检索web页面中所有链接
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.regex.PatternSyntaxException;
public class HerfMatch
{
public static void main(String[] args)
{
try
{
String urlString = "http://www.zhuoda.org/app";
InputStreamReader in = new InputStreamReader(new URL(urlString).openStream());
StringBuffer input = new StringBuffer();
int ch;
while ((ch = in.read()) != -1)
input.append((char)ch);
String patternString = "<[a|A]\\s+href=([^>]*\\s*>)";
Pattern pattern = Pattern.compile(patternString, Pattern.CASE_INSENSITIVE);
Matcher matcher = pattern.matcher(input);
int i = 0;
while (matcher.find())
{
int start = matcher.start();
int end = matcher.end();
String match = input.substring(start, end);
System.out.println(++i + " : " + match);
}
}catch (IOException exception){
exception.printStackTrace();
}catch (PatternSyntaxException exception){
exception.printStackTrace();
}
}
}
1 : <a href="/">
2 : <a href="/app">
3 : <a href="/photo/">
4 : <a href="/bbs/index.jsp">
5 : <a href="/blog/admin/post/addPost0.jsp">
6 : <a href="/users3/index.jsp">
7 : <a href="/users3/register.jsp">
8 : <a href="/blog/admin/general/blogForm.jsp?action=create">
9 : <a href="/blog/admin/post/addPost0.jsp">
10 : <a href="/blog/login.jsp?retUrl=/app" title="登录到本页面">
11 : <a href="/blog/admin/index.jsp" title="进入后台">
12 : <a href="/blog/logout" title="退出本次登录">
13 : <a href="/blog/logout?cmd=erase" title="退出并取消自动登录(自动登录时限为14天)">
14 : <a href="/weiking/52353.html">
15 : <a href="/weiking/33303.html">
16 : <a href="/joy2005/">
17 : <a href="/zhanglf/">
18 : <a href="/wentao/">
19 : <a href="/baby920/">
20 : <a href="/pear/">
21 : <a href="/irini/">
22 : <a href="/wodezhuoda/">
23 : <a href="/flydreams/">
24 : <a href="/air_tuyh/">
25 : <a href="/Angel/">
26 : <a href="/yapeng/">
27 : <a href="/weiking/">
28 : <a href="/study/">
29 : <a href="/hofman/">
30 : <a href="/Jane/">
31 : <a href="/english/">
32 : <a href="/haohao/">
33 : <a href="/lunzi/">
34 : <a href="/firebird/">
35 : <a href="/coffee/">
36 : <a href="/blogList.jsp?type=all">
37 : <a href="/junking25/66289.html">
38 : <a href="/english/66522.html">
39 : <a href="/hofman/66549.html">
40 : <a href="/yapeng/66416.html">
41 : <a href="/luotuo8895/66805.html">
42 : <a href="/Jane/66895.html">
43 : <a href="/Jane/67061.html">
44 : <a href="/junking25/66289.html">
45 : <a href="/pear/67075.html">
46 : <a href="/weiking/66742.html">
47 : <a href=/disTag.jsp?id=946>
48 : <a href=/disTag.jsp?id=976>
49 : <a href=/disTag.jsp?id=1006>
50 : <a href=/disTag.jsp?id=931>
51 : <a href=/disTag.jsp?id=934>
52 : <a href=/disTag.jsp?id=946>
53 : <a href=/disTag.jsp?id=2522>
54 : <a href=/disTag.jsp?id=2521>
55 : <a href=/disTag.jsp?id=2506>
56 : <a href=/disTag.jsp?id=2496>
57 : <a href=/disTag.jsp?id=2495>
58 : <a href="/app?service=external&page=ViewNewPost&sp=1">
59 : <a href="/joy2005/67364.html">
60 : <a href="/wentao/67354.html">
61 : <a href="/wentao/67352.html">
62 : <a href="/yapeng/67350.html">
63 : <a href="/baby920/67347.html">
64 : <a href="/pear/67344.html">
65 : <a href="/weiking/67320.html">
66 : <a href="/pear/67341.html">
67 : <a href="/irini/67335.html">
68 : <a href="/wodezhuoda/67331.html">
69 : <a href="/flydreams/67326.html">
70 : <a href="/Angel/67318.html">
71 : <a href="/Angel/67316.html">
72 : <a href="/Jack/67306.html">
73 : <a href="/Jack/67314.html">
74 : <a href="/subjectIndex2.jsp">
75 : <a href="/yapeng/67350.html">
76 : <a href="/luotuo8895/66314.html">
77 : <a href="/lunzi/66097.html">
78 : <a href="/yapeng/66058.html">
79 : <a href="/luotuo8895/65567.html">
80 : <a href="/yapeng/65538.html">
81 : <a href="/yxblium/63293.html">
82 : <a href="/liry945/63107.html">
83 : <a href="/weiking/33303.html">
84 : <a href="/lunzi/62154.html">
85 : <a href="/weiking/61816.html">
86 : <a href="/haohao/61565.html">
87 : <a href="/lunzi/61631.html">
88 : <a href="/haohao/61610.html">
89 : <a href="/wenbo/60924.html">
90 : <a href="/lunzi/60838.html">
91 : <a href="/lunzi/60524.html">
92 : <a href="/lunzi/59586.html">
93 : <a href="/lunzi/59220.html">
94 : <a href="/yapeng/58697.html">
95 : <a href="/subjectIndex.jsp">
96 : <a href="/hofman/65767.html">
97 : <a href="/hofman/65270.html">
98 : <a href="/hofman/65060.html">
99 : <a href="/baby920/67347.html">
100 : <a href="/baby920/67347.html">
101 : <a href="/pear/67341.html">
102 : <a href="/Jack/67306.html">
103 : <a href="/pear/67341.html">
104 : <a href="/weiking/67320.html">
105 : <a href="/Jane/67198.html">
106 : <a href="/pear/67341.html">
107 : <a href="/weiking/67320.html">
108 : <a href="/pear/67257.html">
109 : <a href="/Jane/67198.html">
110 : <a href="/Jack/67306.html">
111 : <a href="/pear/67257.html">
112 : <a href="/pear/67097.html">
113 : <a href="/pear/67264.html">
114 : <a href="/lady/13567.html">
115 : <a href="/suncity/13309.html">
116 : <a href="/tom/61645.html">
117 : <a href="/ftyushy/45061.html">
118 : <a href="/luotuo8895/21548.html">
119 : <a href="/usage/awstats/2006/09.html">
weiking
2006-09-18 15:23:28
评论:0
阅读:146
引用:0
