packagecom.szy.project.utils;importjava.io.BufferedInputStream;importjava.io.BufferedOutputStream;importjava.io.BufferedReader;importjava.io.DataOutputStream;importjava.io.File;importjava.io.FileInputStream;importjava.io.FileOutputStream;importjava.io.IOException;importjava.io.InputStream;importjava.io.InputStreamReader;importjava.io.OutputStreamWriter;importjava.io.Reader;importjava.io.Writer;importjava.util.Enumeration;importjavax.mail.MessagingException;importjavax.mail.Multipart;importjavax.mail.Session;importjavax.mail.internet.MimeBodyPart;importjavax.mail.internet.MimeMessage;importjavax.mail.internet.MimeMultipart;importorg.jsoup.Jsoup;importorg.jsoup.nodes.Document;/*** 转换工具 ---------- 需要引入第三方依赖 javaMail转换格式 和 jsoup解析HTML
* jsoup 文档地址 :http://www.open-open.com/jsoup/parse-document-from-string.htm* 将mht 转化成 HTML
*@author隔壁老王
**/
public classMht2HtmlUtil {public static void main(String[] args) throwsIOException {/*** 转换*/
//mht2html("f:\\job_111.mht", "f:\\test.htm");
/*** 获取姓名和性别*/String nameAndSex= Mht2HtmlUtil.findResultValue("f:\\test.htm", "li", "info_name");
String tmpString= nameAndSex.replaceAll("(?i)[^a-zA-Z0-9\u4E00-\u9FA5]", "");//去掉所有中英文符号
char[] carr =tmpString.toCharArray();for (int i = 0; i < tmpString.length(); i++) {if (carr[i] < 0xFF) {
carr[i]= ' ';//过滤掉非汉字内容
}
}
System.out.println(tmpString.substring(0, tmpString.length()-1)); //姓名
System.out.println(tmpString.substring(tmpString.length()-1)); //性别
/*** 获取教育经历*/File htmlf=new File("f:\\test.htm");
Document doc=Jsoup.parse(htmlf, "UTF-8");
String ss=doc.body().toString();//class等于masthead的li标签
Object[] aa= doc.select("div.detaile_box").toArray();for (int i = 0; i < aa.length; i++) {if(i==3){
String strtext=aa[i].toString();
Document docs=Jsoup.parse(strtext);
Object[] bb= docs.select("b.edu_main_sch").toArray();for (int j = 0; j < bb.length; j++) {
String tt=bb[j].toString();
Document doct=Jsoup.parse(tt);
String result= doct.select("b.edu_main_sch").text();
String a=result.substring(0, result.indexOf("|")).trim();
String b=result.substring(result.lastIndexOf("|")+1, result.length()).trim();
System.out.println(a+" "+b); //毕业院校加学历
}
}
}
}/*** 解析标签 获取标签值
*@paramhtmlFilePath 文件路径
*@paramlableName 标签名称
*@paramonClassName 标签名称
*@return*@throwsIOException*/
public static String findResultValue(String htmlFilePath , String lableName , String onClassName) throwsIOException{
File htmlf=newFile(htmlFilePath);
Document doc=Jsoup.parse(htmlf, "UTF-8");
String bodyText=doc.body().toString(); //获取文件文本信息//class等于onClassName的lableName标签
String resultValue = doc.select(lableName+"."+onClassName).first().text();returnresultValue;
}/*** 解析标签结果返回多个值
*@paramhtmlFilePath 文件路径
*@paramlableName 标签名称
*@paramonClassName 标签名称
*@return*@throwsIOException*/
public static Object[] findResultValueToArray (String htmlFilePath , String lableName , String onClassName) throwsIOException{
File htmlf=newFile(htmlFilePath);
Document doc=Jsoup.parse(htmlf, "UTF-8");
String bodyText=doc.body().toString(); //获取文件文本信息
return doc.select(lableName+"."+onClassName).toArray();
}/*** 将 mht文件转换成 html文件
*
*@params_SrcMht // mht 文件的位置
*@params_DescHtml // 转换后输出的HTML的位置*/
public static voidmht2html(String srcMht, String descHtml) {try{
InputStream fis= newFileInputStream(srcMht);
Session mailSession=Session.getDefaultInstance(
System.getProperties(),null);
MimeMessage msg= newMimeMessage(mailSession, fis);
Object content=msg.getContent();if (content instanceofMultipart) {
MimeMultipart mp=(MimeMultipart) content;
MimeBodyPart bp1= (MimeBodyPart) mp.getBodyPart(0);//获取mht文件内容代码的编码
String strEncodng =getEncoding(bp1);//获取mht文件的内容
String strText =getHtmlText(bp1, strEncodng);if (strText == null)return;/*** 创建以mht文件名称的文件夹,主要用来保存资源文件。 这里不需要所以注释掉了*/
/*File parent = null;
if (mp.getCount() > 1) {
parent = new File(new File(descHtml).getAbsolutePath()
+ ".files");
parent.mkdirs();
if (!parent.exists()) { // 创建文件夹失败的话则退出
return;
}
}*/
/*** FOR中代码 主要是保存资源文件及替换路径 这里不需要所以注释掉了*/
/*for (int i = 1; i < mp.getCount(); ++i) {
MimeBodyPart bp = (MimeBodyPart) mp.getBodyPart(i);
// 获取资源文件的路径
// 例(获取:http://xxx.com/abc.jpg)
String strUrl = getResourcesUrl(bp);
if (strUrl == null || strUrl.length() == 0)
continue;
DataHandler dataHandler = bp.getDataHandler();
MimePartDataSource source = (MimePartDataSource) dataHandler
.getDataSource();
// 获取资源文件的绝对路径
String FilePath = parent.getAbsolutePath() + File.separator
+ getName(strUrl, i);
File resources = new File(FilePath);
