Detailed Java Crawl Web page picture, Java use regular expression crawl site picture _java

Use Java to crawl all the pictures on a Web page:

With two regular expressions:

1, matching the HTML IMG tags in the regular: ]*?>

2, matching the IMG tags in src in the HTTP path of the regular: Http:\ "? (.*?) (\ "|>|\\s+")

Realize:

Package org.swinglife.main; 
Import Java.io.File; 
Import Java.io.FileOutputStream; 
Import Java.io.InputStream; 
Import Java.net.URL; 
Import java.net.URLConnection; 
Import java.util.ArrayList; 
Import java.util.List; 
Import Java.util.regex.Matcher; 
 
Import Java.util.regex.Pattern; /*** * Java Crawl network picture * @author Swinglife * */public class Catchimage {//address private static final String UR 
  L = "Http://www.csdn.net"; 
  Code private static Final String ecoding = "UTF-8"; Get the IMG tag regular private static final String Imgurl_reg = "]*?> "; Get the regular private static final String Imgsrc_reg = "http:\" for the SRC path? (.*?) 
 
   
  (\ "|>|\\s+"); 
    public static void Main (string[] args) throws Exception {catchimage cm = new catchimage (); 
    Get HTML text content String HTML = cm.gethtml (URL); 
    Get Picture label list<string> Imgurl = Cm.getimageurl (HTML); 
    Get picture src address list<string> imgsrc = CM.GETIMAGESRC (Imgurl); Download picturePiece cm. 
  Download (IMGSRC); /*** * Obtain HTML content * * @param URL * @return * @throws Exception/private String get 
    HTML (String url) throws Exception {URL uri = new URL (URL); 
    URLConnection connection = Uri.openconnection (); 
    InputStream in = Connection.getinputstream (); 
    byte[] buf = new byte[1024]; 
    int length = 0; 
    StringBuffer sb = new StringBuffer (); 
    while (length = In.read (buf, 0, buf.length)) > 0) {sb.append (new String (BUF, ecoding)); 
    } in.close (); 
  return sb.tostring (); /*** * Get imageurl Address * * @param HTML * @return/private list<string> Getimageurl (stri 
    ng HTML) {Matcher Matcher = Pattern.compile (Imgurl_reg). Matcher (HTML); 
    list<string> Listimgurl = new arraylist<string> (); 
    while (Matcher.find ()) {Listimgurl.add (Matcher.group ()); 
  return listimgurl; /*** * Get imagesrc address * * @param Listimageurl * @return * * Private list<string> GETIMAGESRC (list<string> listimageurl) {list& Lt 
    string> listimgsrc = new arraylist<string> (); 
      for (String image:listimageurl) {Matcher Matcher = Pattern.compile (Imgsrc_reg). Matcher (image); 
      while (Matcher.find ()) {Listimgsrc.add (Matcher.group (). substring (0, Matcher.group (). Length ()-1)); 
  } return LISTIMGSRC; 
    /*** * Download Picture * * * @param listimgsrc * * private void Download (list<string> listimgsrc) { try {for (string url:listimgsrc) {string imagename = Url.substring (Url.lastindexof ("/") + 1, Url.leng 
        th ()); 
        URL uri = new URL (URL); 
        InputStream in = Uri.openstream (); 
        FileOutputStream fo = new FileOutputStream (new File (imagename)); 
        byte[] buf = new byte[1024]; 
        int length = 0; 
        System.out.println ("Start download:" + URL); while (length = In.read (buf, 0, buf.length))!=-1) {fo.write (buf, 0, length); 
        } in.close (); 
        Fo.close (); 
      System.out.println (imagename + "Download Complete"); 
    The catch (Exception e) {System.out.println ("Download Failed"); 
 } 
  } 
 
   
}

The above is the entire content of this article, I hope to help you learn, but also hope that we support the cloud habitat community.