java 网络爬虫怎么实现
4个回答
展开全部
网络爬虫是一个自动提取网页的程序,它为搜索引擎从万维网上下载网页,是搜索引擎的重要组成。
传统爬虫从一个或若干初始网页的URL开始,获得初始网页上的URL,在抓取网页的过程中,不断从当前页面上抽取新的URL放入队列,直到满足系统的一定停止条件。对于垂直搜索来说,聚焦爬虫,即有针对性地爬取特定主题网页的爬虫,更为适合。
以下是一个使用java实现的简单爬虫核心代码:
public void crawl() throws Throwable {
while (continueCrawling()) {
CrawlerUrl url = getNextUrl(); //获取待爬取队列中的下一个URL
if (url != null) {
printCrawlInfo();
String content = getContent(url); //获取URL的文本信息
//聚焦爬虫只爬取与主题内容相关的网页,这里采用正则匹配简单处理
if (isContentRelevant(content, this.regexpSearchPattern)) {
saveContent(url, content); //保存网页至本地
//获取网页内容中的链接,并放入待爬取队列中
Collection urlStrings = extractUrls(content, url);
addUrlsToUrlQueue(url, urlStrings);
} else {
System.out.println(url + " is not relevant ignoring ...");
}
//延时防止被对方屏蔽
Thread.sleep(this.delayBetweenUrls);
}
}
closeOutputStream();
}
private CrawlerUrl getNextUrl() throws Throwable {
CrawlerUrl nextUrl = null;
while ((nextUrl == null) && (!urlQueue.isEmpty())) {
CrawlerUrl crawlerUrl = this.urlQueue.remove();
//doWeHavePermissionToVisit:是否有权限访问该URL,友好的爬虫会根据网站提供的"Robot.txt"中配置的规则进行爬取
//isUrlAlreadyVisited:URL是否访问过,大型的搜索引擎往往采用BloomFilter进行排重,这里简单使用HashMap
//isDepthAcceptable:是否达到指定的深度上限。爬虫一般采取广度优先的方式。一些网站会构建爬虫陷阱(自动生成一些无效链接使爬虫陷入死循环),采用深度限制加以避免
if (doWeHavePermissionToVisit(crawlerUrl)
&& (!isUrlAlreadyVisited(crawlerUrl))
&& isDepthAcceptable(crawlerUrl)) {
nextUrl = crawlerUrl;
// System.out.println("Next url to be visited is " + nextUrl);
}
}
return nextUrl;
}
private String getContent(CrawlerUrl url) throws Throwable {
//HttpClient4.1的调用与之前的方式不同
HttpClient client = new DefaultHttpClient();
HttpGet httpGet = new HttpGet(url.getUrlString());
StringBuffer strBuf = new StringBuffer();
HttpResponse response = client.execute(httpGet);
if (HttpStatus.SC_OK == response.getStatusLine().getStatusCode()) {
HttpEntity entity = response.getEntity();
if (entity != null) {
BufferedReader reader = new BufferedReader(
new InputStreamReader(entity.getContent(), "UTF-8"));
String line = null;
if (entity.getContentLength() > 0) {
strBuf = new StringBuffer((int) entity.getContentLength());
while ((line = reader.readLine()) != null) {
strBuf.append(line);
}
}
}
if (entity != null) {
nsumeContent();
}
}
//将url标记为已访问
markUrlAsVisited(url);
return strBuf.toString();
}
public static boolean isContentRelevant(String content,
Pattern regexpPattern) {
boolean retValue = false;
if (content != null) {
//是否符合正则表达式的条件
Matcher m = regexpPattern.matcher(content.toLowerCase());
retValue = m.find();
}
return retValue;
}
public List extractUrls(String text, CrawlerUrl crawlerUrl) {
Map urlMap = new HashMap();
extractHttpUrls(urlMap, text);
extractRelativeUrls(urlMap, text, crawlerUrl);
return new ArrayList(urlMap.keySet());
}
private void extractHttpUrls(Map urlMap, String text) {
Matcher m = (text);
while (m.find()) {
String url = m.group();
String[] terms = url.split("a href=\"");
for (String term : terms) {
// System.out.println("Term = " + term);
if (term.startsWith("http")) {
int index = term.indexOf("\"");
if (index > 0) {
term = term.substring(0, index);
}
urlMap.put(term, term);
System.out.println("Hyperlink: " + term);
}
}
}
}
private void extractRelativeUrls(Map urlMap, String text,
CrawlerUrl crawlerUrl) {
