栏目分类:
子分类:
返回
名师互学网用户登录
快速导航关闭
当前搜索
当前分类
子分类
实用工具
热门搜索
名师互学网 > IT > 软件开发 > 后端开发 > .Net

解决webmagic访问报错javax.net.ssl.SSLException: Received fatal alert: protocol

.Net 更新时间: 发布时间: IT归档 最新发布 模块sitemap 名妆网 法律咨询 聚返吧 英语巴士网 伯小乐 网商动力

解决webmagic访问报错javax.net.ssl.SSLException: Received fatal alert: protocol

拷贝两个类:

package com.example.mindsa.webmagic.sslconfig;

import org.apache.commons.io.IOUtils;
import org.apache.http.HttpResponse;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.util.EntityUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import oshi.annotation.concurrent.ThreadSafe;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Request;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Task;
import us.codecraft.webmagic.downloader.AbstractDownloader;
import us.codecraft.webmagic.downloader.HttpClientRequestContext;
import us.codecraft.webmagic.downloader.HttpUriRequestConverter;
import us.codecraft.webmagic.proxy.Proxy;
import us.codecraft.webmagic.proxy.ProxyProvider;
import us.codecraft.webmagic.selector.PlainText;
import us.codecraft.webmagic.utils.CharsetUtils;
import us.codecraft.webmagic.utils.HttpClientUtils;

import java.io.IOException;
import java.nio.charset.Charset;
import java.util.HashMap;
import java.util.Map;



@ThreadSafe
public class HttpClientDownloader extends AbstractDownloader {

    private Logger logger = LoggerFactory.getLogger(getClass());

    private final Map httpClients = new HashMap();

    private HttpClientGenerator httpClientGenerator = new HttpClientGenerator();

    private HttpUriRequestConverter httpUriRequestConverter = new HttpUriRequestConverter();

    private ProxyProvider proxyProvider;

    private boolean responseHeader = true;

    public void setHttpUriRequestConverter(HttpUriRequestConverter httpUriRequestConverter) {
        this.httpUriRequestConverter = httpUriRequestConverter;
    }

    public void setProxyProvider(ProxyProvider proxyProvider) {
        this.proxyProvider = proxyProvider;
    }

    private CloseableHttpClient getHttpClient(Site site) {
        if (site == null) {
            return httpClientGenerator.getClient(null);
        }
        String domain = site.getDomain();
        CloseableHttpClient httpClient = httpClients.get(domain);
        if (httpClient == null) {
            synchronized (this) {
                httpClient = httpClients.get(domain);
                if (httpClient == null) {
                    httpClient = httpClientGenerator.getClient(site);
                    httpClients.put(domain, httpClient);
                }
            }
        }
        return httpClient;
    }

    @Override
    public Page download(Request request, Task task) {
        if (task == null || task.getSite() == null) {
            throw new NullPointerException("task or site can not be null");
        }
        CloseableHttpResponse httpResponse = null;
        CloseableHttpClient httpClient = getHttpClient(task.getSite());
        Proxy proxy = proxyProvider != null ? proxyProvider.getProxy(task) : null;
        HttpClientRequestContext requestContext = httpUriRequestConverter.convert(request, task.getSite(), proxy);
        Page page = Page.fail();
        try {
            httpResponse = httpClient.execute(requestContext.getHttpUriRequest(), requestContext.getHttpClientContext());
            page = handleResponse(request, request.getCharset() != null ? request.getCharset() : task.getSite().getCharset(), httpResponse, task);
            onSuccess(request);
            logger.info("downloading page success {}", request.getUrl());
            return page;
        } catch (IOException e) {
            logger.warn("download page {} error", request.getUrl(), e);
            onError(request);
            return page;
        } finally {
            if (httpResponse != null) {
                //ensure the connection is released back to pool
                EntityUtils.consumeQuietly(httpResponse.getEntity());
            }
            if (proxyProvider != null && proxy != null) {
                proxyProvider.returnProxy(proxy, page, task);
            }
        }
    }

    @Override
    public void setThread(int thread) {
        httpClientGenerator.setPoolSize(thread);
    }

    protected Page handleResponse(Request request, String charset, HttpResponse httpResponse, Task task) throws IOException {
        byte[] bytes = IOUtils.toByteArray(httpResponse.getEntity().getContent());
        String contentType = httpResponse.getEntity().getContentType() == null ? "" : httpResponse.getEntity().getContentType().getValue();
        Page page = new Page();
        page.setBytes(bytes);
        if (!request.isBinaryContent()){
            if (charset == null) {
                charset = getHtmlCharset(contentType, bytes);
            }
            page.setCharset(charset);
            page.setRawText(new String(bytes, charset));
        }
        page.setUrl(new PlainText(request.getUrl()));
        page.setRequest(request);
        page.setStatusCode(httpResponse.getStatusLine().getStatusCode());
        page.setDownloadSuccess(true);
        if (responseHeader) {
            page.setHeaders(HttpClientUtils.convertHeaders(httpResponse.getAllHeaders()));
        }
        return page;
    }

    private String getHtmlCharset(String contentType, byte[] contentBytes) throws IOException {
        String charset = CharsetUtils.detectCharset(contentType, contentBytes);
        if (charset == null) {
            charset = Charset.defaultCharset().name();
            logger.warn("Charset autodetect failed, use {} as charset. Please specify charset in Site.setCharset()", Charset.defaultCharset());
        }
        return charset;
    }
}
package com.example.mindsa.webmagic.sslconfig;

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 us.codecraft.webmagic.downloader.CustomRedirectStrategy;

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;


public class HttpClientGenerator {

	private transient Logger logger = LoggerFactory.getLogger(getClass());

    private PoolingHttpClientConnectionManager connectionManager;

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

	private SSLConnectionSocketFactory buildSSLConnectionSocketFactory() {
        try {
            return new SSLConnectionSocketFactory(createIgnoreVerifySSL(), new String[]{"SSLv3", "TLSv1", "TLSv1.1", "TLSv1.2"},
                    null,
                    new DefaultHostnameVerifier()); // 优先绕过安全证书
        } 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 cookieEntry : site.getCookies().entrySet()) {
            BasicClientCookie cookie = new BasicClientCookie(cookieEntry.getKey(), cookieEntry.getValue());
            cookie.setDomain(site.getDomain());
            cookieStore.addCookie(cookie);
        }
        for (Map.Entry> domainEntry : site.getAllCookies().entrySet()) {
            for (Map.Entry cookieEntry : domainEntry.getValue().entrySet()) {
                BasicClientCookie cookie = new BasicClientCookie(cookieEntry.getKey(), cookieEntry.getValue());
                cookie.setDomain(domainEntry.getKey());
                cookieStore.addCookie(cookie);
            }
        }
        httpClientBuilder.setDefaultCookieStore(cookieStore);
    }

}

创建爬虫时加上中间件:

.setDownloader(new HttpClientDownloader())

示例:

参考连接:https://www.cnblogs.com/vcmq/p/9484418.html

转载请注明:文章转载自 www.mshxw.com
本文地址:https://www.mshxw.com/it/905488.html
我们一直用心在做
关于我们 文章归档 网站地图 联系我们

版权所有 (c)2021-2022 MSHXW.COM

ICP备案号:晋ICP备2021003244-6号