爬虫

爬虫简介

爬虫：

网络爬虫机器人，以互联网自由抓取数据的程序

爬虫的作用:

• 搜索引擎
• 商品比价
• 知乎的数据分析平台 

如何写一个爬虫？

网页的三大特征：

• 每一个网页都有一个唯一的url（统一资源定位符）来进行定位
• 网页都是通过HTML<超文本>文本展示的
• 所有的网页都是通过HTTP<超文本传输协议>（HTTPS）协议来传输的

爬虫的流程：

1.分析网站，得到新的url
+2. 根据url，发起请求，获取页面的HTML源码

3.从页面中提取数据
a.提取到目标数据，做数据的筛选和持久化储存
b.从页面中提取到新的url地址，继续执行第二操作

4.爬虫结束：所有的目标url都提取完毕，并且得到了数据，再也没有其他请求任务，意味着爬虫结束

pom依赖

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.javaxl</groupId>
    <artifactId>T226_jsoup</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <packaging>jar</packaging>

    <name>T226_jsoup</name>
    <url>http://maven.apache.org</url>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>

    <dependencies>
        <!-- jdbc驱动包 -->
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.44</version>
        </dependency>

        <!-- 添加Httpclient支持 -->
        <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpclient</artifactId>
            <version>4.5.2</version>
        </dependency>

        <!-- 添加jsoup支持 -->
        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.10.1</version>
        </dependency>


        <!-- 添加日志支持 -->
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.16</version>
        </dependency>

        <!-- 添加ehcache支持 -->
        <dependency>
            <groupId>net.sf.ehcache</groupId>
            <artifactId>ehcache</artifactId>
            <version>2.10.3</version>
        </dependency>

        <!-- 添加commons io支持 -->
        <dependency>
            <groupId>commons-io</groupId>
            <artifactId>commons-io</artifactId>
            <version>2.5</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.47</version>
        </dependency>
    </dependencies>
</project>

我们来爬一个图片

DownloadImg .java

package com.javaxl.crawler;

import java.io.File;
import java.io.IOException;
import java.util.UUID;

import org.apache.commons.io.FileUtils;
import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
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.log4j.Logger;

import com.javaxl.util.DateUtil;
import com.javaxl.util.PropertiesUtil;

public class DownloadImg {
    private static Logger logger = Logger.getLogger(DownloadImg.class);
    private static String URL = "https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1570570095818&di=f6f36a34fb29850cce69942cce9e8259&imgtype=0&src=http%3A%2F%2Fpic1.win4000.com%2Fpic%2F6%2F56%2F85ea1629713.jpg";
    public static void main(String[] args) {
        logger.info("开始爬取首页：" + URL);
        CloseableHttpClient httpClient = HttpClients.createDefault();
        HttpGet httpGet = new HttpGet(URL);
        RequestConfig config = RequestConfig.custom().setConnectTimeout(5000).setSocketTimeout(8000).build();
        httpGet.setConfig(config);
        CloseableHttpResponse response = null;
        try {
            response = httpClient.execute(httpGet);
            if (response == null) {
                logger.info("连接超时！！！");
            } else {
                HttpEntity entity = response.getEntity();
                String imgPath = PropertiesUtil.getValue("blogImages");
                String dateDir = DateUtil.getCurrentDatePath();
                String uuid = UUID.randomUUID().toString();
                String subfix = entity.getContentType().getValue().split("/")[1];
                String localFile = imgPath+dateDir+"/"+uuid+"."+subfix;
//                System.out.println(localFile);
                FileUtils.copyInputStreamToFile(entity.getContent(), new File(localFile));
            }
        } catch (ClientProtocolException e) {
            logger.error(URL+"-ClientProtocolException", e);
        } catch (IOException e) {
            logger.error(URL+"-IOException", e);
        } catch (Exception e) {
            logger.error(URL+"-Exception", e);
        } finally {
            try {
                if (response != null) {
                    response.close();
                }
                if(httpClient != null) {
                    httpClient.close();
                }
            } catch (IOException e) {
                logger.error(URL+"-IOException", e);
            }
        }
        

        logger.info("结束首页爬取：" + URL);
    