Matcher m = relativeRegexp.matcher(text);
URL textURL = crawlerUrl.getURL();
String host = textURL.getHost();
while (m.find()) {
String url = m.group();
String[] terms = url.split("a href=\"");
for (String term : terms) {
if (term.startsWith("/")) {
int index = term.indexOf("\"");
if (index > 0) {
term = term.substring(0, index);
}
String s = //" + host + term;
urlMap.put(s, s);
System.out.println("Relative url: " + s);
}
}
}
}
public static void main(String[] args) {
try {
String url = "";
Queue urlQueue = new LinkedList();
String regexp = "java";
urlQueue.add(new CrawlerUrl(url, 0));
NaiveCrawler crawler = new NaiveCrawler(urlQueue, 100, 5, 1000L,
regexp);
// boolean allowCrawl = crawler.areWeAllowedToVisit(url);
// System.out.println("Allowed to crawl: " + url + " " +
// allowCrawl);
crawler.crawl();
} catch (Throwable t) {
System.out.println(t.toString());
t.printStackTrace();
}
}
传统爬虫从一个或若干初始网页的URL开始,获得初始网页上的URL,在抓取网页的过程中,不断从当前页面上抽取新的URL放入队列,直到满足系统的一定停止条件。对于垂直搜索来说,聚焦爬虫,即有针对性地爬取特定主题网页的爬虫,更为适合。
以下是一个使用java实现的简单爬虫核心代码:
public void crawl() throws Throwable {
while (continueCrawling()) {
CrawlerUrl url = getNextUrl(); //获取待爬取队列中的下一个URL
if (url != null) {
printCrawlInfo();
String content = getContent(url); //获取URL的文本信息
//聚焦爬虫只爬取与主题内容相关的网页,这里采用正则匹配简单处理
if (isContentRelevant(content, this.regexpSearchPattern)) {
saveContent(url, content); //保存网页至本地
//获取网页内容中的链接,并放入待爬取队列中
Collection urlStrings = extractUrls(content, url);
addUrlsToUrlQueue(url, urlStrings);
} else {
System.out.println(url + " is not relevant ignoring ...");
}
//延时防止被对方屏蔽
Thread.sleep(this.delayBetweenUrls);
}
}
closeOutputStream();
}
private CrawlerUrl getNextUrl() throws Throwable {
CrawlerUrl nextUrl = null;
while ((nextUrl == null) && (!urlQueue.isEmpty())) {
CrawlerUrl crawlerUrl = this.urlQueue.remove();
//doWeHavePermissionToVisit:是否有权限访问该URL,友好的爬虫会根据网站提供的"Robot.txt"中配置的规则进行爬取
//isUrlAlreadyVisited:URL是否访问过,大型的搜索引擎往往采用BloomFilter进行排重,这里简单使用HashMap
//isDepthAcceptable:是否达到指定的深度上限。爬虫一般采取广度优先的方式。一些网站会构建爬虫陷阱(自动生成一些无效链接使爬虫陷入死循环),采用深度限制加以避免
if (doWeHavePermissionToVisit(crawlerUrl)
&& (!isUrlAlreadyVisited(crawlerUrl))
&& isDepthAcceptable(crawlerUrl)) {
nextUrl = crawlerUrl;
// System.out.println("Next url to be visited is " + nextUrl);
}
}
return nextUrl;
}
private String getContent(CrawlerUrl url) throws Throwable {
//HttpClient4.1的调用与之前的方式不同
HttpClient client = new DefaultHttpClient();
HttpGet httpGet = new HttpGet(url.getUrlString());
StringBuffer strBuf = new StringBuffer();
HttpResponse response = client.execute(httpGet);
if (HttpStatus.SC_OK == response.getStatusLine().getStatusCode()) {
HttpEntity entity = response.getEntity();
if (entity != null) {
BufferedReader reader = new BufferedReader(
new InputStreamReader(entity.getContent(), "UTF-8"));
String line = null;
if (entity.getContentLength() > 0) {
strBuf = new StringBuffer((int) entity.getContentLength());
while ((line = reader.readLine()) != null) {
strBuf.append(line);
}
}
}
if (entity != null) {
nsumeContent();
}
}
//将url标记为已访问
markUrlAsVisited(url);
return strBuf.toString();
}
public static boolean isContentRelevant(String content,
Pattern regexpPattern) {
boolean retValue = false;
if (content != null) {
