wkhtmltopdf - 将HTML转成PDF

介绍

wkhtmltopdf是一个开源的C语言开发的命令行工具, 它通过Qt WebKit渲染引擎将HTML转换成PDF, 它可以完全不依赖于图形用户界面, 例如它在Linux Server上运行可以不依赖于X11. 官网: 请输入链接描述

命令行运行方式:

wkhtmltopdf http://google.com google.pdf

更多的运行参数参考: https://wkhtmltopdf.org/usage/wkhtmltopdf.txt

Java工具类:

因为wkhtmltopdf是一个简单易用的命令行工具, 我们可以简单通过命令很简单调用它为帮助转换PDF.

以下是一个简单的Java工具类, 帮助调用wkhtmltopdf转换HTML

Java 类

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;

import java.nio.charset.Charset;

import java.util.ArrayList;
import java.util.List;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;


/**
 * Document for new class.
 *
 * @User:    Wang Yang
 * @Date:    12-12-2
 * @Time:    PM3:10
 * @author   $author$
 * @version  $Revision$, $Date$
 */
public class WKHtml2PdfConverter {

  // 配置最大retry次数
  private static final Integer MAX_RETRY_COUNT = 5;

  /**
   * wkhtmltopdf 命令位置<br/>
   * 比如 :
   *
   * <pre>
         CentOS: /opt/wkhtmltopdf/bin/wkhtmltopdf
         MacOS:  /Users/username/Appliactions/wkhtmltopdf.app/Contents/MacOS/wkhtmltopdf
   </pre>
   */
  private String cmdPath;

  /**
   * wkhtmltopdf的运行参数 (https://wkhtmltopdf.org/usage/wkhtmltopdf.txt)<br/>
   * 比如设置页宽: --Letter
   */
  private String extraArgs;

  /** 需要转换的HTML文件的位置. */
  private String input;

  private final transient Logger logger = LoggerFactory.getLogger(getClass());

  /** 转换后的输出PDF文件的位置. */
  private String output;

  /**
   * 老版本的wkhtmltopdf是需要X11的, 在X11的运行参数类似:
   *
   * <pre>
       /usr/bin/xvfb-run --auto-servernum --server-num=1 /usr/bin/wkhtmltopdf --use-xserver --help
   * </pre>
   */
  private String runAsArgs;

  /**
   * 拼凑命令脚本, {@link ProcessBuilder}将{@code input}转换成{@code output}.
   *
   * @throws  IOException           DOCUMENT ME!
   * @throws  InterruptedException  DOCUMENT ME!
   * @throws  RuntimeException      DOCUMENT ME!
   */
  public void convert() {
    List<String> command = new ArrayList<String>();

    if ((runAsArgs != null) && !"".equals(runAsArgs.trim())) {
      String[] arguments = runAsArgs.trim().split("\\s+");

      for (String arg : arguments) {
        command.add(arg);
      }
    }

    command.add(cmdPath);

    if ((extraArgs != null) && !"".equals(extraArgs.trim())) {
      String[] arguments = extraArgs.trim().split("\\s+");

      for (String arg : arguments) {
        command.add(arg);
      }
    }

    command.add(input);
    command.add(output);

    int     retryCount = 0;
    boolean failed     = false;

    do {
      try {
        if (failed) {
          retryCount++;
          logger.info("Retry to converter the html. [Retry Times: " + retryCount + "]");
        }

        ProcessBuilder processBuilder = new ProcessBuilder(command);

        if (logger.isDebugEnabled()) {
          String msg = logExecutingCommand(processBuilder);
          logger.debug(msg);
        }

