网络爬虫(Web crawler),是一种按照一定的规则,自动地抓取万维网信息的程序或者脚本
环境准备
JDK1.8
IntelliJ IDEA
IDEA自带的Maven
创建Maven工程给pom.xml加入依赖
<dependencies>
<dependency>
<groupId>org.apache.httpcomponentsgroupId>
<artifactId>httpclientartifactId>
<version>4.5.3version>
dependency>
<dependency>
<groupId>org.slf4jgroupId>
<artifactId>slf4j-log4j12artifactId>
<version>1.7.25version>
dependency>
dependencies>
加入log4j.properties
log4j.rootLogger=DEBUG,A1
log4j.logger.cn.itcast = DEBUG
log4j.appender.A1=org.apache.log4j.ConsoleAppender
log4j.appender.A1.layout=org.apache.log4j.PatternLayout
log4j.appender.A1.layout.ConversionPattern=%-d{yyyy-MM-dd HH:mm:ss,SSS} [%t] [%c]-[%p] %m%n
编写最简单的爬虫,抓取传智播客首页:http://www.itcast.cn/
package cn.itcast.carwler.test;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
public class CarwlerFirst {
public static void main(String[] args) throws Exception {
//1.打开浏览器,创建HttpClient对象
CloseableHttpClient httpClient = HttpClients.createDefault();
//2.输入网址,发起get请求创建HttpGet对象
HttpGet httpGet = new HttpGet("http://www.itcast.cn/");
//3.回车,发起请求,返回响应,使用HttpClient对象发起请求
CloseableHttpResponse response = httpClient.execute(httpGet);
//4.解析响应,获取数据、
//判断状态码是否为200
if (response.getStatusLine().getStatusCode() == 200) {
String content = EntityUtils.toString(response.getEntity(), "UTF-8");
System.out.println(content);
}
}
}
HttpClient
网络爬虫就是用程序帮助我们访问网络上的资源,我们一直以来都是使用HTTP协议访问互联网的网页,网络爬虫需要编写程序,在这里使用同样的HTTP协议访问网页。
这里我们使用Java的HTTP协议客户端 HttpClient这个技术,来实现抓取网页数据。
GET请求
访问传智官网,请求url地址:http://www.itcast.cn/
package cn.itcast.carwler.test;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import sun.net.www.http.HttpClient;
import javax.xml.ws.Response;
import java.io.IOException;
public class HttpGetTest {
public static void main(String[] args) {
//创建HttpClient对象
CloseableHttpClient httpClient = HttpClients.createDefault();
//创建HttpGet对象,设置url访问地址
HttpGet httpGet = new HttpGet("http://www.itcast.cn/");
System.out.println("发起的请求信息:"+httpGet);
CloseableHttpResponse response=null;
try {
//使用HttpClient发起请求,获取response
response = httpClient.execute(httpGet);
//解析响应
if(response.getStatusLine().getStatusCode()==200){
String content = EntityUtils.toString(response.getEntity());
System.out.println(content.length());
}
}catch (IOException e){
e.printStackTrace();
}finally {
//关闭response
try {
response.close();
} catch (IOException e) {
e.printStackTrace();
}
try {
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
带参数的GET请求
在传智中搜索学习视频,地址为: http://yun.itheima.com/search?keys=Java
package cn.itcast.carwler.test;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.utils.URIBuilder;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import java.io.IOException;
import java.net.URISyntaxException;
public class HttpGetParamTest {
public static void main(String[] args) throws Exception {
//创建HttpClient对象
CloseableHttpClient httpClient = HttpClients.createDefault();
//设置请求地址:http://yun.itheima.com/search?keys=Java
//创建URIBuilder
URIBuilder uriBuilder = new URIBuilder("http://yun.itheima.com/search");
//设置参数
uriBuilder.setParameter("keys","Java");
//多个参数
//uriBuilder.setParameter("keys","Java").setParameters();
//创建HttpGet对象,设置url访问地址
HttpGet httpGet = new HttpGet(uriBuilder.build());
System.out.println("发起的请求信息"+httpGet);
CloseableHttpResponse response=null;
try {
//使用HttpClient发起请求,获取response
response = httpClient.execute(httpGet);
//解析响应
if(response.getStatusLine().getStatusCode()==200){
String content = EntityUtils.toString(response.getEntity());
System.out.println(content);
System.out.println(content.length());
}
}catch (IOException e){
e.printStackTrace();
}finally {
//关闭response
try {
response.close();
} catch (IOException e) {
e.printStackTrace();
}
try {
