[WebMagic]Https下无法抓取只支持TLS1.2的站点

我按照官网的步骤,部署好了Maven,复制了他的示例代码,运行直接报错;报错的原因是因为 WebMagic默认的HttpClient只会用TLSv1去请求,对于某些只支持TLS1.2的站点 ,而官网抓取GitHub正好是TLS1.2的站点………

关于这个问题的解决思路,这个框架的作者已经给出了临时解决方案(https://github.com/code4craft/webmagic/issues/701)。

我来说一下具体操作:首先在你的工程目录创建以下的包结构

us.codecraft.webmagic.downloader

在downloader包下面创建一个HttpClientGenerator类,这个类更改之后的代码,我放在本文最后,可以复制粘贴编译使用;之后还记得那个Hello World吗?没错打开CMD,输入下面代码,将他编译成一个.class文件;

javac HttpClientGenerator.java

然后打开你的Maven本地仓库的路径,找到路径为

us\codecraft\webmagic-core\0.7.3 下面的webmagic-core-0.7.3.jar文件,用压缩软件打开,最后直接将你编译后的.class文件替换掉压缩包里\us\codecraft\webmagic\downloader\的HttpClientGenerator.class文件即可

附:HttpClientGenerator.java

package us.codecraft.webmagic.downloader;

import org.apache.http.HttpException;
import org.apache.http.HttpRequest;
import org.apache.http.HttpRequestInterceptor;
import org.apache.http.client.CookieStore;
import org.apache.http.config.Registry;
import org.apache.http.config.RegistryBuilder;
import org.apache.http.config.SocketConfig;
import org.apache.http.conn.socket.ConnectionSocketFactory;
import org.apache.http.conn.socket.PlainConnectionSocketFactory;
import org.apache.http.conn.ssl.DefaultHostnameVerifier;
import org.apache.http.conn.ssl.SSLConnectionSocketFactory;
import org.apache.http.impl.client.*;
import org.apache.http.impl.conn.PoolingHttpClientConnectionManager;
import org.apache.http.impl.cookie.BasicClientCookie;
import org.apache.http.protocol.HttpContext;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import us.codecraft.webmagic.Site;

import javax.net.ssl.SSLContext;
import javax.net.ssl.TrustManager;
import javax.net.ssl.X509TrustManager;
import java.io.IOException;
import java.security.KeyManagementException;
import java.security.NoSuchAlgorithmException;
import java.security.cert.CertificateException;
import java.security.cert.X509Certificate;
import java.util.Map;

/**
 * @author code4crafter@gmail.com <br>
 * @since 0.4.0
 */
public class HttpClientGenerator {
	
	private transient Logger logger = LoggerFactory.getLogger(getClass());
	
    private PoolingHttpClientConnectionManager connectionManager;

    public HttpClientGenerator() {
        Registry<ConnectionSocketFactory> reg = RegistryBuilder.<ConnectionSocketFactory>create()
                .register("http", PlainConnectionSocketFactory.INSTANCE)
                .register("https", buildSSLConnectionSocketFactory())
                .build();
        connectionManager = new PoolingHttpClientConnectionManager(reg);
        connectionManager.setDefaultMaxPerRoute(100);
    }

	private SSLConnectionSocketFactory buildSSLConnectionSocketFactory() {
		try {
			//return new SSLConnectionSocketFactory(createIgnoreVerifySSL()); // 优先绕过安全证书
			return new SSLConnectionSocketFactory(createIgnoreVerifySSL(), new String[]{"SSLv3", "TLSv1", "TLSv1.1", "TLSv1.2"},
                    null,
                    new DefaultHostnameVerifier());
		} catch (KeyManagementException e) {
            logger.error("ssl connection fail", e);
        } catch (NoSuchAlgorithmException e) {
            logger.error("ssl connection fail", e);
        }
		return SSLConnectionSocketFactory.getSocketFactory();
	}

	private SSLContext createIgnoreVerifySSL() throws NoSuchAlgorithmException, KeyManagementException {
		// 实现一个X509TrustManager接口,用于绕过验证,不用修改里面的方法
		X509TrustManager trustManager = new X509TrustManager() {

			@Override
			public void checkClientTrusted(X509Certificate[] chain, String authType) throws CertificateException {
			}

			@Override
			public void checkServerTrusted(X509Certificate[] chain, String authType) throws CertificateException {
			}

			@Override
			public X509Certificate[] getAcceptedIssuers() {
				return null;
			}
			
		};
		
		SSLContext sc = SSLContext.getInstance("SSLv3");
		sc.init(null, new TrustManager[] { trustManager }, null);
		return sc;
	}
    
    public HttpClientGenerator setPoolSize(int poolSize) {
        connectionManager.setMaxTotal(poolSize);
        return this;
    }

    public CloseableHttpClient getClient(Site site) {
        return generateClient(site);
    }

    private CloseableHttpClient generateClient(Site site) {
        HttpClientBuilder httpClientBuilder = HttpClients.custom();
        
        httpClientBuilder.setConnectionManager(connectionManager);
        if (site.getUserAgent() != null) {
            httpClientBuilder.setUserAgent(site.getUserAgent());
        } else {
            httpClientBuilder.setUserAgent("");
        }
        if (site.isUseGzip()) {
            httpClientBuilder.addInterceptorFirst(new HttpRequestInterceptor() {

                public void process(
                        final HttpRequest request,
                        final HttpContext context) throws HttpException, IOException {
                    if (!request.containsHeader("Accept-Encoding")) {
                        request.addHeader("Accept-Encoding", "gzip");
                    }
                }
            });
        }
        //解决post/redirect/post 302跳转问题
        httpClientBuilder.setRedirectStrategy(new CustomRedirectStrategy());

        SocketConfig.Builder socketConfigBuilder = SocketConfig.custom();
        socketConfigBuilder.setSoKeepAlive(true).setTcpNoDelay(true);
        socketConfigBuilder.setSoTimeout(site.getTimeOut());
        SocketConfig socketConfig = socketConfigBuilder.build();
        httpClientBuilder.setDefaultSocketConfig(socketConfig);
        connectionManager.setDefaultSocketConfig(socketConfig);
        httpClientBuilder.setRetryHandler(new DefaultHttpRequestRetryHandler(site.getRetryTimes(), true));
        generateCookie(httpClientBuilder, site);
        return httpClientBuilder.build();
    }

    private void generateCookie(HttpClientBuilder httpClientBuilder, Site site) {
        if (site.isDisableCookieManagement()) {
            httpClientBuilder.disableCookieManagement();
            return;
        }
        CookieStore cookieStore = new BasicCookieStore();
        for (Map.Entry<String, String> cookieEntry : site.getCookies().entrySet()) {
            BasicClientCookie cookie = new BasicClientCookie(cookieEntry.getKey(), cookieEntry.getValue());
            cookie.setDomain(site.getDomain());
            cookieStore.addCookie(cookie);
        }
        for (Map.Entry<String, Map<String, String>> domainEntry : site.getAllCookies().entrySet()) {
            for (Map.Entry<String, String> cookieEntry : domainEntry.getValue().entrySet()) {
                BasicClientCookie cookie = new BasicClientCookie(cookieEntry.getKey(), cookieEntry.getValue());
                cookie.setDomain(domainEntry.getKey());
                cookieStore.addCookie(cookie);
            }
        }
        httpClientBuilder.setDefaultCookieStore(cookieStore);
    }

}

 

  • 3
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 4
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 4
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值