使用itext7统计PDF文件中的字数

最新推荐文章于 2024-07-02 10:37:48 发布

_古井心

最新推荐文章于 2024-07-02 10:37:48 发布

阅读量839

点赞数

分类专栏：实用代码片段

本文链接：https://blog.csdn.net/u010234516/article/details/121673855

版权

java itext7 pdf

实用代码片段专栏收录该内容

11 篇文章 0 订阅

订阅专栏

依赖：

        <dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>kernel</artifactId>
            <version>7.2.0</version>
        </dependency>
        <!--中文字体支持start-->
        <dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>font-asian</artifactId>
            <version>7.2.0</version>
        </dependency>
        <!--中文字体支持end-->

代码：


import com.itextpdf.kernel.pdf.PdfDocument;
import com.itextpdf.kernel.pdf.PdfReader;
import com.itextpdf.kernel.pdf.canvas.parser.PdfTextExtractor;
import lombok.extern.slf4j.Slf4j;

import java.io.IOException;
import java.io.InputStream;

/**
 * 统计pdf字数的工具
 *
 */
@Slf4j
public class PdfUtils {
    public static Integer countText(String fileName) throws IOException {
        try {
            PdfReader reader = new PdfReader(fileName);
            return countText(reader);
        } catch (IOException e) {
            log.error("打开pdf失败，文件名:{}", fileName, e);
            throw e;
        }
    }

    public static Integer countText(InputStream inputStream) throws IOException {
        try {
            PdfReader reader = new PdfReader(inputStream);
            return countText(reader);
        } catch (IOException e) {
            log.error("使用流打开pdf失败", e);
            throw e;
        }
    }

    public static Integer countText(PdfReader reader) {
        try {
            int characterCount = 0;

            PdfDocument pdfDoc = new PdfDocument(reader);
            // get the number of pages in PDF
            int noOfPages = pdfDoc.getNumberOfPages();
            System.out.println("Extracted content of PDF---- ");
            for (int i = 1; i <= noOfPages; i++) {
                // Extract content of each page
                String contentOfPage = PdfTextExtractor.getTextFromPage(pdfDoc.getPage(i));
                contentOfPage = contentOfPage.replaceAll("\\p{C}", "").replaceAll(" ", "");
                characterCount += contentOfPage.length();
                log.debug(contentOfPage);
                log.debug("这页几个字：" + contentOfPage.length());
            }
            pdfDoc.close();
            log.info("文档总共" + characterCount + "个字");
            return characterCount;
        } finally {
            try {
                if (reader != null) {
                    reader.close();
                }
            } catch (IOException e) {
                // do noting
            }
        }
    }

    public static void main(String[] args) throws IOException {
        String testPdf = "C:\\Users\\xxx\\Downloads\\test.pdf";
        countText(testPdf);
    }
}