Java讀取網(wǎng)頁內(nèi)容并下載圖片的實例

很多人在第一次了解數(shù)據(jù)采集的時候,可能無從下手,尤其是作為一個新手,更是感覺很是茫然,所以,在這里分享一下自己的心得,希望和大家一起分享技術(shù),如果有什么不足,還請大家指正。寫出這篇目的,就是希望大家一起成長,我也相信技術(shù)之間沒有高低,只有互補,只有分享,才能使彼此更加成長。
示例代碼:
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("取網(wǎng)絡(luò)圖片");
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("圖片獲取成功");
} 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); // 創(chuàng)建URL類對象
BufferedReader ii = new BufferedReader(new InputStreamReader(uu
.openStream())); // //使用openStream得到一輸入流并由此構(gòu)造一個BufferedReader對象
String input;
while ((input = ii.readLine()) != null) { // 建立讀取循環(huán),并判斷是否有讀取值
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);
}
}
當前名稱:Java讀取網(wǎng)頁內(nèi)容并下載圖片的實例-創(chuàng)新互聯(lián)
標題來源:http://www.jbt999.com/article14/ddsede.html
成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián),為您提供域名注冊、網(wǎng)站改版、服務(wù)器托管、Google、品牌網(wǎng)站制作、移動網(wǎng)站建設(shè)
聲明:本網(wǎng)站發(fā)布的內(nèi)容(圖片、視頻和文字)以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主,如果涉及侵權(quán)請盡快告知,我們將會在第一時間刪除。文章觀點不代表本網(wǎng)站立場,如需處理請聯(lián)系客服。電話:028-86922220;郵箱:[email protected]。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載,或轉(zhuǎn)載時需注明來源: 創(chuàng)新互聯(lián)
猜你還喜歡下面的內(nèi)容