java正则表达式 提取img_JAVA正则表达式,提取img的src问题!!! | 学步园

Pattern  p = Pattern.compile("href\\s*=\\s*(?:"([^"]*)"|'([^']*)'|([^"'>\s]+))");//这个不正确

/**

* 得到网页中图片的地址

*/

public static List getImgStr(String htmlStr){

String img="";

Pattern p_image;

Matcher m_image;

List pics = new ArrayList();

//     String regEx_img = "]*?>"; //图片链接地址

String regEx_img = "]*?>"; 

p_image = Pattern.compile

(regEx_img,Pattern.CASE_INSENSITIVE);

m_image = p_image.matcher(htmlStr);

while(m_image.find()){

img = img + "," + m_image.group();

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

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

while(m.find()){

pics.add(m.group(1));

}

}

return pics;

}

         //重点在于正则表达式 ]*?>   

//               src=\"?(.*?)(\"|>|\\s+)

private final static String regxpForHtml = "]*)>"; // 过滤所有以结尾的标签

private final static String regxpForImgTag = "]*)\\s*>"; // 找出IMG标签

private final static String regxpForImaTagSrcAttrib = "src=\"([^\"]+)\""; // 找出IMG标签的SRC属性

String regxp = "]*)\\s*>";  红色的 tag 是动态的变(指定标签)

1. public static String getImgStr(String htmlStr){

2.         String img="",tmp="";

3.         java.util.regex.Pattern p_image;

4.         java.util.regex.Matcher m_image;

5.

6.         String regEx_img = "http://[([a-z0-9]|.|/|\\-)]+.[(jpg)|(bmp)|(gif)|(png)]";//图片链接地址

7.         p_image = java.util.regex.Pattern.compile(regEx_img,java.util.regex.Pattern.CASE_INSENSITIVE);

8.         m_image = p_image.matcher(htmlStr);

9.         while(m_image.find()){

10.             img = img + "," + m_image.group();

11.         }

12.         if(img.indexOf(",")>=0)

13.             return img.substring(1);

14.         else

15.             return img;

16.    }

方法一：

http://www.cnblogs.com/jintan/archive/2009/10/31/1593639.html

package com.cn;

import java.util.ArrayList;

import java.util.List;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

public class img_src {

public   static   void   main(String[]   args)   {

String   html   =   "\r\n"   +

"

test\r\n"   +

"

"   +

"

abcdefg"   +

                "
"   +  

"

"       src=\"abc.jpg\"   \r\n"   +

"   weight=\"30\">abcdefg         \r\n"   +

                "   "   +  

                "   "   +  

//                 ""   +   //这种我也无能为力  

"";

System.out.println(getImgSrc(html));

}

public   static   final   Pattern   PATTERN   =   Pattern.compile("]*)src\\s*=\\s*([^>]+)",   Pattern.CASE_INSENSITIVE   |   Pattern.MULTILINE);  

public   static   List   getImgSrc(String   html)   {

Matcher   matcher   =   PATTERN.matcher(html);

List   list   =   new   ArrayList();

while   (matcher.find())   {

String   group   =   matcher.group(1);

if   (group   ==   null)   {

continue;

}

//   这里可能还需要更复杂的判断,用以处理src="...."内的一些转义符

if   (group.startsWith("'"))   {

list.add(group.substring(1,   group.indexOf("'",   1)));

}   else   if   (group.startsWith("\""))   {

list.add(group.substring(1,   group.indexOf("\"",   1)));

}   else   {

list.add(group.split("\\s")[0]);

}

}

return   list;

}

}

方法二：

package com.cn;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

public class test {

public static void main(String[] args) {

String s = "<IMG height=55 src=\"http://www.gobygo.com/TheGoByGo/images/book-channel.gif\" width=210 border=0 />";

Pattern p1 = Pattern.compile("<IMG[\\w\\s\\d\\p{Punct}]*/>");

Matcher m = p1.matcher(s);

while (m.find()) {

String str = m.group();

Pattern p = Pattern.compile("src=\"[\\w\\s\\d\\p{Punct}]*\"");

Matcher m1 = p.matcher(s);

while (m1.find()) {

String str1 = m1.group();

str = str1.substring(5, str1.length() - 1);

System.out.println(str);

}

}

}

}