java替换路径_JAVA-替换html中图片的路径-从html代码中提取图片路径并下载

packagecom.googosoft.until;importjava.io.BufferedInputStream;importjava.io.FileOutputStream;importjava.io.IOException;importjava.net.HttpURLConnection;importjava.net.URL;importjava.util.ArrayList;importjava.util.Date;importjava.util.List;importjava.util.regex.Matcher;importjava.util.regex.Pattern;importorg.junit.Test;public classHtmlUtil {public staticString delHTMLTag(String htmlStr) {

String regEx_script= "

String regEx_style = "

String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式

Pattern p_script=Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);

Matcher m_script=p_script.matcher(htmlStr);

htmlStr= m_script.replaceAll(""); //过滤script标签

Pattern p_style=Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);

Matcher m_style=p_style.matcher(htmlStr);

htmlStr= m_style.replaceAll(""); //过滤style标签

Pattern p_html=Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);

Matcher m_html=p_html.matcher(htmlStr);

htmlStr= m_html.replaceAll(""); //过滤html标签

return htmlStr.trim(); //返回文本字符串

}/*** 根据图片的网络路径将图片下载到本地，并返回本地路径

*@paramurlHttp 图片的网络路径

*@parampath 新生成的图片的目录

*@return

*/

private staticString getPicture2(String urlHttp, String path) {

FileOutputStream out= null;

BufferedInputStream in= null;

HttpURLConnection connection= null;

String newPath= "";byte[] buf = new byte[1024];int len = 0;try{

URL url= newURL(urlHttp);

connection=(HttpURLConnection) url.openConnection();

connection.connect();

in= newBufferedInputStream(connection.getInputStream());

newPath= path + "/" + new Date().getTime() + ".jpg";

out= newFileOutputStream(newPath);while ((len = in.read(buf)) != -1) {

out.write(buf,0, len);

}

out.flush();

}catch(Exception e) {

e.printStackTrace();

}finally{try{

in.close();

out.close();

connection.disconnect();

}catch(IOException e) {

e.printStackTrace();

}

}returnnewPath;

}/*** 提取HTML字符串中的img列表

*@paramhtmlStr 要处理的html字符串

*@return

*/

private static ListgetImgStrList(String htmlStr) {

List list = new ArrayList<>();

String img= "";

Pattern p_image;

Matcher m_image;

String regEx_img= "]*?>";

p_image=Pattern.compile(regEx_img, Pattern.CASE_INSENSITIVE);

m_image=p_image.matcher(htmlStr);while(m_image.find()) {

img=m_image.group();

Matcher m= Pattern.compile("src\\s*=\\s*\"?(.*?)(\"|>|\\s+)").matcher(img);while(m.find()) {

list.add(handleSrc(m.group(1)));

}

}returnlist;

}/*** 去除src路径中的前后单引号

*@paramsrc 图片的src路径

*@return

*/

private staticString handleSrc(String src) {if (src != null) {if (src.startsWith("'")) {return src.substring(1, src.length());

}if (src.endsWith("'")) {return src.substring(0, src.length());

}

}returnsrc;

}

@Testpublic void testTransSrc() throwsException {

String str= "

标题

";

List imgList =getImgStrList(str);for(String img : imgList) {

System.out.println(getPicture2(img,"D://uploadFiles"));

}

}

}