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
POST请求
使用POST访问传智官网,请求url地址:http://www.itcast.cn/
package cn.itcast.carwler.test;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import java.io.IOException;
public class HttpPostTest {
public static void main(String[] args) {
//创建HttpClient对象
CloseableHttpClient httpClient = HttpClients.createDefault();
//创建HttpGet对象,设置url访问地址
HttpPost httpPost = new HttpPost("http://www.itcast.cn/");
System.out.println("发起的请求信息:"+httpPost);
CloseableHttpResponse response=null;
try {
//使用HttpClient发起请求,获取response
response = httpClient.execute(httpPost);
//解析响应
if(response.getStatusLine().getStatusCode()==200){
String content = EntityUtils.toString(response.getEntity());
System.out.println(content.length());
}
}catch (IOException e){
e.printStackTrace();
}finally {
//关闭response
try {
response.close();
} catch (IOException e) {
e.printStackTrace();
}
try {
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
带参数的POST请求
在传智中搜索学习视频,使用POST请求,url地址为:
http://yun.itheima.com/search
url地址没有参数,参数keys=java放到表单中进行提交
package cn.itcast.carwler.test;
import org.apache.http.NameValuePair;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.util.EntityUtils;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.util.ArrayList;
public class HttpPostParamTest {
public static void main(String[] args) throws UnsupportedEncodingException {
//创建HttpClient对象
CloseableHttpClient httpClient = HttpClients.createDefault();
//创建HttpGet对象,设置url访问地址
HttpPost httpPost = new HttpPost("http://www.itcast.cn/");
System.out.println("发起的请求信息:"+httpPost);
//声明List集合,封装表单中的参数
ArrayList<NameValuePair> params = new ArrayList<NameValuePair>();
params.add(new BasicNameValuePair("keys","java"));
//创建表单的Entity对象
UrlEncodedFormEntity formEntity = new UrlEncodedFormEntity(params, "UTF-8");
//设置表单的Entity对象到Post请求中
httpPost.setEntity(formEntity);
CloseableHttpResponse response=null;
try {
//使用HttpClient发起请求,获取response
response = httpClient.execute(httpPost);
//解析响应
if(response.getStatusLine().getStatusCode()==200){
String content = EntityUtils.toString(response.getEntity());
System.out.println(content.length());
}
}catch (IOException e){
e.printStackTrace();
}finally {
//关闭response
try {
response.close();
} catch (IOException e) {
e.printStackTrace();
}
try {
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
连接池
如果每次请求都要创建HttpClient,会有频繁创建和销毁的问题,可以使用连接池来解决这个问题。
测试以下代码,并断点查看每次获取的HttpClient都是不一样的。
package cn.itcast.carwler.test;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;
import org.apache.http.util.EntityUtils;
import java.io.IOException;
public class HttpClientPoolTest {
public static void main(String[] args) {
// 创建连接池管理器
PoolingHttpClientConnectionManager cm = new PoolingHttpClientConnectionManager();
// 设置最大连接数
cm.setMaxTotal(200);
// 设置每个主机的并发数
cm.setDefaultMaxPerRoute(20);
// 使用连接池管理器发起请求
doGet(cm);
doGet(cm);
}
private static void doGet(PoolingHttpClientConnectionManager cm) {
CloseableHttpClient httpClient = HttpClients.custom().setConnectionManager(cm).build();
HttpGet httpGet = new HttpGet("http://www.itcast.cn/");
CloseableHttpResponse response = null;
try {
response = httpClient.execute(httpGet);
// 判断状态码是否是200
if (response.getStatusLine().getStatusCode() == 200) {
// 解析数据
String content = EntityUtils.toString(response.getEntity(), "UTF-8");
System.out.println(content.length());
}
} catch (Exception e) {
e.printStackTrace();
} finally {
//释放连接
if (response == null) {
try {
response.close();
} catch (IOException e) {
e.printStackTrace();
}
//不能关闭HttpClient
//httpClient.close();
}
}
}
}
请求参数
有时候因为网络,或者目标服务器的原因,请求需要更长的时间才能完成,我们需要自定义相关时间
package cn.itcast.carwler.test;