    }
}

爬博客园的首页

BlogCrawlerStarter.java

package com.javaxl.crawler;

import java.io.File;
import java.io.IOException;
import java.sql.Connection;
import java.sql.PreparedStatement;
import java.sql.SQLException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.UUID;

import org.apache.commons.io.FileUtils;
import org.apache.http.HttpEntity;
import org.apache.http.client.ClientProtocolException;
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 org.apache.log4j.Logger;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import com.javaxl.util.DateUtil;
import com.javaxl.util.DbUtil;
import com.javaxl.util.PropertiesUtil;

import net.sf.ehcache.Cache;
import net.sf.ehcache.CacheManager;
import net.sf.ehcache.Status;

/**
 * @author Administrator
 *
 */
public class BlogCrawlerStarter {

    private static Logger logger = Logger.getLogger(BlogCrawlerStarter.class);
//    https://www.csdn.net/nav/newarticles
    private static String HOMEURL = "https://www.cnblogs.com/";
    private static CloseableHttpClient httpClient;
    private static Connection con;
    private static CacheManager cacheManager;
    private static Cache cache;

    /**
     * httpclient解析首页，获取首页内容
     */
    public static void parseHomePage() {
        logger.info("开始爬取首页：" + HOMEURL);
        
        cacheManager = CacheManager.create(PropertiesUtil.getValue("ehcacheXmlPath"));
        cache = cacheManager.getCache("cnblog");
        
        httpClient = HttpClients.createDefault();
        HttpGet httpGet = new HttpGet(HOMEURL);
        RequestConfig config = RequestConfig.custom().setConnectTimeout(5000).setSocketTimeout(8000).build();
        httpGet.setConfig(config);
        CloseableHttpResponse response = null;
        try {
            response = httpClient.execute(httpGet);
            if (response == null) {
                logger.info(HOMEURL + ":爬取无响应");
                return;
            }

            if (response.getStatusLine().getStatusCode() == 200) {
                HttpEntity entity = response.getEntity();
                String homePageContent = EntityUtils.toString(entity, "utf-8");
                // System.out.println(homePageContent);
                parseHomePageContent(homePageContent);
            }

        } catch (ClientProtocolException e) {
            logger.error(HOMEURL + "-ClientProtocolException", e);
        } catch (IOException e) {
            logger.error(HOMEURL + "-IOException", e);
        } finally {
            try {
                if (response != null) {
                    response.close();
                }

                if (httpClient != null) {
                    httpClient.close();
                }
            } catch (IOException e) {
                logger.error(HOMEURL + "-IOException", e);
            }
        }

        if(cache.getStatus() ==  Status.STATUS_ALIVE) {
            cache.flush();
        }
        cacheManager.shutdown();
        logger.info("结束爬取首页：" + HOMEURL);

    }

    /**
     * 通过网络爬虫框架jsoup，解析网页类容，获取想要数据（博客的连接）
     * 
     * @param homePageContent
     */
    private static void parseHomePageContent(String homePageContent) {
        Document doc = Jsoup.parse(homePageContent);
        //#feedlist_id .list_con .title h2 a
        Elements aEles = doc.select("#post_list .post_item .post_item_body h3 a");
        for (Element aEle : aEles) {
//            这个是首页中的博客列表中的单个链接URL
            String blogUrl = aEle.attr("href");
            if (null == blogUrl || "".equals(blogUrl)) {
                logger.info("该博客未内容，不再爬取插入数据库！");
                continue;
            }
            if(cache.get(blogUrl) != null) {
                logger.info("该数据已经被爬取到数据库中，数据库不再收录！");
                continue;
            }
//            System.out.println("************************"+blogUrl+"****************************");
            
            parseBlogUrl(blogUrl);
        }
    }

    /**
     * 通过博客地址获取博客的标题，以及博客的类容
     * 
     * @param blogUrl
     */
    private static void parseBlogUrl(String blogUrl) {

