Java读取网页内容并下载图片的实例-创新互联
Java读取网页内容并下载图片的实例
目前创新互联建站已为上1000家的企业提供了网站建设、域名、虚拟空间、网站改版维护、企业网站设计、驻马店网站维护等服务,公司将坚持客户导向、应用为本的策略,正道将秉承"和谐、参与、激情"的文化,与客户和合作伙伴齐心协力一起成长,共同发展。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); } }
网站题目:Java读取网页内容并下载图片的实例-创新互联
URL地址:http://scyanting.com/article/ddsede.html