--no commit message

com.zrqx.resource/src/main/java/com/zrqx/resource/commons/util/EpubUtil.java

+package com.zrqx.resource.commons.util;
+
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.FileNotFoundException;
+import java.io.IOException;
+import java.io.InputStream;
+import java.text.ParseException;
+import java.text.SimpleDateFormat;
+import java.util.List;
+import java.util.zip.ZipInputStream;
+
+import nl.siegmann.epublib.domain.Author;
+import nl.siegmann.epublib.domain.Book;
+import nl.siegmann.epublib.domain.Date;
+import nl.siegmann.epublib.domain.Identifier;
+import nl.siegmann.epublib.domain.MediaType;
+import nl.siegmann.epublib.domain.Metadata;
+import nl.siegmann.epublib.domain.Resource;
+import nl.siegmann.epublib.domain.Resources;
+import nl.siegmann.epublib.domain.SpineReference;
+import nl.siegmann.epublib.domain.TOCReference;
+import nl.siegmann.epublib.domain.TableOfContents;
+import nl.siegmann.epublib.epub.EpubReader;
+
+/**
+ * epub 数字书籍格式 数据工具包
+ * @author Administrator
+ *
+ */
+public class EpubUtil {
+
+	private Book book=null;
+	private EpubReader epubReader=null;
+	
+	
+	/**
+	 * 设置Book实例对象
+	 * @return
+	 */
+	public  EpubUtil setEpubFile(File file){
+		try {
+			return setEpubFile(new FileInputStream(file));
+		} catch (FileNotFoundException e) {
+			e.printStackTrace();
+		}
+		return this;
+	}
+	
+	/**
+	 * 设置Book实例对象
+	 * @return
+	 */
+	public  EpubUtil setEpubFile(InputStream in){
+		try {
+			epubReader=getEpubReader();
+			book=epubReader.readEpub(in);
+		} catch (IOException e) {
+			e.printStackTrace();
+		}
+		return this;
+	}
+	
+	/**
+	 * 设置Book实例对象
+	 * @return
+	 */
+	public  EpubUtil setEpubFile(InputStream in, String encoding){
+		try {
+			epubReader=getEpubReader();
+			book=epubReader.readEpub(in,encoding);
+		} catch (IOException e) {
+			e.printStackTrace();
+		}
+		return this;
+	}
+	
+	/**
+	 * 设置Book实例对象
+	 * @return
+	 */
+	public  EpubUtil setEpubFile(ZipInputStream in){
+		try {
+			epubReader=getEpubReader();
+			book=epubReader.readEpub(in);
+		} catch (IOException e) {
+			e.printStackTrace();
+		}
+		return this;
+	}
+	
+	/**
+	 * 设置Book实例对象
+	 * @return
+	 */
+	public  EpubUtil setEpubFile(ZipInputStream in,String encoding){
+		try {
+			epubReader=getEpubReader();
+			book=epubReader.readEpub(in,encoding);
+		} catch (IOException e) {
+			e.printStackTrace();
+		}
+		return this;
+	}
+	
+
+	
+	/**
+	 * 获取所有的资源对象
+	 * @return
+	 */
+	public Resources getResources(){
+		return book.getResources();
+	}
+	
+	/**
+	 * 获取封面
+	 */
+	public Resource getCover(){
+		//epub格式的书籍中都没有将封面图片的信息放到<metadata>标签下的cover标签中。所以用第二种fangs
+		Resource res = book.getCoverImage();
+		if(res!=null){
+			return res;
+		}else{
+			Resources ress = book.getResources();  
+	        res = ress.getById("cover");
+	        if(res==null){
+	        	res = ress.getById("cover-image");  	
+	        }
+	        if(res==null){
+	        	res=ress.getById("Cover");	
+	        }
+			return res;
+		}
+	}
+	
+	/**
+	 * 获取制定的文件资源
+	 * @param mediaTypes
+	 * @return
+	 */
+	public List<Resource> getResources(MediaType ... mediaTypes){
+		return getResources().getResourcesByMediaTypes(mediaTypes);
+	}
+	
+	/**
+	 * 获取图书的css资源文件
+	 * @return
+	 */
+	public Resource getCssResource(){
+		List<Resource> list=getResources(new MediaType("text/css","css"));
+		if(list!=null && list.size()>0){
+			return list.get(0);
+		}
+		return null;
+	}
+	
+	/**
+	 * 获取图书的图片资源
+	 * @return
+	 */
+	public List<Resource> getImagesResources(){
+		return getResources(
+				new MediaType("image/jpeg","jpg"),
+				new MediaType("image/gif","gif"),
+				new MediaType("image/png","png")
+				);
+	}
+	
+	/**
+	 *获取根据阅读顺序获取图书的内容资源（html）文件资源
+	 * @return
+	 */
