Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Commit91dd115

Browse files
committed
Added Web Crawler Multithreaded.java
1 parenta89344a commit91dd115

File tree

1 file changed

+108
-0
lines changed

1 file changed

+108
-0
lines changed
Lines changed: 108 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,108 @@
1+
/**
2+
* // This is the HtmlParser's API interface.
3+
* // You should not implement it, or speculate about its implementation
4+
* interface HtmlParser {
5+
* public List<String> getUrls(String url) {}
6+
* }
7+
*/
8+
importjava.net.URI;
9+
importjava.net.URISyntaxException;
10+
11+
12+
classSolution {
13+
publicList<String>crawl(StringstartUrl,HtmlParserhtmlParser) {
14+
ResultRecordresultRecord =newResultRecord();
15+
CrawlTasktask =newCrawlTask(
16+
startUrl,htmlParser,resultRecord,UrlUtil.parseHostname(startUrl));
17+
try {
18+
task.start();
19+
task.join();
20+
}catch (InterruptedExceptione) {
21+
e.printStackTrace();
22+
}
23+
returnresultRecord.getResultList();
24+
}
25+
}
26+
27+
classCrawlTaskextendsThread {
28+
29+
privatefinalStringurl;
30+
privatefinalHtmlParserhtmlParser;
31+
privatefinalResultRecordresultRecord;
32+
privatefinalStringparentHost;
33+
34+
publicCrawlTask(Stringurl,
35+
HtmlParserhtmlParser,
36+
ResultRecordresultRecord,
37+
StringparentHost) {
38+
this.url =url;
39+
this.htmlParser =htmlParser;
40+
this.resultRecord =resultRecord;
41+
this.parentHost =parentHost;
42+
}
43+
44+
publicvoidrun() {
45+
Stringhostname =UrlUtil.parseHostname(url);
46+
if (!hostname.equals(parentHost)) {
47+
return;
48+
}
49+
if (resultRecord.addIfNotExists(url)) {
50+
List<String>childUrls =htmlParser.getUrls(url);
51+
List<CrawlTask>tasks =newArrayList<>();
52+
for (StringchildUrl :childUrls) {
53+
tasks.add(newCrawlTask(
54+
childUrl,htmlParser,resultRecord,parentHost));
55+
}
56+
try {
57+
for (CrawlTasktask :tasks) {
58+
task.start();
59+
}
60+
for (CrawlTasktask :tasks) {
61+
task.join();
62+
}
63+
}catch (InterruptedExceptione) {
64+
e.printStackTrace();
65+
}
66+
}
67+
}
68+
}
69+
70+
classUrlUtil {
71+
72+
publicstaticStringparseHostname(Stringurl) {
73+
try {
74+
URIuri =newURI(url);
75+
returnuri.getHost();
76+
}catch(URISyntaxExceptione) {
77+
e.printStackTrace();
78+
}
79+
returnnull;
80+
}
81+
}
82+
83+
classResultRecord {
84+
85+
privateSet<String>urls;
86+
privateSemaphoremutex;
87+
88+
publicResultRecord() {
89+
this.urls =newHashSet<>();
90+
this.mutex =newSemaphore(1);
91+
}
92+
93+
publicbooleanaddIfNotExists(Stringurl) {
94+
try {
95+
this.mutex.acquire();
96+
booleanadded =this.urls.add(url);
97+
this.mutex.release();
98+
returnadded;
99+
}catch (InterruptedExceptione) {
100+
e.printStackTrace();
101+
}
102+
returnfalse;
103+
}
104+
105+
publicList<String>getResultList() {
106+
returnnewArrayList<>(urls);
107+
}
108+
}

0 commit comments

Comments
 (0)

[8]ページ先頭

©2009-2025 Movatter.jp