Java读取网页内容并下载图片的实例

java读取网页内容并下载图片的实例

     很多人在第一次了解数据采集的时候，可能无从下手，尤其是作为一个新手，更是感觉很是茫然，所以，在这里分享一下自己的心得，希望和大家一起分享技术，如果有什么不足，还请大家指正。写出这篇目的，就是希望大家一起成长，我也相信技术之间没有高低，只有互补，只有分享，才能使彼此更加成长。  

示例代码：

import java.io.bufferedinputstream;
import java.io.bufferedreader;
import java.io.file;
import java.io.filenotfoundexception;
import java.io.fileoutputstream;
import java.io.ioexception;
import java.io.inputstreamreader;
import java.net.malformedurlexception;
import java.net.url;
import java.util.regex.matcher;
import java.util.regex.pattern;

public class getcontentpicture {
public void gethtmlpicture(string httpurl) {
url url;
bufferedinputstream in;
fileoutputstream file;
try {
  system.out.println("取网络图片");
  string filename = httpurl.substring(httpurl.lastindexof("/"));
  string filepath = "./pic/";
  url = new url(httpurl);

  in = new bufferedinputstream(url.openstream());

  file = new fileoutputstream(new file(filepath+filename));
  int t;
  while ((t = in.read()) != -1) {
  file.write(t);
  }
  file.close();
  in.close();
  system.out.println("图片获取成功");
} catch (malformedurlexception e) {
  e.printstacktrace();
} catch (filenotfoundexception e) {
  e.printstacktrace();
} catch (ioexception e) {
  e.printstacktrace();
}
}

public string gethtmlcode(string httpurl) throws ioexception {
string content ="";
url uu = new url(httpurl); // 创建url类对象
bufferedreader ii = new bufferedreader(new inputstreamreader(uu
  .openstream())); // //使用openstream得到一输入流并由此构造一个bufferedreader对象
string input;
while ((input = ii.readline()) != null) { // 建立读取循环，并判断是否有读取值
  content += input;
}
ii.close();
return content;
}

public void get(string url) throws ioexception {

string searchimgreg = "(?x)(src|src|background|background)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|jpg|png|png|gif|gif)))('|\")";
string searchimgreg2 = "(?x)(src|src|background|background)=('|\")(http://([\\w-]+\\.)+[\\w-]+(:[0-9]+)*(/[\\w-]+)*(/[\\w-]+\\.(jpg|jpg|png|png|gif|gif)))('|\")";

string content = this.gethtmlcode(url);
system.out.println(content);

pattern pattern = pattern.compile(searchimgreg);
matcher matcher = pattern.matcher(content);
while (matcher.find()) {
  system.out.println(matcher.group(3));
  this.gethtmlpicture(url+matcher.group(3));

}

pattern = pattern.compile(searchimgreg2);
matcher = pattern.matcher(content);
while (matcher.find()) {
  system.out.println(matcher.group(3));
  this.gethtmlpicture(matcher.group(3));

}
// searchimgreg =
// "(?x)(src|src|background|background)=('|\")/?(([\\w-]+/)*([\\w-]+\\.(jpg|jpg|png|png|gif|gif)))('|\")";
}
public static void main(string[] args) throws ioexception {
string url = "http://www.baidu.com/";
getcontentpicture gcp = new getcontentpicture();
gcp.get(url);
}
}

如有疑问请留言或者到本站社区交流讨论，感谢阅读，希望能帮助到大家，谢谢大家对本站的支持！