本文以Java示例展示使用Itext读取pdf文本的方法。
1、Maven仓库
在pom.xml中配置maven路径，指定依赖，如下：
<dependency>
<groupId>com.itextpdf</groupId>
<artifactId>itextpdf</artifactId>
<version>5.5.1</version>
<type>jar</type>
</dependency>
2 、读取PDF文本
2.1 读取整个PDF文本
/**
* 用来读取pdf文件
* @param fileName
* @return
* @throws IOException
*/
public static String readPdfByPage(String fileName) {
String result = "";
File file = new File(fileName);
FileInputStream in = null;
try {
in = new FileInputStream(fileName);
// 新建一个PDF解析器对象
PdfReader reader = new PdfReader(fileName);
reader.setAppendable(true);
// 对PDF文件进行解析，获取PDF文档页码
int size = reader.getNumberOfPages();
for(int i = 1 ; i < size + 1; ){
//一页页读取PDF文本
String pageStr = PdfTextExtractor.getTextFromPage(reader,i);
result = result + pageStr + "\n" + "PDF解析第"+ (i)+ "页\n";
i= i+1;
}
reader.close();
} catch (Exception e) {
System.out.println("读取PDF文件" + file.getAbsolutePath() + "生失败！" + e);
e.printStackTrace();
} finally {
if (in != null) {
try {
in.close();
} catch (IOException e1) {
}
}
}
return result;
}2.2 读取某几页PDF文本
public static String readPdfByPage(String fileName, int from, int end) {
String result = "";
File file = new File(fileName);
FileInputStream in = null;
try {
in = new FileInputStream(fileName);
// 新建一个PDF解析器对象
PdfReader reader = new PdfReader(fileName);
reader.setAppendable(false);
// 对PDF文件进行解析，获取PDF文档页码
int size = reader.getNumberOfPages();
for(int i = from ; i <= end && i< size;i++ ){
//一页页读取PDF文本
String pageStr = PdfTextExtractor.getTextFromPage(reader,i);
result = result + pageStr + "\n" + "PDF解析第"+ i+ "页\n";
}
reader.close();
} catch (Exception e) {
System.out.println("读取PDF文件" + file.getAbsolutePath() + "生失败！" + e);
e.printStackTrace();
} finally {
if (in != null) {
try {
in.close();
} catch (IOException e1) {
}
}
}
return result;
}