// 保存资源文件
if (SaveResourcesFile(resources, bp.getInputStream())) {
// 将远程地址替换为本地地址 如图片、JS、CSS样式等等
strText = strText.replace(strUrl,
resources.getAbsolutePath());
}
}*/
//最后保存HTML文件
SaveHtml(strText, descHtml, strEncodng);
}
}catch(Exception e) {
e.printStackTrace();
}
}/*** 获取mht文件内容中资源文件的名称
*
*@paramstrName
*@paramID
*@return
*/
public static String getName(String strName, intID) {char separator1 = '/';char separator2 = '\\';//将换行替换
strName = strName.replaceAll("\r\n", "");//获取文件名称
if (strName.lastIndexOf(separator1) >= 0) {return strName.substring(strName.lastIndexOf(separator1) + 1);
}if (strName.lastIndexOf(separator2) >= 0) {return strName.substring(strName.lastIndexOf(separator2) + 1);
}return "";
}/*** 将提取出来的html内容写入保存的路径中。
*
*@paramstrText
*@paramstrHtml
*@paramstrEncodng*/
public static booleanSaveHtml(String s_HtmlTxt, String s_HtmlPath,
String s_Encode) {try{
Writer out= null;
out= newOutputStreamWriter(new FileOutputStream(s_HtmlPath, false), s_Encode);
out.write(s_HtmlTxt);
out.close();
}catch(Exception e) {return false;
}return true;
}/*** 保存网页中的JS、图片、CSS样式等资源文件
*
*@paramSrcFile
* 源文件
*@paraminputStream
* 输入流
*@return
*/
private static booleanSaveResourcesFile(File SrcFile,
InputStream inputStream) {if (SrcFile == null || inputStream == null) {return false;
}
BufferedInputStream in= null;
FileOutputStream fio= null;
BufferedOutputStream osw= null;try{
in= newBufferedInputStream(inputStream);
fio= newFileOutputStream(SrcFile);
osw= new BufferedOutputStream(newDataOutputStream(fio));int index = 0;byte[] a = new byte[1024];while ((index = in.read(a)) != -1) {
osw.write(a,0, index);
}
osw.flush();return true;
}catch(Exception e) {
e.printStackTrace();return false;
}finally{try{if (osw != null)
osw.close();if (fio != null)
fio.close();if (in != null)
in.close();if (inputStream != null)
inputStream.close();
}catch(Exception e) {
e.printStackTrace();return false;
}
}
}/*** 获取mht文件里资源文件的URL路径
*
*@parambp
*@return
*/
private staticString getResourcesUrl(MimeBodyPart bp) {if (bp == null) {return null;
}try{
Enumeration list=bp.getAllHeaders();while(list.hasMoreElements()) {
javax.mail.Header head=(javax.mail.Header) list.nextElement();if (head.getName().compareTo("Content-Location") == 0) {returnhead.getValue();
}
}return null;
}catch(MessagingException e) {return null;
}
}/*** 获取mht文件中的内容代码
*
*@parambp
*@paramstrEncoding
* 该mht文件的编码
*@return
*/
private staticString getHtmlText(MimeBodyPart bp, String strEncoding) {
InputStream textStream= null;
BufferedInputStream buff= null;
BufferedReader br= null;
Reader r= null;try{
textStream=bp.getInputStream();
buff= newBufferedInputStream(textStream);
r= newInputStreamReader(buff, strEncoding);
br= newBufferedReader(r);
StringBuffer strHtml= new StringBuffer("");
String strLine= null;while ((strLine = br.readLine()) != null) {
System.out.println(strLine);
strHtml.append(strLine+ "\r\n");
}
br.close();
r.close();
textStream.close();returnstrHtml.toString();
}catch(Exception e) {
e.printStackTrace();
}finally{try{if (br != null)
br.close();if (buff != null)
buff.close();if (textStream != null)
textStream.close();
}catch(Exception e) {
}
}return null;
}/*** 获取mht网页文件中内容代码的编码
*
*@parambp
*@return
*/
private staticString getEncoding(MimeBodyPart bp) {if (bp == null) {return null;
}try{
Enumeration list=bp.getAllHeaders();while(list.hasMoreElements()) {
javax.mail.Header head=(javax.mail.Header) list.nextElement();if (head.getName().equalsIgnoreCase("Content-Type")) {
String strType=head.getValue();int pos = strType.indexOf("charset=");if (pos >= 0) {
String strEncoding= strType.substring(pos + 8,
strType.length());if (strEncoding.startsWith("\"")|| strEncoding.startsWith("\'")) {
strEncoding= strEncoding.substring(1,
strEncoding.length());
}if (strEncoding.endsWith("\"")|| strEncoding.endsWith("\'")) {
strEncoding= strEncoding.substring(0,
strEncoding.length()- 1);
}if (strEncoding.toLowerCase().compareTo("gb2312") == 0) {
strEncoding= "gbk";
}returnstrEncoding;
}
}
}
}catch(MessagingException e) {
e.printStackTrace();
}return null;
}/*** 删除指定文件
*@paramfilePath 文件路径
*@paramfileName 文件名称
*@paramlayout 文件格式*/
public static voiddeleteFileName(String filePath , String fileName , String layout){
File folder= newFile(filePath);
String fileNameOnLayout=fileName+"."+layout;
File[] files= folder.listFiles(); //获取该文件夹下的所有文件
for(File file:files){if(file.getName().equals(fileNameOnLayout)){
file.delete();
}
}
}
}