Commit7a448d0

authored

Create Web Crawler.java

1 parent2ab62d1 commit7a448d0Copy full SHA for 7a448d0

File tree

+31

-0

lines changed

+31

-0

lines changed

Lines changed: 31 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,31 @@`
	`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`	`+classSolution {`
	`9`	`+publicList<String>crawl(StringstartUrl,HtmlParserhtmlParser) {`
	`10`	`+Set<String>visited =newHashSet<>();`
	`11`	`+Stack<String>stack =newStack<>();`
	`12`	`+stack.push(startUrl);`
	`13`	`+Stringhostname =getHostname(startUrl);`
	`14`	`+while(!stack.isEmpty()) {`
	`15`	`+Stringpopped =stack.pop();`
	`16`	`+visited.add(popped);`
	`17`	`+List<String>connectedUrls =htmlParser.getUrls(popped);`
	`18`	`+for (Stringurl :connectedUrls) {`
	`19`	`+if (!visited.contains(url) &&url.contains(hostname)) {`
	`20`	`+stack.push(url);`
	`21`	`+ }`
	`22`	`+ }`
	`23`	`+ }`
	`24`	`+returnnewArrayList<>(visited);`
	`25`	`+ }`
	`26`	`+`
	`27`	`+privateStringgetHostname(Stringurl) {`
	`28`	`+String[]splits =url.split("/");`
	`29`	`+returnsplits[2];`
	`30`	`+ }`
	`31`	`+}`

Comments

(0)