很多人在第一次了解数据采集的时候，可能无从下手，尤其是作为一个新手，更是感觉很是茫然，所以，在这里分享一下自己的心得，希望和大家一起分享技术，如果有什么不足，还请大家指正。写出这篇目的，就是希望大家一起成长，我也相信技术之间没有高低，只有互补，只有分享，才能使彼此更加成长。
示例代码：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
|
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("取网络图片");
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("图片获取成功");
} 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); // 创建URL类对象
BufferedReader ii = new BufferedReader(new InputStreamReader(uu
.openStream())); // //使用openStream得到一输入流并由此构造一个BufferedReader对象
String input;
while ((input = ii.readLine()) != null) { // 建立读取循环，并判断是否有读取值
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);
}
}
|
如有疑问请留言或者到本站社区交流讨论，感谢阅读，希望能帮助到大家，谢谢大家对本站的支持！
原文链接：http://blog.csdn.net/rickiyeat/article/details/55832817