您好,登錄后才能下訂單哦!
Java讀取網頁內容并下載圖片的實例
很多人在第一次了解數據采集的時候,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,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("取網絡圖片"); 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造一個BufferedReader對象 String input; while ((input = ii.readLine()) != null) { // 建立讀取循環,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); } }
如有疑問請留言或者到本站社區交流討論,感謝閱讀,希望能幫助到大家,謝謝大家對本站的支持!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。