使用itextpdf提取pdf内容

package test;

import java.io.FileInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Pattern;

import org.apache.pdfbox.cos.COSDocument;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.util.PDFTextStripper;

import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.PdfTextExtractor;

public class UploadUtils {
    
    private final static Pattern pattern = Pattern.compile("\d+");
    private final static int stateParaOverFlag = 800;
    private final static int thankParaOverFlag = 800;
    
    /**
     * 读取pdf参考文献内容
     * 
     * @param s
     * @return
     */
    public String readPdf(String filePath) {
        StringBuilder buffer = new StringBuilder();
        FileInputStream fis = null;
        PdfReader pdfReader = null;
        COSDocument cosDocument = null;
        String[] paragraphs = null;
        PDFParser p;
        boolean addBool = true;
        boolean judgeState = false;
        boolean judgeThank = false;
        StringBuilder tempSb = new StringBuilder();
        try {
            fis = new FileInputStream(filePath);
            p = new PDFParser(fis);
            p.parse();
            cosDocument = p.getDocument();
            // 加密文档判断
            if (cosDocument.isEncrypted()) {
                StringBuilder tempContent = new StringBuilder();
                pdfReader = new PdfReader(filePath);
                int i = pdfReader.getNumberOfPages();
                for (int j = 1; j <= i; j++) {
                    tempContent.append(PdfTextExtractor.getTextFromPage(pdfReader, j));
                }
                paragraphs = tempContent.toString().split("
");
            } else {
                PDFTextStripper ts = new PDFTextStripper();
                paragraphs = ts.getText(p.getPDDocument()).split("
");
            }
            boolean mark = false;
            List<Integer> errornum = new ArrayList<Integer>();
            int flag = 0;
            int endRange = paragraphs.length * 70 / 100;
            int rangeFlag = 0;
            for (String lineContent : paragraphs) {
                if (judgeState) {
                    tempSb.append(lineContent);
                    if (tempSb.length() >= stateParaOverFlag) {
                        judgeState = false;
                        addBool = true;
                        tempSb.delete(0, tempSb.length() - 1);
                    }
                }
                if (judgeThank) {
                    tempSb.append(lineContent);
                    if (tempSb.length() >= thankParaOverFlag) {
                        judgeThank = false;
                        addBool = true;
                        tempSb.delete(0, tempSb.length() - 1);
                    }
                }
                if (addBool) {
                    buffer.append(lineContent);
                }
                if (mark && rangeFlag >= endRange) {
                    if (lineContent.length() < 5) {
                        errornum.add(++flag);
                        rangeFlag++;
                        continue;
                    }
                    if (pattern.matcher(lineContent.substring(0, 5)).find()) {
                        if (flag != 0) {
                            flag = 0;
                            errornum.clear();
                        }
                    } else {
                        errornum.add(++flag);
                    }
                    if (errornum.size() > 2) {
                        mark = false;
                    }
                }
                rangeFlag++;
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (fis != null) {
                try {
                    fis.close();
                } catch (IOException e) {
                    e.printStackTrace();
                } finally {
                    fis = null;
                }
            }
            if (pdfReader != null) {
                pdfReader.close();
            }
            if (cosDocument != null) {
                try {
                    cosDocument.close();
                } catch (IOException e) {
                    e.printStackTrace();
                } finally {
                    cosDocument = null;
                }
            }
        }
        return buffer.toString();
    }
    
    public static boolean isBlank(CharSequence cs) {
        int strLen;
        if (cs == null || (strLen = cs.length()) == 0) {
            return true;
        }
        for (int i = 0; i < strLen; i++) {
            if (Character.isWhitespace(cs.charAt(i)) == false) {
                return false;
            }
        }
        return true;
    }
    
    public static void main(String[] args) {
        // System.err.println(new UploadUtils()
        // .readPdf("/opt/fileCache/2014/125/13/shuangping_D7037870CF4FC5C421A3E5359DCF8BBE.pdf"));
        System.err.println(new UploadUtils().readPdf("E:\MyWork\guyezhai\pdf提取\路径依赖视角下高校新专业建设的策略创新(1).pdf"));
        
    }
    
}

其中用到的jar包：

bcpkix-jdk15on-1.47.jar
bcprov-jdk15on-1.49.jar
commons-logging-1.1.2.jar
fontbox-1.8.2.jar
icu4j-4.0.1.jar
itextpdf-5.4.3.jar
jempbox-1.8.2.jar
pdfbox-1.8.2.jar