        Process     process = processBuilder.start();
        InputStream is      = process.getInputStream();
        boolean     running = true;

        if (logger.isDebugEnabled()) {
          logger.debug(logCommandOutput(is));
        }

        if (logger.isDebugEnabled()) {
          logger.debug(logCommandOutput(process.getErrorStream()));
        }

        while (running) {
          try {
            process.waitFor();
            running = false;
          } catch (InterruptedException e) {
            // you could stop a process by interrupting it's Job thread
            process.destroy();
          }
        }

        int exitVal = process.exitValue(); //

        if (logger.isDebugEnabled()) {
          logger.debug("Exited with error code " + exitVal);
        }

        failed = exitVal != 0;
      } catch (Exception e) {
        logger.error("Failed to convert template", e);
        failed = true;
      } // end try-catch
    } while (failed && (retryCount < MAX_RETRY_COUNT));

    if (failed) {
      throw new RuntimeException("Failed generating PDF file");
    }
  } // end method convert

  /**
   * DOCUMENT ME!
   *
   * @param  cmdPath  DOCUMENT ME!
   */
  public void setCmdPath(String cmdPath) {
    this.cmdPath = cmdPath;
  }

  /**
   * DOCUMENT ME!
   *
   * @param  extraArgs  DOCUMENT ME!
   */
  public void setExtraArgs(String extraArgs) {
    this.extraArgs = extraArgs;
  }

  /**
   * DOCUMENT ME!
   *
   * @param  input  DOCUMENT ME!
   */
  public void setInput(String input) {
    this.input = input;
  }

  /**
   * DOCUMENT ME!
   *
   * @param  output  DOCUMENT ME!
   */
  public void setOutput(String output) {
    this.output = output;
  }

  /**
   * DOCUMENT ME!
   *
   * @param  runAsArgs  DOCUMENT ME!
   */
  public void setRunAsArgs(String runAsArgs) {
    this.runAsArgs = runAsArgs;
  }

  /**
   * 输出执行WKHtmlToPdf命令过程中的log信息.
   *
   * @param   is  InputStream
   *
   * @return  输出执行WKHtmlToPdf命令过程中的log信息.
   *
   * @throws  IOException
   */
  private String logCommandOutput(InputStream is) throws IOException {
    StringBuffer sb = new StringBuffer("Processing \n");

    if (logger.isDebugEnabled()) {
      BufferedReader input = new BufferedReader(new InputStreamReader(is, Charset.forName("UTF-8")));

      String line = null;

      while ((line = input.readLine()) != null) {
        sb.append(line).append("\n");
      }
    }

    return sb.toString();
  }

  /**
   * 打印输出最终拼凑出来的脚本命令.
   *
   * @param   processBuilder  ProcessBuilder
   *
   * @return  打印输出最终拼凑出来的脚本命令.
   */
  private String logExecutingCommand(ProcessBuilder processBuilder) {
    List<String> commands = processBuilder.command();
    StringBuffer sb       = new StringBuffer("Executing command: ");
    String       tab      = " ";

    for (int i = 0; i < commands.size(); i++) {
      String command = commands.get(i);

      if (i == 0) {
        sb.append(command);
      } else {
        sb.append(tab).append(command);
      }
    }

    return sb.toString();
  }
} // end class WKHtml2PdfConverter

测试

1. 测试代码:

   public static void main(String[] args) {
     WKHtml2PdfConverter converter = new WKHtml2PdfConverter();
   
     converter.cmdPath   = "/usr/local/bin/wkhtmltopdf";
     converter.input     = "https://www.google.com/";
     converter.output    = "/tmp/Downloads/5.pdf";
     converter.extraArgs = "--quiet";
   
     converter.convert();
   }

2. 老版本wkhtmltopdf依赖于X11, 测试方法:

   public static void main(String[] args) {
     WKHtml2PdfConverter converter = new WKHtml2PdfConverter();
   
     /**
      * 老版本的WKHtmlToPdf是需要依赖X11的
      */
     converter.runAsArgs = "/usr/bin/xvfb-run";
     converter.cmdPath   = "/usr/bin/wkhtmltopdf-amd64";
     converter.input     = "/tmp/a.html";
     converter.output    = "/tmp/a.pdf";
     converter.extraArgs = "--use-xserver";
   
     converter.convert();
   }