import org.apache.http.client.config.RequestConfig;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;
import java.io.IOException;
public class HttpConfigTest {
public static void main(String[] args) {
//创建HttpClient对象
CloseableHttpClient httpClient = HttpClients.createDefault();
//创建HttpGet对象,设置url访问地址
HttpGet httpGet = new HttpGet("http://www.itcast.cn/");
System.out.println("发起的请求信息:"+httpGet);
//配置请求信息
RequestConfig requestConfig = RequestConfig.custom()
.setConnectTimeout(1000)//设置创建连接的最长时间,单位是毫秒
.setConnectionRequestTimeout(500)//设置获取连接的最长时间
.setSocketTimeout(10 * 1000)//设置数据传输的最长时间
.build();
httpGet.setConfig(requestConfig);
CloseableHttpResponse response=null;
try {
//使用HttpClient发起请求,获取response
response = httpClient.execute(httpGet);
//解析响应
if(response.getStatusLine().getStatusCode()==200){
String content = EntityUtils.toString(response.getEntity());
System.out.println(content.length());
}
}catch (IOException e){
e.printStackTrace();
}finally {
//关闭response
try {
response.close();
} catch (IOException e) {
e.printStackTrace();
}
try {
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
我们抓取到页面之后,还需要对页面进行解析。可以使用字符串处理工具解析页面,也可以使用正则表达式,但是这些方法都会带来很大的开发成本,所以我们需要使用一款专门解析html页面的技术。
jsoup介绍
jsoup 是一款Java 的HTML解析器,可直接解析某个URL地址、HTML文本内容。它提供了一套非常省力的API,可通过DOM,CSS以及类似于jQuery的操作方法来取出和操作数据。
jsoup的主要功能如下:
- 从一个URL,文件或字符串中解析HTML;
- 使用DOM或CSS选择器来查找、取出数据;
- 可操作HTML元素、属性、文本;
先加入Jsoup依赖:
<dependency>
<groupId>org.jsoupgroupId>
<artifactId>jsoupartifactId>
<version>1.10.3version>
dependency>
<dependency>
<groupId>junitgroupId>
<artifactId>junitartifactId>
<version>4.12version>
dependency>
<dependency>
<groupId>org.apache.commonsgroupId>
<artifactId>commons-lang3artifactId>
<version>3.7version>
dependency>
<dependency>
<groupId>commons-iogroupId>
<artifactId>commons-ioartifactId>
<version>2.6version>
dependency>
/**
* 解析url
* @throws Exception
*/
@Test
public void testJsoupUrl() throws Exception {
//解析url地址,第一个参数是访问的url,第二个参数是访问时候的超时时间
Document document = Jsoup.parse(new URL("http://www.itcast.cn/"), 1000);
//使用标签选择器,获取title标签中的内容
String title = document.getElementsByTag("title").first().text();
System.out.println(title);
}
PS:虽然使用Jsoup可以替代HttpClient直接发起请求解析数据,但是往往不会这样用,因为实际的开发过程中,需要使用到多线程,连接池,代理等等方式,而jsoup对这些的支持并不是很好,所以我们一般把jsoup仅仅作为Html解析工具使用
/**
* 解析字符串
* @throws Exception
*/
@Test
public void testJsoupString() throws Exception {
//读取文件获取
String html = FileUtils.readFileToString(new File("D:\\jsoup.html"), "UTF-8");
//解析字符串
Document document = Jsoup.parse(html);
//获取title的内容
Element title = document.getElementsByTag("title").first();
System.out.println(title.text());
}
/**
* 解析文件
* @throws Exception
*/
@Test
public void testJsoupHtml() throws Exception {
//解析文件
Document document = Jsoup.parse(new File("D:\\jsoup.html"), "UTF-8");
//获取title的内容
Element title = document.getElementsByTag("title").first();
System.out.println(title.text());
}
使用dom方式遍历文档
7.1 元素获取
/**
* 使用dom方式遍历文档
* 元素获取
* @throws Exception
*/
@Test
public void testDom() throws Exception {
//解析文件,获取Document对象
Document document = Jsoup.parse(new File("D:\\jsoup.html"), "utf-8");
//1.根据id查询元素getElementById
Element element = document.getElementById("city_bj");
//2.根据标签获取元素getElementsByTag
Element element1 = document.getElementsByTag("span").first();
//3.根据class获取元素getElementsByClass
Element element2 = document.getElementsByClass("class_a class_b").first();
Element element3 = document.getElementsByClass("class_b").first();
//4.根据属性获取元素getElementsByAttribute
Element element4 = document.getElementsByAttribute("abc").first();
Element element5 = document.getElementsByAttributeValue("href", "http://www.itcast.cn").first();
//打印元素的内容
System.out.println("获取到的元素内容是:" + element.text());
