Java pdf到Excel的转换

Question

我正在从PDF提取数据到excel。 该PDF中也包含表格。 我使用Itext- pdf来将PDF转换为文本，并借助apache poi为excel。 但我无法检索要存储在数据库中的数据。 我试过PDF-BOX ， ASPOSE也得到相同的结果。 如果有人知道，请帮助我解决此问题。

这是我的代码

//使用itext将pdf转换为文本

            PdfReader reader = new PdfReader(
                    "C:\\Users\\mohmeds\\Desktop\\BOI_SCFS banking.pdf_page_1.pdf");
            PdfReaderContentParser parser = new PdfReaderContentParser(
                    reader);
            // PrintWriter out = new PrintWriter(new FileOutputStream(txt));
            TextExtractionStrategy strategy;
            String line = null;
            for (int i = 1; i <= reader.getNumberOfPages(); i++) {
                strategy = parser.processContent(i,
                        new SimpleTextExtractionStrategy());
                line = strategy.getResultantText();
            }
            reader.close();

            // using apache poi text to excel converter

            org.apache.poi.ss.usermodel.Workbook wb = new HSSFWorkbook();
            CreationHelper helper = wb.getCreationHelper();
            Sheet sheet = wb.createSheet("new sheet");
            System.out.println("link------->" + line);
            List<String> lines = IOUtils.readLines(new StringReader(line));

            for (int i = 0; i < lines.size(); i++) {
                String str[] = lines.get(i).split(",");
                Row row = sheet.createRow((short) i);
                for (int j = 0; j < str.length; j++) {
                    row.createCell(j).setCellValue(
                            helper.createRichTextString(str[j]));

                }
            }

            FileOutputStream fileOut = new FileOutputStream(
                    "C:\\Users\\mohmeds\\Desktop\\someName1.xls");
            wb.write(fileOut);
            fileOut.close();

Answer 1

您的问题有点含糊，但是如果您希望将PDF中的数据存储到数据库中，则可能希望将数据提取为CSV而不是Excel。 同样，此处的代码省去了将PDF转换为Text，然后将Text转换为Excel的中间步骤。 定义格式时，选择“ csv”：

package com.pdftables.examples;

import java.io.File;
import java.util.Arrays;
import java.util.List;

import org.apache.commons.io.FileUtils;
import org.apache.http.HttpEntity;
import org.apache.http.client.config.CookieSpecs;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.entity.mime.MultipartEntityBuilder;
import org.apache.http.entity.mime.content.FileBody;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;

public class ConvertToFile {
    private static List<String> formats = Arrays.asList(new String[] { "csv", "xml", "xlsx-single", "xlsx-multiple" });

    public static void main(String[] args) throws Exception {
        if (args.length != 3) {
            System.out.println("Command line: <API_KEY> <FORMAT> <PDF filename>");
            System.exit(1);
        }

        final String apiKey = args[0];
        final String format = args[1].toLowerCase();
        final String pdfFilename = args[2];

        if (!formats.contains(format)) {
            System.out.println("Invalid output format: \"" + format + "\"");
            System.exit(1);
        }

        // Avoid cookie warning with default cookie configuration
        RequestConfig globalConfig = RequestConfig.custom().setCookieSpec(CookieSpecs.STANDARD).build();

        File inputFile = new File(pdfFilename);

        if (!inputFile.canRead()) {
            System.out.println("Can't read input PDF file: \"" + pdfFilename + "\"");
            System.exit(1);
        }

        try (CloseableHttpClient httpclient = HttpClients.custom().setDefaultRequestConfig(globalConfig).build()) {
            HttpPost httppost = new HttpPost("https://pdftables.com/api?format=" + format + "&key=" + apiKey);
            FileBody fileBody = new FileBody(inputFile);

            HttpEntity requestBody = MultipartEntityBuilder.create().addPart("f", fileBody).build();
            httppost.setEntity(requestBody);

            System.out.println("Sending request");

            try (CloseableHttpResponse response = httpclient.execute(httppost)) {
                if (response.getStatusLine().getStatusCode() != 200) {
                    System.out.println(response.getStatusLine());
                    System.exit(1);
                }
                HttpEntity resEntity = response.getEntity();
                if (resEntity != null) {
                    final String outputFilename = getOutputFilename(pdfFilename, format.replaceFirst("-.*$", ""));
                    System.out.println("Writing output to " + outputFilename);

                    final File outputFile = new File(outputFilename);
                    FileUtils.copyToFile(resEntity.getContent(), outputFile);
                } else {
                    System.out.println("Error: file missing from response");
                    System.exit(1);
                }
            }
        }
    }

    private static String getOutputFilename(String pdfFilename, String suffix) {
        if (pdfFilename.length() >= 5 && pdfFilename.toLowerCase().endsWith(".pdf")) {
            return pdfFilename.substring(0, pdfFilename.length() - 4) + "." + suffix;
        } else {
            return pdfFilename + "." + suffix;
        }
    }
}

https://github.com/pdftables/java-pdftables-api/blob/master/pdftables.java