如何解析pdf中带颜色部分

╰+哭是因爲堅強的太久メ 2024-04-19 13:09 50阅读 0赞

二话部署先上图  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VsbGVuX1Rhbmd4aWFuZw_size_16_color_FFFFFF_t_70]问如何解析pdf中红色部分内容？

1.  尝试tika，失败。tika只能解析到pdf中的文字，无法定位红色部分。
2.  尝试pdfpox，依然失败，没有找到能够定位的api。
3.  同事给出的思路能不能转成html然后在解析。

bingo  
这一思路可行  
引入maven依赖

<dependency>
        <groupId>net.sf.cssbox</groupId>
        <artifactId>pdf2dom</artifactId>
        <version>1.7</version>
    </dependency>
    <dependency>
        <groupId>org.apache.pdfbox</groupId>
        <artifactId>pdfbox</artifactId>
        <version>2.0.12</version>
    </dependency>
    <dependency>
        <groupId>org.apache.pdfbox</groupId>
        <artifactId>pdfbox-tools</artifactId>
        <version>2.0.12</version>
    </dependency>

import com.laibo.reduce.reduce_center.common.exception.GeneralException;
    import org.apache.pdfbox.pdmodel.PDDocument;
    import org.fit.pdfdom.PDFDomTree;
    import org.jsoup.nodes.Document;
    import org.jsoup.nodes.Element;
    import org.jsoup.select.Elements;
    import org.springframework.stereotype.Component;
    
    import java.io.*;
    import java.util.HashMap;
    import java.util.Map;
    @Component
    public class PdfToHtmlUtil { 
        public static final String PDF_SUFFIX = ".pdf";
        public static final String HTML_SUFFIX = ".html";
    
    	public static void main(String[] args) { 
            String path = "C:\\Users\\laibo\\Desktop\\temp\\test.pdf";
            pdfToHtml(path);
        }
    
        /** * 将指定路径的pdf转成Html * @param path 文件路径 */
        public static void pdfToHtml(String path) { 
            if (path == null || path.length() == 0) { 
                throw new GeneralException("path为空！");
            }
            if (!path.endsWith(PDF_SUFFIX)) { 
                throw new GeneralException("文件类型不是pdf，请检查文件类型！");
            }
            int endIndex = path.indexOf(PDF_SUFFIX);
            String pathPrefixWithFileName = path.substring(0, endIndex);
            String outputPath = pathPrefixWithFileName + HTML_SUFFIX;
            byte[] bytes = getBytes(path);
            pdfBytesToHtml(bytes,outputPath);
        }
    
        /** * 将pdf的字节数组转成html * @param bytes 字节数组 * @param outputPath html输出路径 */
        public static void pdfBytesToHtml(byte[] bytes,String outputPath){ 
            /** * try() 写在()里面会自动关闭流 */
            try (BufferedWriter out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(new File(outputPath)), "UTF-8"));) { 
                /** * 加载PDF文档 */
                PDDocument document = PDDocument.load(bytes);
                PDFDomTree pdfDomTree = new PDFDomTree();
                pdfDomTree.writeText(document, out);
            } catch (Exception e) { 
                e.printStackTrace();
            }
        }
    
        /** * 将文件转换为byte数组 * @param filePath * @return byte[] */
        private static byte[] getBytes(String filePath) { 
            byte[] buffer = null;
            try { 
                File file = new File(filePath);
                FileInputStream fis = new FileInputStream(file);
                ByteArrayOutputStream bos = new ByteArrayOutputStream(1000);
                byte[] b = new byte[1000];
                int n;
                while ((n = fis.read(b)) != -1) { 
                    bos.write(b, 0, n);
                }
                fis.close();
                bos.close();
                buffer = bos.toByteArray();
            } catch (FileNotFoundException e) { 
                e.printStackTrace();
            } catch (IOException e) { 
                e.printStackTrace();
            }
            return buffer;
        }
    }

生成html完成

再使用jsoup解析即可

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L0VsbGVuX1Rhbmd4aWFuZw_size_16_color_FFFFFF_t_70]: https://image.dandelioncloud.cn/pgy_files/images/2024/04/18/82038fcf37854665b8bcff90678f345f.png