Java讀取網(wǎng)頁(yè)內(nèi)容并下載圖片的實(shí)例
“真誠(chéng)服務(wù)，讓網(wǎng)絡(luò)創(chuàng)造價(jià)值”是我們的服務(wù)理念，成都創(chuàng)新互聯(lián)團(tuán)隊(duì)十多年如一日始終堅(jiān)持在網(wǎng)站建設(shè)領(lǐng)域,為客戶(hù)提供優(yōu)質(zhì)服。不管你處于什么行業(yè)，助你輕松跨入“互聯(lián)網(wǎng)+”時(shí)代，PC網(wǎng)站+手機(jī)網(wǎng)站+公眾號(hào)+小程序定制開(kāi)發(fā)。
很多人在第一次了解數(shù)據(jù)采集的時(shí)候，可能無(wú)從下手，尤其是作為一個(gè)新手，更是感覺(jué)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(qǐng)大家指正。寫(xiě)出這篇目的，就是希望大家一起成長(zhǎng)，我也相信技術(shù)之間沒(méi)有高低，只有互補(bǔ)，只有分享，才能使彼此更加成長(zhǎng)。
示例代碼：
重慶分公司
重慶分公司
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(lèi)對(duì)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(gè)BufferedReader對(duì)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);
}
}如有疑問(wèn)請(qǐng)留言或者到本站社區(qū)交流討論，感謝閱讀，希望能幫助到大家，謝謝大家對(duì)本站的支持！
