JAVA爬虫学习笔记
环境准备
JDK1.8
IntelliJ IDEA
IDEA自带的Maven
一.导入pom.xml
<dependencies>
<!-- https://mvnrepository.com/artifact/org.apache.httpcomponents/httpclient -->
<!-- HttpClient -->
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.12</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.slf4j/slf4j-log4j12 -->
<!--日志-->
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>1.7.25</version>
<scope>test</scope>
</dependency>
</dependencies>
二、创建slf4j日志配置文件
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
三、第一个爬虫
import org.apache.http.HttpEntity;
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;
import java.sql.SQLOutput;
//爬虫:采集,处理,存储
public class CrawlerFirst {
public static void main(String[] args) throws IOException {
//1.打开浏览器,创建HttpClient对象
CloseableHttpClient httpClient= HttpClients.createDefault();
//2.输入网址
HttpGet httpGet=new HttpGet("http://www.itcast.cn");
//3.按回车,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
//1.判断状态码:200
if(response.getStatusLine().getStatusCode()==200){
HttpEntity httpEntity=response.getEntity();
String content= EntityUtils.toString(httpEntity,"utf8");
System.out.println(content);
}
}
}
四、HttpClient (用来抓取网页数据)
GET请求
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 HttpGetTest {
public static void main(String[] args) {
//1.创建HttpClient对象
CloseableHttpClient httpClient= HttpClients.createDefault();
//2.创建HttpGet对象,设置url访问地址
HttpGet httpGet=new HttpGet("http://www.itcast.cn");
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(),"utf8");
System.out.println(content.length());
}
} catch (IOException e) {
e.printStackTrace();
}finally {
try{
response.close();
}catch (IOException e){
e.printStackTrace();
}
try{
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
GET请求带参数
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.client.utils.URIBuilder;
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.util.ArrayList;
import java.util.List;
public class HttpPostParmTest {
public static void main(String[] args) throws Exception {
//1.创建HttpClient对象
CloseableHttpClient httpClient= HttpClients.createDefault();
//2.创建HttpPost对象,设置url访问地址
HttpPost httpPost=new HttpPost("http://yun.itheima.com/search");
//声明list集合,封装表单中的参数
List<NameValuePair> params=new ArrayList<NameValuePair>();
params.add(new BasicNameValuePair("keys","Java"));
//设置请求地址:http://yun.iteima.com/search?keys=Java
//创建表单的Entity对象
UrlEncodedFormEntity formEntity=new UrlEncodedFormEntity(params,"utf8");
//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(),"utf8");
System.out.println(content.length());
}
} catch (IOException e) {
e.printStackTrace();
}finally {
try{
response.close();
}catch (IOException e){
e.printStackTrace();
}
try{
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
POST请求
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) {
//1.创建HttpClient对象
CloseableHttpClient httpClient= HttpClients.createDefault();
//2.创建HttpPost对象,设置url访问地址
HttpPost httppost=new HttpPost("http://www.itcast.cn");
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(),"utf8");
System.out.println(content.length());
}
} catch (IOException e) {
e.printStackTrace();
}finally {
try{
response.close();
}catch (IOException e){
e.printStackTrace();
}
try{
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
POST请求带参数
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.client.utils.URIBuilder;
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.util.ArrayList;
import java.util.List;
public class HttpPostParmTest {
public static void main(String[] args) throws Exception {
//1.创建HttpClient对象
CloseableHttpClient httpClient= HttpClients.createDefault();
//2.创建HttpPost对象,设置url访问地址
HttpPost httpPost=new HttpPost("http://yun.itheima.com/search");
//声明list集合,封装表单中的参数
List<NameValuePair> params=new ArrayList<NameValuePair>();
params.add(new BasicNameValuePair("keys","Java"));
//设置请求地址:http://yun.iteima.com/search?keys=Java
//创建表单的Entity对象
UrlEncodedFormEntity formEntity=new UrlEncodedFormEntity(params,"utf8");
//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(),"utf8");
System.out.println(content.length());
}
} catch (IOException e) {
e.printStackTrace();
}finally {
try{
response.close();
}catch (IOException e){
e.printStackTrace();
}
try{
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
连接池
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) {
//1.创建HttpClient对象
CloseableHttpClient httpClient= HttpClients.createDefault();
//2.创建HttpGet对象,设置url访问地址
HttpGet httpGet=new HttpGet("http://www.itcast.cn");
//配置请求信息
RequestConfig config=RequestConfig.custom().setConnectTimeout(1000)//连接最长时间,单位为毫秒
.setConnectionRequestTimeout(500)//设置获取连接最长时间
.setSocketTimeout(10*1000) //设置数据传输的最长时间
.build();
//给请求设置请求信息
httpGet.setConfig(config);
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(),"utf8");
System.out.println(content.length());
}
} catch (IOException e) {
e.printStackTrace();
}finally {
try{
response.close();
}catch (IOException e){
e.printStackTrace();
}
try{
httpClient.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
视频来源:https://www.bilibili.com/video/BV1cE411u7RA?p=44&spm_id_from=pageDriver