資源簡介
基于jsoup解析網(wǎng)頁獲取圖片鏈接并下載的例子,關于下載部分有詳細注釋,其余地方也有方法注釋,若是想用Java做爬蟲初學的話,可以看看,忘有用。(附源碼,pom文件,和jsoup的jar包)免去你再找了

代碼片段和文件信息
package?com.img.p;
import?java.io.ByteArrayOutputStream;
import?java.io.File;
import?java.io.FileOutputStream;
import?java.io.InputStream;
import?java.net.HttpURLConnection;
import?java.net.URL;
import?java.util.List;
public?class?Download?{
??public?void?downloadList(String?pathList?list)?{
????try?{
??????for?(ImgPojo?imgPojo?:?list)?downloadLocal(pathimgPojo.getId()?imgPojo.getSrc());
????}?catch?(Exception?e)?{
??????e.printStackTrace();
????}
??}
??public?void?downloadLocal(String?pathString?name?String?imgUrl)?throws?Exception?{
????//?new一個URL對象
????URL?url?=?new?URL(imgUrl);
????//?打開鏈接
????HttpURLConnection?conn?=?(HttpURLConnection)?url.openConnection();
????//?設置請求方式為“GET“
????conn.setRequestMethod(“GET“);
????//?超時響應時間為5秒
????conn.setConnectTimeout(5?*?1000);
????//?通過輸入流獲取圖片數(shù)據(jù)
????InputStream?inStream?=?conn.getInputStream();
????//?得到圖片的二進制數(shù)據(jù),以二進制封裝得到數(shù)據(jù),具有通用性
????byte[]?data?=?readInputStream(inStream);
????//?new一個文件對象用來保存圖片,默認保存當前工程根目錄
????File?imageFile?=?new?File(path+“\\id=“+name+“.jpg“);
????//?創(chuàng)建輸出流
????FileOutputStream?outStream?=?new?FileOutputStream(imageFile);
????//?寫入數(shù)據(jù)
????outStream.write(data);
????//?關閉輸出流
????outStream.close();
????System.out.println(name+“下載ok“);
??}
??public?byte[]?readInputStream(InputStream?inStream)?throws?Exception?{
????ByteArrayOutputStream?outStream?=?new?ByteArrayOutputStream();
????//?創(chuàng)建一個Buffer字符串
????byte[]?buffer?=?new?byte[1024];
????//?每次讀取的字符串長度,如果為-1,代表全部讀取完畢
????int?len?=?0;
????//?使用一個輸入流從buffer里把數(shù)據(jù)讀取出來
????while?((len?=?inStream.read(buffer))?!=?-1)?{
??????//?用輸出流往buffer里寫入數(shù)據(jù),中間參數(shù)代表從哪個位置開始讀,len代表讀取的長度
??????outStream.write(buffer?0?len);
????}
????//?關閉輸入流
????inStream.close();
????//?把outStream里的數(shù)據(jù)寫入內存
????return?outStream.toByteArray();
??}
}
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????文件???????2211??2018-11-03?18:30??爬蟲(p站圖片)\Download.java
?????文件???????5081??2018-11-04?13:58??爬蟲(p站圖片)\FromP.java
?????文件????????671??2018-11-04?13:58??爬蟲(p站圖片)\ImgPojo.java
?????文件?????395748??2018-11-04?17:00??爬蟲(p站圖片)\jsoup-1.11.3.jar
?????文件????????254??2018-11-04?17:01??爬蟲(p站圖片)\jsoup_pom.txt
?????文件???????3006??2018-11-04?14:43??爬蟲(p站圖片)\Myfr
?????文件????????202??2018-11-04?17:06??爬蟲(p站圖片)\需知.txt
?????目錄??????????0??2018-11-04?17:01??爬蟲(p站圖片)
-----------?---------??----------?-----??----
???????????????407173????????????????????8
評論
共有 條評論