Java使用PDFBox提取PDF文本并统计关键词出现的次数

<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>2.0.29</version>
</dependency>

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

import java.io.File;
import java.io.IOException;

public class PDFWordCounter {

    public static void main(String[] args) {
        String pdfPath = "sample.pdf";  // 替换为你的 PDF 文件路径
        String keyword = "Java";        // 要统计的词语

        try {
            // 加载 PDF 文档
            PDDocument document = PDDocument.load(new File(pdfPath));

            // 使用 PDFTextStripper 提取文本
            PDFTextStripper stripper = new PDFTextStripper();
            String text = stripper.getText(document);
            document.close(); // 记得关闭文档资源

            // 转小写处理，方便忽略大小写
            String lowerText = text.toLowerCase();
            String lowerKeyword = keyword.toLowerCase();

            // 调用词频统计函数
            int count = countOccurrences(lowerText, lowerKeyword);

            System.out.println("词语 \"" + keyword + "\" 出现次数: " + count);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    // 使用 indexOf 遍历匹配词语出现次数
    private static int countOccurrences(String text, String word) {
        int count = 0;
        int index = 0;
        while ((index = text.indexOf(word, index)) != -1) {
            count++;
            index += word.length();
        }
        return count;
    }
}

Pattern pattern = Pattern.compile("\\b" + Pattern.quote(word) + "\\b", Pattern.CASE_INSENSITIVE);
Matcher matcher = pattern.matcher(text);
int count = 0;
while (matcher.find()) {
    count++;
}

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

import java.io.InputStream;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class OnlinePDFKeywordCounter {

    public static void main(String[] args) {
        String pdfUrl = "https://www.example.com/sample.pdf"; // 你的在线 PDF 链接
        String keyword = "Java";  // 需要统计的关键词

        try (InputStream inputStream = new URL(pdfUrl).openStream();
             PDDocument document = PDDocument.load(inputStream)) {

            PDFTextStripper stripper = new PDFTextStripper();
            String text = stripper.getText(document);

            // 使用正则匹配单词边界（忽略大小写）
            Pattern pattern = Pattern.compile("\\b" + Pattern.quote(keyword) + "\\b", Pattern.CASE_INSENSITIVE);
            Matcher matcher = pattern.matcher(text);

            int count = 0;
            while (matcher.find()) {
                count++;
            }

            System.out.println("词语 \"" + keyword + "\" 出现在在线 PDF 中的次数为: " + count);

        } catch (Exception e) {
            System.err.println("处理 PDF 时出错: " + e.getMessage());
            e.printStackTrace();
        }
    }
}

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

import java.io.InputStream;
import java.net.URL;

public class OnlinePDFKeywordCounter {

    public static void main(String[] args) {
        String pdfUrl = "https://www.xxxx.pdf";
        String keyword = "管理层";  // 要统计的中文关键词

        try (InputStream inputStream = new URL(pdfUrl).openStream();
             PDDocument document = PDDocument.load(inputStream)) {

            PDFTextStripper stripper = new PDFTextStripper();
            String text = stripper.getText(document);

            // 直接用 indexOf 不区分大小写（对于中文没必要转小写）
            int count = countOccurrences(text, keyword);
            System.out.println("词语 \"" + keyword + "\" 出现次数为: " + count);

        } catch (Exception e) {
            System.err.println("处理 PDF 时出错: " + e.getMessage());
            e.printStackTrace();
        }
    }

    // 简单统计子串出现次数（适用于中文）
    private static int countOccurrences(String text, String keyword) {
        int count = 0;
        int index = 0;
        while ((index = text.indexOf(keyword, index)) != -1) {
            count++;
            index += keyword.length();
        }
        return count;
    }
}