//是否符合正则表达式的条件
Matcher m = regexpPattern.matcher(content.toLowerCase());
retValue = m.find();
}
return retValue;
}
public List extractUrls(String text, CrawlerUrl crawlerUrl) {
Map urlMap = new HashMap();
extractHttpUrls(urlMap, text);
extractRelativeUrls(urlMap, text, crawlerUrl);
return new ArrayList(urlMap.keySet());
}
private void extractHttpUrls(Map urlMap, String text) {
Matcher m = (text);
while (m.find()) {
String url = m.group();
String[] terms = url.split("a href=\"");
for (String term : terms) {
// System.out.println("Term = " + term);
if (term.startsWith("http")) {
int index = term.indexOf("\"");
if (index > 0) {
term = term.substring(0, index);
}
urlMap.put(term, term);
System.out.println("Hyperlink: " + term);
}
}
}
}
private void extractRelativeUrls(Map urlMap, String text,
CrawlerUrl crawlerUrl) {
Matcher m = relativeRegexp.matcher(text);
URL textURL = crawlerUrl.getURL();
String host = textURL.getHost();
while (m.find()) {
String url = m.group();
String[] terms = url.split("a href=\"");
for (String term : terms) {
if (term.startsWith("/")) {
int index = term.indexOf("\"");
if (index > 0) {
term = term.substring(0, index);
}
String s = //" + host + term;
urlMap.put(s, s);
System.out.println("Relative url: " + s);
}
}
}
}
public static void main(String[] args) {
try {
String url = "";
Queue urlQueue = new LinkedList();
String regexp = "java";
urlQueue.add(new CrawlerUrl(url, 0));
NaiveCrawler crawler = new NaiveCrawler(urlQueue, 100, 5, 1000L,
regexp);
// boolean allowCrawl = crawler.areWeAllowedToVisit(url);
// System.out.println("Allowed to crawl: " + url + " " +
// allowCrawl);
crawler.crawl();
} catch (Throwable t) {
System.out.println(t.toString());
t.printStackTrace();
}
}
展开全部
代码如下:
package webspider;
import
java.util.HashSet;
import java.util.PriorityQueue;
import
java.util.Set;
import java.util.Queue;
public class LinkQueue {
// 已访问的 url 集合
private static Set visitedUrl
= new HashSet();
// 待访问的 url 集合
private static Queue unVisitedUrl = new
PriorityQueue();
// 获得URL队列
public static Queue getUnVisitedUrl() {
return
unVisitedUrl;
}
// 添加到访问过的URL队列中
public static void addVisitedUrl(String url)
{
visitedUrl.add(url);
}
// 移除访问过的URL
public static void removeVisitedUrl(String url)
{
visitedUrl.remove(url);
}
// 未访问的URL出队列
public static Object unVisitedUrlDeQueue() {
return
unVisitedUrl.poll();
}
// 保证每个 url 只被访问一次
public static void addUnvisitedUrl(String url)
{
if (url != null && !url.trim().equals("") &&
!visitedUrl.contains(url)
&&
!unVisitedUrl.contains(url))
unVisitedUrl.add(url);
}
// 获得已经访问的URL数目
public static int getVisitedUrlNum() {
return
visitedUrl.size();
}
// 判断未访问的URL队列中是否为空
public static boolean unVisitedUrlsEmpty()
{
return unVisitedUrl.isEmpty();
}
}
本回答被提问者和网友采纳
已赞过
已踩过<
评论
收起
你对这个回答的评价是?
展开全部
鉴于网络爬虫的实现的复杂性我的确没有什么发言权,不过可以推荐两本书。
一本是罗刚写的《自己动手写搜索引擎》,另一本是罗刚和王振东合著的《自己动手写网络爬虫》。
另外Apache下有一个开源的搜索引擎项目Nutch,Nutch是一个用java实现的网络爬虫,你如果真的感兴趣可以看一下的源代码。
一本是罗刚写的《自己动手写搜索引擎》,另一本是罗刚和王振东合著的《自己动手写网络爬虫》。
另外Apache下有一个开源的搜索引擎项目Nutch,Nutch是一个用java实现的网络爬虫,你如果真的感兴趣可以看一下的源代码。
已赞过
已踩过<
评论
收起
你对这个回答的评价是?
展开全部
<meta content="all" name="robots" />
已赞过
已踩过<
评论
收起
你对这个回答的评价是?
推荐律师服务:
若未解决您的问题,请您详细描述您的问题,通过百度律临进行免费专业咨询