodel.HSSFDateUtil;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.xslf.usermodel.XMLSlideShow;
import org.apache.poi.xslf.usermodel.XSLFSlide;
import org.apache.poi.xssf.usermodel.XSSFSheet;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.openxmlformats.schemas.drawingml.x2006.main.CTRegularTextRun;
import org.openxmlformats.schemas.drawingml.x2006.main.CTTextBody;
import org.openxmlformats.schemas.drawingml.x2006.main.CTTextParagraph;
import org.openxmlformats.schemas.presentationml.x2006.main.CTGroupShape;
import org.openxmlformats.schemas.presentationml.x2006.main.CTShape;
import org.openxmlformats.schemas.presentationml.x2006.main.CTSlide;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.springframework.stereotype.Service;

import com.jrtech.riskcontrol.modules.crawl.service.IFileParseService;

@Service
public class FileParseService implements IFileParseService{
	private static Logger logger = LoggerFactory.getLogger(FileParseService.class);
	
	@Override
	public String parseWord2003(InputStream inputStream) throws IOException{
		try {
			logger.info("parse Word 2003 begin");
			WordExtractor ex = new WordExtractor(inputStream);
			return ex.getText();
		} finally{
			if (inputStream!=null) {
				inputStream.close();
			}
		}
	}

	@Override
	public String parseWord2007(InputStream inputStream) throws Exception{
		try {
			logger.info("parse Word 2007 begin");
			OPCPackage opcPackage = OPCPackage.open(inputStream);
			POIXMLTextExtractor ex = new XWPFWordExtractor(opcPackage);
			return ex.getText();
		} finally{
			if (inputStream!=null) {
				inputStream.close();
			}
		}
	}

	@Override
	public String parsePPT2003(InputStream inputStream) throws IOException {
        try {
        	logger.info("parse PPT 2003 begin");
        	StringBuffer content = new StringBuffer("");
            SlideShow ss = new SlideShow(new HSLFSlideShow(inputStream));
            Slide[] slides = ss.getSlides();
            for (int i = 0; i < slides.length; i++) {
                TextRun[] t = slides[i].getTextRuns();
                for (int j = 0; j < t.length; j++) {
                    content.append(t[j].getText());
                }
                content.append(slides[i].getTitle());
            }
            return content.toString();
        } finally {
        	if (inputStream!=null) {
				inputStream.close();
			}
        }
	}

	@Override
	public String parsePPT2007(InputStream inputStream) throws IOException{
        try {
        	logger.info("parse PPT 2007 begin");
            XMLSlideShow xmlSlideShow = new XMLSlideShow(inputStream);
            XSLFSlide[] slides = xmlSlideShow.getSlides();
            StringBuilder sb = new StringBuilder();
            for (XSLFSlide slide : slides) {
                CTSlide rawSlide = slide.getXmlObject();
                CTGroupShape gs = rawSlide.getCSld().getSpTree();
                List<CTShape> shapes = gs.getSpList();
                for (CTShape shape : shapes) {
                    CTTextBody tb = shape.getTxBody();
                    if (null == tb){
                    	continue;
                    }
                    List<CTTextParagraph> paras = tb.getPList();
                    for (CTTextParagraph textParagraph : paras) {
                    	List<CTRegularTextRun> textRuns = textParagraph.getRList();
                        for (CTRegularTextRun textRun : textRuns) {
                            sb.append(textRun.getT());
                        }
                    }
                }
            }
            return sb.toString();
        }finally{
        	if (inputStream!=null) {
				inputStream.close();
			}
        }
	}

	@Override
	public String parsePDF(InputStream inputStream) throws IOException{
		try {
			logger.info("parse PDF begin");
			PDFTextStripper stripper = new PDFTextStripper();
			PDFParser parser = new PDFParser(inputStream);
			parser.parse();
			COSDocument cosDoc = parser.getDocument();
			String pdfText = stripper.getText(new PDDocument(cosDoc));
			return pdfText;
		}finally{
			if (inputStream!=null) {
				inputStream.close();
			}
		}
	}

	@Override
	public String parseExecl(InputStream inputStream) throws IOException{
		try {
			logger.info("parse Execl begin");
			StringBuffer buff = new StringBuffer("");
			Workbook wb = null;
			// 创建对Excel工作簿文件的引用
			if (POIFSFileSystem.hasPOIFSHeader(inputStream)) {
				wb = new HSSFWorkbook(inputStream);
			}
			if (POIXMLDocument.hasOOXMLHeader(inputStream)) {
				wb = new XSSFWorkbook(inputStream);
			}
			// 创建对工作表的引用。
		    int sheetSize =  wb.getNumberOfSheets();
			for (int sheetNum = 0; sheetNum < sheetSize; sheetNum++) {
				if (null != wb.getSheetAt(sheetNum)) {
					Sheet sheet = null;
					if(wb instanceof HSSFWorkbook){
						sheet = (HSSFSheet) wb.getSheetAt(sheetNum);
					}else {
						sheet = (XSSFSheet) wb.getSheetAt(sheetNum);
					}
					int rowSize = sheet.getLastRowNum();
					for (int rowNum = 0; rowNum <= rowSize; rowNum++) {
						if (null != sheet.getRow(rowNum)) {
							Row row = sheet.getRow(rowNum);
							int cellSize = row.getLastCellNum();
							for (int cellNum = 0; cellNum <= cellSize; cellNum++) {
								if (null != row.getCell(cellNum)) {
									Cell cell = row.getCell(cellNum);
									int typeId = cell.getCellType();
									switch (typeId) {
										case HSSFCell.CELL_TYPE_NUMERIC:
											if (HSSFDateUtil.isCellDateFormatted(cell)) {
												buff.append(cell.getDateCellValue());
											}else {
												buff.append(cell.getNumericCellValue());
											}
											break;
										case HSSFCell.CELL_TYPE_STRING:
											buff.append(cell.getStringCellValue());
											break;
									}
								}
							}
						}
					}
				}
			}
			return buff.toString();
		}finally{
			if (inputStream != null) {
				inputStream.close();
			}
		}
	}
}

 

转载于:https://my.oschina.net/xiaoen/blog/798617