java正则表达式爬图片_正则表达式抓取网页面上所有图片-优快云博客

本文介绍了一个简单的Java程序，用于从指定网址抓取所有图片资源，包括不同格式的图片文件如jpg、png和gif等。该程序通过发送HTTP请求获取网页内容，并使用正则表达式匹配所有图片的URL。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

packagecom.roadway.test;importjava.io.InputStream;importjava.net.HttpURLConnection;importjava.net.URL;importjava.util.regex.Matcher;importjava.util.regex.Pattern;publicclassTeskSRC {publicString getHtmlCode(String httpUrl) {

String htmlCode="";try{

InputStream in;

URL url=newjava.net.URL(httpUrl);

HttpURLConnection connection=(HttpURLConnection) url

.openConnection();

connection=(HttpURLConnection) url.openConnection();

connection.setRequestProperty("User-Agent","Mozilla/4.0");

connection.connect();

in=connection.getInputStream();byte[] buffer=newbyte[512];intlength=-1;while((length=in.read(buffer,0,512))!=-1){

htmlCode+=newString(buffer,0,length);

}

}catch(Exception e) {

}if(htmlCode==null){return"";

}returnhtmlCode;

}publicstaticvoidmain(String[] args){

TeskSRC ts=newTeskSRC();

String searchImgReg="(?x)(src|SRC|background|BACKGROUND)=('|\")(http://([\\w-]+\\.)+[\\w-]+(:[0-9]+)*(/[\\w-]+)*(/[\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")";String content=ts.getHtmlCode("http://www.163.com");

Pattern pattern=Pattern.compile(searchImgReg);

Matcher matcher=pattern.matcher(content);while(matcher.find()){

System.out.println(matcher.group(3));

}//searchImgReg = "(?x)(src|SRC|background|BACKGROUND)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|JPG|png|PNG|gif|GIF)))('|\")";}

}