+	public List<SpineReference> getSpineReferences(){
+		return book.getSpine().getSpineReferences();
+	}
+	
+	/**
+	 *获取图书的目录结构标题及对应的资源内容
+	 * @return
+	 */
+	public List<TOCReference> getTocReferences(){
+		return book.getTableOfContents().getTocReferences();
+	}
+	
+	/**
+	 * 获取图书
+	 * @return
+	 * author:haopeng
+	 */
+	public Book getBook(){
+		return book;
+	}
+	
+	/**
+	 * 获取图书信息
+	 * @return
+	 * author:haopeng
+	 * @throws Exception 
+	 */
+	public Metadata getMetadata() throws Exception{
+		  if(book==null){
+			 throw new NullPointerException("图书Book属性为null");
+		  }
+		  return book.getMetadata();
+	}
+	/**
+	 * 获取文件读取器
+	 * @return
+	 */
+	private EpubReader getEpubReader(){
+		if(epubReader==null){
+			epubReader=new EpubReader();
+		}
+		return epubReader;
+	}
+	
+	/**
+	 * 获取图书ISBN号
+	 * @throws Exception 
+	 */
+	public String getISBN() throws Exception{
+		String isbn=null;
+		List<Identifier> identifiers=getMetadata().getIdentifiers();
+		for(Identifier identifier:identifiers){
+			String value=identifier.getValue();
+//			if(value.matches("^97[8|9]\\d{10}$") ){//新版isbn号格式
+			if(value.contains("-")){
+				value=value.replaceAll("-", "");
+				isbn=value;
+				break;
+			}
+		}
+		return isbn;
+	}
+	
+	/**
+	 * 获取图书作者
+	 */
+	public String getAuthor(){
+		List<Author> authors = null;
+		try {
+			authors = getMetadata().getAuthors();
+		} catch (Exception e) {
+			e.printStackTrace();
+		}
+		String author = "";
+		if(authors.size()>0){
+			author = authors.get(0).getFirstname()+authors.get(0).getLastname();
+			author = author.replaceAll("[\\[\\],]"," ");
+		}
+		return author;
+		
+	}
+	
+	/**
+	 * 获取出版日期
+	 */
+	public  java.util.Date getPublishDate(){
+		List<Date> dates = null;
+		try {
+			dates = getMetadata().getDates();
+		} catch (Exception e) {
+			e.printStackTrace();
+		}
+		SimpleDateFormat sdf = new SimpleDateFormat("yyy");
+		String tempDate = "";
+		if(dates.size()>0){
+			if(dates.get(0).toString().contains(".")){
+				sdf= new SimpleDateFormat("yyy.MM");
+			}
+			if(dates.get(0).toString().contains("-")){
+				sdf= new SimpleDateFormat("yyy-MM");
+			}
+		
+		
+			tempDate= dates.get(0).toString();
+		}
+		java.util.Date publicDate = null;
+		try {
+			if(tempDate!=null && !tempDate.equals("")){
+				publicDate = sdf.parse(tempDate);
+			}
+		} catch (ParseException e) {
+			System.out.println("日期转换错误!");
+			e.printStackTrace();
+		}
+	
+		return publicDate;
+	}
+	
+	/**
+	 * 出版单位
+	 */
+	public  String getPublisher(){
+		String publisher = "";
+		List<String> publishers;
+		try {
+			publishers = getMetadata().getPublishers();
+			for(String p : publishers){
+				if(p.contains("-")){
+					publisher = publisher + "、" + p;
+					break;
+				}
+			}
+		} catch (Exception e) {
+			e.printStackTrace();
+		}
+		
+		return publisher;
+	}
+	
+	/**
+	 * 获取图书的名字 
+	 */
+	public String getBookTitle(){
+		String bookTitle = "";
+		//List<String> bookTitle2 = null;
+		try {
+			bookTitle = getMetadata().getFirstTitle();
+			//bookTitle2 = getMetadata().getTitles();
+		} catch (Exception e) {
+			e.printStackTrace();
+		}
+		return bookTitle;
+	}
+	
+}

com.zrqx.resource/src/main/java/com/zrqx/resource/commons/util/ParseFile.java

+package com.zrqx.resource.commons.util;
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.InputStreamReader;
+import java.io.Reader;
+
+import org.springframework.stereotype.Component;
+
+@Component
+public class ParseFile {
+
+    /**
+     * 解析html文件
+     * @param file
+     * @return
+     */
+    public static String readHtml(File file){
+        String body = "";
+        try {
+            FileInputStream iStream = new FileInputStream(file);
+            Reader reader = new InputStreamReader(iStream);
