下面是我正在使用的代码，我提供了一个pdf文件和一个文本文件作为命令行的输入。
import org.pdfbox.cos.COSDocument;
import org.pdfbox.pdfparser.PDFParser;
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.pdmodel.PDDocumentInformation;
import org.pdfbox.util.PDFTextStripper;
import java.io.File;
import java.io.FileInputStream;
import java.io.PrintWriter;
public class PDFTextParser {
PDFParser parser;
String parsedText;
PDFTextStripper pdfStripper;
PDDocument pdDoc;
COSDocument cosDoc;
PDDocumentInformation pdDocInfo;
// PDFTextParser Constructor
public PDFTextParser() {
}
// Extract text from PDF Document
String pdftoText(String fileName) {
System.out.println("Parsing text from PDF file " + fileName + "....");
File f = new File(fileName);
if (!f.isFile()) {
System.out.println("File " + fileName + " does not exist.");
return null;
}
try {
parser = new PDFParser(new FileInputStream(f));
} catch (Exception e) {
System.out.println("Unable to open PDF Parser.");
return null;
}
try {
parser.parse();
cosDoc = parser.getDocument();
pdfStripper = new PDFTextStripper();
pdDoc = new PDDocument(cosDoc);
parsedText = pdfStripper.getText(pdDoc);
} catch (Exception e) {
System.out.println("An exception occured in parsing the PDF Document.");
e.printStackTrace();
try {
if (cosDoc != null) cosDoc.close();
if (pdDoc != null) pdDoc.close();
} catch (Exception e1) {
e.printStackTrace();
}
return null;
}
System.out.println("Done.");
return parsedText;
}
// Write the parsed text from PDF to a file
void writeTexttoFile(String pdfText, String fileName) {
System.out.println("\nWriting PDF text to output text file " + fileName + "....");
try {
PrintWriter pw = new PrintWriter(fileName);
pw.print(pdfText);
pw.close();
} catch (Exception e) {
System.out.println("An exception occured in writing the pdf text to file.");
e.printStackTrace();
}
System.out.println("Done.");
}
//Extracts text from a PDF Document and writes it to a text file
public static void main(String args[]) {
if (args.length != 2) {
System.out.println("Usage: java PDFTextParser ");
System.exit(1);
}
PDFTextParser pdfTextParserObj = new PDFTextParser();
String pdfToText = pdfTextParserObj.pdftoText(args[0]);
if (pdfToText == null) {
System.out.println("PDF to Text Conversion failed.");
}
else {
System.out.println("\nThe text parsed from the PDF Document....\n" + pdfToText);
pdfTextParserObj.writeTexttoFile(pdfToText, args[1]);
}
}
}
在通过命令行运行此代码后，输入一个pdf文件名和另一个文本文件名，我得到noClassDefFound异常。下面是堆栈跟踪。
Exception in thread "main" java.lang.NoClassDefFoundError: org/pdfbox/pdfparser/
PDFParser
at PDFTextParser.pdftoText(PDFTextParser.java:42)
at PDFTextParser.main(PDFTextParser.java:93)
Caused by: java.lang.ClassNotFoundException: org.pdfbox.pdfparser.PDFParser
at java.net.URLClassLoader$1.run(URLClassLoader.java:202)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:190)
at java.lang.ClassLoader.loadClass(ClassLoader.java:306)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:301)
at java.lang.ClassLoader.loadClass(ClassLoader.java:247)
... 2 more
添加类路径后，我得到了Exceptions
Exception in thread "main" java.lang.NoClassDefFoundError: org/fontbox/afm/AFMParser
at org.pdfbox.pdmodel.font.PDFont.getAFM(PDFont.java:350)
at org.pdfbox.pdmodel.font.PDFont.getAverageFontWidthFromAFMFile(PDFont.java:313)
at org.pdfbox.pdmodel.font.PDSimpleFont.getAverageFontWidth(PDSimpleFont.java:231)
at org.pdfbox.util.PDFStreamEngine.showString(PDFStreamEngine.java:276)
at org.pdfbox.util.operator.ShowTextGlyph.process(ShowTextGlyph.java:80)
at org.pdfbox.util.PDFStreamEngine.processOperator(PDFStreamEngine.java:452)
at org.pdfbox.util.PDFStreamEngine.processSubStream(PDFStreamEngine.java:215)
at org.pdfbox.util.PDFStreamEngine.processStream(PDFStreamEngine.java:174)
at org.pdfbox.util.PDFTextStripper.processPage(PDFTextStripper.java:336)
at org.pdfbox.util.PDFTextStripper.processPages(PDFTextStripper.java:259)
at org.pdfbox.util.PDFTextStripper.writeText(PDFTextStripper.java:216)
at org.pdfbox.util.PDFTextStripper.getText(PDFTextStripper.java:149)
at PDFTextParser.pdftoText(PDFTextParser.java:53)
at PDFTextParser.main(PDFTextParser.java:93)
Caused by: java.lang.ClassNotFoundException: org.fontbox.afm.AFMParser
at java.net.URLClassLoader$1.run(URLClassLoader.java:202)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:190)
at java.lang.ClassLoader.loadClass(ClassLoader.java:306)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:301)
at java.lang.ClassLoader.loadClass(ClassLoader.java:247)
... 14 more
在Java中运行具有外部依赖项（在您的案例中为PDF解析器）的程序时，您必须将适当的JAR文件包含在CLASSPATH中。
见this other thread on Stack Overflow或the documentation at Oracle。
我搜索了jarfinder.com上找不到的类，结果发现你需要包含（至少）两个不同的JAR文件--font box和pdf box JAR。
你可以从这里http://mvnrepository.com/artifact/org.apache.pdfbox/fontbox/1.8.5获得fontbox jar
如果你正在使用maven org.apache.pdfbox fontbox 1.8.5
除了Apache pdfbox jar之外，您需要在类路径中包含fontbox-1.3.1 jar，这将解决您的问题，因为PDFBox内部使用fontbox-1.3.1
我解决了这个问题，在我的常春藤文件中插入transitive = true以获得pdfbox依赖。
<dependency org="org.apache.pdfbox" name="pdfbox" rev="1.8.11" transitive="true"/>
我用iText库来解决我的目的。它对我来说非常好用。