java 正则 img_java 正则表达式 网页爬虫（获取一个网页中的图片<img src=""/>

public class WebCrawler { public static void

main(String[] agrs) throws HttpException, IOException{ //要访问的网页URL

String url="http://caikan.com//platform//index.do"; HttpClient

httpClient=new HttpClient(); HttpMethod method=new GetMethod(url);

httpClient.executeMethod(method); String response=null;

if(method.getStatusCode()==HttpStatus.SC_OK){

response=method.getResponseBodyAsString(); } //释放httpClient连接

method.releaseConnection(); //定义正则表达式：获取图片，()表示分组 String

regex="[\\w\\W]*?";

//将返回的网页内容存储成一个 文本文件保存在本地文件夹filetext中，文件名为通过url截取 String

name=url.substring(url.lastIndexOf("/")); File file=new

File("D:\\filetext\\" name ".txt"); FileWriter os=new

FileWriter(file); BufferedWriter bw=new BufferedWriter(os);

//将response写入文件file中 bw.write(response); //从刚保存的文件中获取response内容

FileReader fr=new FileReader(file); BufferedReader br=new

BufferedReader(fr); //当前行的内容 String lineStr=""; //逐行进行判断

while((lineStr=br.readLine())!= null){ Pattern

p=Pattern.compile(regex); Matcher m=p.matcher(lineStr);

if(m.find()){ String src=m.group(1); //判断src的格式的正则表达式 String

regex1="http://[\\W\\w]*?"; Pattern p1=Pattern.compile(regex1);

Matcher m1=p1.matcher(src); //url2作用是特定的图片地址，直接获取 URL url2=null;

if(m1.matches()){ url2=new URL(src); }else{ String

basepath=url.substring(0, url.lastIndexOf("/")); url2=new

URL(basepath "//" src); } //根据src截取图片文件名 String

filename=src.substring(src.lastIndexOf("/") 1); //将图片保存到本地文件中

BufferedImage currentImage=javax.imageio.ImageIO.read(url2);

javax.imageio.ImageIO.write(currentImage, "jpg", new

File("D:\\webImage\\" filename)); } } //关掉所有流 fr.close();

br.close(); os.close(); System.out.println("执行完毕"); }}