System.out.println("获取到的元素内容是:" + element1.text());
System.out.println("获取到的元素内容是:" + element2.text());
System.out.println("获取到的元素内容是:" + element3.text());
System.out.println("获取到的元素内容是:" + element4.text());
System.out.println("获取到的元素内容是:" + element5.text());
}
7.2 元素中获取数据
/**
* 使用dom方式遍历文档
* 从元素中获取数据
* @throws Exception
*/
@Test
public void testData() throws Exception {
//解析文件,获取Document对象
Document document = Jsoup.parse(new File("D:\\jsoup.html"), "utf-8");
//根据id查询元素getElementById
Element element = document.getElementById("test");
//1.从元素中获取id
String s = element.id();
//2.从元素中获取className
String s1 = element.className();
//3.从元素中获取属性的值attr
String s2 = element.attr("id");
//4.从元素中获取所有属性attributes
String s3 = element.attributes().toString();
//5.从元素中获取文本内容text
String s4 = element.text();
//打印获取到的内容
System.out.println("获取到的数据是:" + s);
System.out.println("获取到的数据是:" + s1);
System.out.println("获取到的数据是:" + s2);
System.out.println("获取到的数据是:" + s3);
System.out.println("获取到的数据是:" + s4);
}
使用选择器语法查找元素
jsoup elements对象支持类似于CSS (或jquery)的选择器语法,来实现非常强大和灵活的查找功能。这个select 方法在Document, Element,或Elements对象中都可以使用。且是上下文相关的,因此可实现指定元素的过滤,或者链式选择访问。
Select方法将返回一个Elements集合,并提供一组方法来抽取和处理结果。
8.1 Selector选择器概述
tagname: 通过标签查找元素,比如:span #id: 通过ID查找元素,比如:# city_bj .class:
通过class名称查找元素,比如:.class_a [attribute]: 利用属性查找元素,比如:[abc]
[attr=value]: 利用属性值来查找元素,比如:[class=s_name]
/**
* Selector选择器概述
* @throws Exception
*/
@Test
public void testSelector() throws Exception{
//解析文件,获取Document对象
Document document = Jsoup.parse(new File("D:\\jsoup.html"), "utf-8");
//tagname: 通过标签查找元素,比如:span
Elements elements = document.select("span");
for (Element element : elements) {
System.out.println(element.text());
}
//#id: 通过ID查找元素,比如:# city_bj
String text = document.select("#city_bj").text();
System.out.println(text);
//.class: 通过class名称查找元素,比如:.class_a
String text1 = document.select(".class_a").text();
System.out.println(text1);
//[attribute]: 利用属性查找元素,比如:[abc]
String text2 = document.select("[abc]").text();
System.out.println(text2);
//[attr=value]: 利用属性值来查找元素,比如:[class=s_name]
Elements elements2 = document.select("[class=s_name]");
for (Element element : elements2) {
System.out.println(element.text());
}
}
8.2 Selector选择器组合使用
el#id: 元素+ID,比如: h3#city_bj el.class: 元素+class,比如: li.class_a
el[attr]: 元素+属性名,比如: span[abc] 任意组合: 比如:span[abc].s_name ancestor
child: 查找某个元素下子元素,比如:.city_con li 查找"city_con"下的所有li parent > child:
查找某个父元素下的直接子元素,比如: .city_con > ul > li
查找city_con第一级(直接子元素)的ul,再找所有ul下的第一级li parent > *: 查找某个父元素下所有直接子元素
/**
* Selector选择器组合使用
* @throws Exception
*/
@Test
public void testSelect2() throws Exception {
//解析文件,获取Document对象
Document document = Jsoup.parse(new File("D:\\jsoup.html"), "utf-8");
//el#id: 元素+ID,比如: h3#city_bj
String text = document.select("h3#city_bj").text();
//el.class: 元素+class,比如: li.class_a
String text1 = document.select("li.class_a").text();
//el[attr]: 元素+属性名,比如: span[abc]
String text2 = document.select("span[abc]").text();
//任意组合: 比如:span[abc].s_name
String text3 = document.select("span[abc].s_name").text();
//ancestor child: 查找某个元素下子元素,比如:.city_con li 查找"city_con"下的所有li
String text4 = document.select(".city_con li").text();
//parent > child: 查找某个父元素下的直接子元素,比如:
//.city_con > ul > li 查找city_con第一级(直接子元素)的ul,再找所有ul下的第一级li
String text5 = document.select(".city_con > ul > li").text();
//parent > *: 查找某个父元素下所有直接子元素
String text6 = document.select(".city_con > *").text();
//打印获取到的内容
System.out.println("获取到的数据是:" + text);
System.out.println("获取到的数据是:" + text1);
System.out.println("获取到的数据是:" + text2);
System.out.println("获取到的数据是:" + text3);
System.out.println("获取到的数据是:" + text4);
System.out.println("获取到的数据是:" + text5);
System.out.println("获取到的数据是:" + text6);
}