+            BufferedReader htmlReader = new BufferedReader(reader);
+                        
+            String line;
+            boolean found = false;
+            while (!found && (line = htmlReader.readLine()) != null) {
+                if (line.toLowerCase().indexOf("<body") != -1) { // 在<body>的前面可能存在空格
+                    found = true;
+                }
+            }
+            
+            found = false;
+            while (!found && (line = htmlReader.readLine()) != null) {
+                if (line.toLowerCase().indexOf("</body") != -1) {
+                    found = true;
+                } else {
+                    // 如果存在图片，则将相对路径转换为绝对路径
+                    String lowerCaseLine = line.toLowerCase();
+                    if (lowerCaseLine.contains("src")) {
+                        
+                        //这里是定义图片的访问路径
+                        String directory = "D:/test";
+                        // 如果路径名不以反斜杠结尾，则手动添加反斜杠
+                        /*if (!directory.endsWith("\\")) {
+                            directory = directory + "\\";
+                        }*/
+                    //    line = line.substring(0,  lowerCaseLine.indexOf("src") + 5) + directory + line.substring(lowerCaseLine.indexOf("src") + 5);
+                        /*String filename = extractFilename(line);
+                        line = line.substring(0,  lowerCaseLine.indexOf("src") + 5) + directory + filename + line.substring(line.indexOf(filename) + filename.length());
+                    */
+                        // 如果该行存在多个<img>元素，则分行进行替代
+                        String[] splitLines = line.split("<img\\s+"); // <img后带一个或多个空格
+                        // 因为java中引用的问题不能使用for each
+                        for (int i = 0; i < splitLines.length; i++) {
+                            if (splitLines[i].toLowerCase().startsWith("src")) {
+                                splitLines[i] = splitLines[i].substring(0, splitLines[i].toLowerCase().indexOf("src") + 5)
+                                        + directory
+                                        + splitLines[i].substring(splitLines[i].toLowerCase().indexOf("src") + 5);
+                            }
+                        }
+                        
+                        // 最后进行拼接
+                        line = "";
+                        for (int i = 0; i < splitLines.length - 1; i++) { // 循环次数要-1，因为最后一个字符串后不需要添加<img
+                            line = line + splitLines[i] + "<img ";
+                        }
+                        line = line + splitLines[splitLines.length - 1];
+                    }
+                    
+                    body = body + line + "\n";
+                }
+            }
+            htmlReader.close();
+    //        System.out.println(body);
+            
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+        return body;
+    }
+    
+    /**
+     * 
+     * @param htmlLine 一行html片段，包含<img>元素
+     * @return 文件名
+     */
+    public static String extractFilename(String htmlLine) {
+        int srcIndex = htmlLine.toLowerCase().indexOf("src=");
+        if (srcIndex == -1) { // 图片不存在，返回空字符串
+            return "";
+        } else {
+            String htmlSrc = htmlLine.substring(srcIndex + 4);
+            char splitChar = '\"'; // 默认为双引号，但也有可能为单引号
+            if (htmlSrc.charAt(0) == '\'') {
+                splitChar = '\'';
+            } 
+            String[] firstSplit = htmlSrc.split(String.valueOf(splitChar));
+            String path = firstSplit[1]; // 第0位为空字符串
+            String[] secondSplit = path.split("[/\\\\]"); // 匹配正斜杠或反斜杠
+            return secondSplit[secondSplit.length - 1];
+        }
+    }
+    
+}
\ No newline at end of file