本文目录一览：
java爬虫读取某一张指定图片的url，求解答
使用jsoup解析到这个url就行，dom结构如下:
look-inside-cover类只有一个，所以直接找到这个img元素，获取src属性，就可以获取到图片路径。
代码实现如下：
Document doc = Jsoup.connect("").get();
Elements imgs = doc.select(".look-inside-cover");
String imgUrl = imgs.get(0).attr("src");
jsoup的jar包分享给你：
用java编写一个 图书馆图书借阅管理系统
---------------------------------------------------
给你修改了三个地方：
1.borrowBooks方法中，将System.out.println("你要借吗？"); 改为：
System.out.println("你要借吗？输入1表示借，其他数字表示不借。");
保证输入的时候输入的数字，否则会报出异常。
2.borrowBooks方法中，将self[score] = all[9]; 改为：self[score] = all[i];
如果是all[9]，那么就始终是最后一本书籍信息了。
3.have方法中，你是想将所借的书籍信息都打印出来。修改的比较多，下面注释代码是原来的。
void have(Books[] self) {
// for (int i = 0; i 2; i++) {
// self[i].showBookInfo();
// }
for (int i = 0; i 3; i++) {
if(self[i]!=null)
self[i].showBookInfo();
}
}
****************** 附上所有代码：*************************
import java.util.Scanner;
public class TestBook {
public static void main(String[] args) {
Books all[] = new Books[10];
Books self[] = new Books[3];
all[0] = new Books("java", 1, "12345", "tom", 34.0f, "人民出版社");
all[1] = new Books("c", 2, "12346", "tnn", 31.0f, "人民出版社");
all[2] = new Books("c++", 3, "12445", "mm", 35.0f, "人民出版社");
all[3] = new Books("c#", 4, "12365", "tt", 38.0f, "人民出版社");
all[4] = new Books("j2se", 5, "13345", "tosm", 31.1f, "人民出版社");
all[5] = new Books("j2ee", 6, "18345", "ttm", 32.0f, "人民出版社");
all[6] = new Books("jsp", 7, "12335", "cc", 33.0f, "人民出版社");
all[7] = new Books("net", 8, "12341", "bb", 36.0f, "人民出版社");
all[8] = new Books("ip", 9, "12343", "aa", 37.0f, "人民出版社");
all[9] = new Books("tcp", 10, "22345", "jj", 39.0f, "人民出版社");
Readers r = new Readers("xiaoming", 101, "1", 3);
r.searchAllBooks(all);
r.borrowBooks(all, self);
r.have(self);
r.give(all, self);
}
}
class Readers {
Scanner scan = new Scanner(System.in);
String names;
int nums;
String classes;
int grade;
int score = 0;
// Books self[]=new Books[3];
Readers(String n, int u, String c, int g) {
names = n;
nums = u;
classes = c;
grade = g;
}
void searchAllBooks(Books[] all) {// 查书
for (int i = 0; i 10; i++)
all[i].showBookInfo();
// self[score]=all[0];
}
void give(Books[] all, Books[] self) {// 还书
System.out.println("请输入您要还的书的书号");
int n = scan.nextInt();
for (int i = 0; i 10; i++) {
if (n == all[i].num) {
for (int j = 0; j 3; j++) {
if (self[j] == all[i]) {
self[j] = null;
System.out.println("还书成功");
}
}
}
}
}
void have(Books[] self) {
// for (int i = 0; i 2; i++) {
// self[i].showBookInfo();
// }
for (int i = 0; i 3; i++) {
if(self[i]!=null)
self[i].showBookInfo();
}
}
void giveMoney() {
}
void borrowBooks(Books[] all, Books[] self) {
System.out.println("请输入您要查找的书名：");
String n = scan.next();
int i;
for (i = 0; i 10; i++) {
if (n.equals(all[i].name)) {
all[i].showBookInfo();
break;
}
}
//System.out.println("你要借吗？");
System.out.println("你要借吗？输入1表示借，其他数字表示不借。");
int j;
j = scan.nextInt();
if (j == 1) {
System.out.println("借阅成功");
//self[score] = all[9];
self[score] = all[i];
score += 1;
}
if (score 4) {
System.out.println("您还可以借阅" + (3 - score) + "本");
} else {
System.out.println("对不起，一个人只能借3本");
}
}
}
class Books {
String name;
int num;
String ISBN;
String writer;
float price;
String publisher;
Books(String n, int u, String i, String w, float p, String l) {
name = n;
num = u;
ISBN = i;
writer = w;
price = p;
publisher = l;
}
void showBookInfo() {
System.out.println("**************************");
System.out.println("书名：" + name);
System.out.println("索书号：" + num);
System.out.println("ISBN号：" + ISBN);
System.out.println("价格：" + price);
System.out.println("出版社：" + publisher);
System.out.println("**************************");
}
}
----------------------------------------------------
用java写爬虫程序，有个网站获取不到链接，求指导
//读取网页上的内容方法---------------------2010.01.25 public String getOneHtml(String htmlurl) throws IOException {
URL url;
String temp;
final StringBuffer sb = new StringBuffer();
try {
url = new URL(htmlurl);
// 读取网页全部内容
final BufferedReader in = new BufferedReader(new InputStreamReader(
url.openStream(),"GBK"));
while ((temp = in.readLine()) != null) {
sb.append(temp);
}
in.close();
} catch (final MalformedURLException me) {
System.out.println("你输入的URL格式有问题！请仔细输入");
me.getMessage();
} catch (final IOException e) {
e.printStackTrace();
}
return sb.toString();
}上面这个方法是根据你传入的url爬取整个网页的内容，然后你写个正则表达式去匹配这个字符串的内容。