        logger.info("开始爬取博客网页：" + blogUrl);
        httpClient = HttpClients.createDefault();
        HttpGet httpGet = new HttpGet(blogUrl);
        RequestConfig config = RequestConfig.custom().setConnectTimeout(5000).setSocketTimeout(8000).build();
        httpGet.setConfig(config);
        CloseableHttpResponse response = null;
        try {
            response = httpClient.execute(httpGet);
            if (response == null) {
                logger.info(blogUrl + ":爬取无响应");
                return;
            }

            if (response.getStatusLine().getStatusCode() == 200) {
                HttpEntity entity = response.getEntity();
                String blogContent = EntityUtils.toString(entity, "utf-8");
                parseBlogContent(blogContent, blogUrl);
            }

        } catch (ClientProtocolException e) {
            logger.error(blogUrl + "-ClientProtocolException", e);
        } catch (IOException e) {
            logger.error(blogUrl + "-IOException", e);
        } finally {
            try {
                if (response != null) {
                    response.close();
                }
            } catch (IOException e) {
                logger.error(blogUrl + "-IOException", e);
            }
        }

        logger.info("结束爬取博客网页：" + HOMEURL);

    }

    /**
     * 解析博客类容，获取博客中标题以及所有内容
     * 
     * @param blogContent
     */
    private static void parseBlogContent(String blogContent, String link) {
        Document doc = Jsoup.parse(blogContent);
        if(!link.contains("ansion2014")) {
            System.out.println(blogContent);
        }
        Elements titleEles = doc
                //#mainBox main .blog-content-box .article-header-box .article-header .article-title-box h1
                .select("#topics .post h1 a");
        System.out.println("123");
        System.out.println(titleEles.toString());
        System.out.println("123");
        if (titleEles.size() == 0) {
            logger.info("博客标题为空，不插入数据库！");
            return;
        }
        String title = titleEles.get(0).html();

        Elements blogContentEles = doc.select("#cnblogs_post_body ");
        if (blogContentEles.size() == 0) {
            logger.info("博客内容为空，不插入数据库！");
            return;
        }
        String blogContentBody = blogContentEles.get(0).html();
        
//        Elements imgEles = doc.select("img");
//        List<String> imgUrlList = new LinkedList<String>();
//        if(imgEles.size() > 0) {
//            for (Element imgEle : imgEles) {
//                imgUrlList.add(imgEle.attr("src"));
//            }
//        }
//        
//        if(imgUrlList.size() > 0) {
//            Map<String, String> replaceUrlMap = downloadImgList(imgUrlList);
//            blogContent = replaceContent(blogContent,replaceUrlMap);
//        }

        String sql = "insert into `t_jsoup_article` values(null,?,?,null,now(),0,0,null,?,0,null)";
        try {
            PreparedStatement pst = con.prepareStatement(sql);
            pst.setObject(1, title);
            pst.setObject(2, blogContentBody);
            pst.setObject(3, link);
            if(pst.executeUpdate() == 0) {
                logger.info("爬取博客信息插入数据库失败");
            }else {
                cache.put(new net.sf.ehcache.Element(link, link));
                logger.info("爬取博客信息插入数据库成功");
            }
        } catch (SQLException e) {
            logger.error("数据异常-SQLException：",e);
        }
    }

    /**
     * 将别人博客内容进行加工，将原有图片地址换成本地的图片地址
     * @param blogContent
     * @param replaceUrlMap
     * @return
     */
    private static String replaceContent(String blogContent, Map<String, String> replaceUrlMap) {
        for(Map.Entry<String, String> entry: replaceUrlMap.entrySet()) {
            blogContent = blogContent.replace(entry.getKey(), entry.getValue());
        }
        return blogContent;
    }

    /**
     * 别人服务器图片本地化
     * @param imgUrlList
     * @return
     */
    private static Map<String, String> downloadImgList(List<String> imgUrlList) {
        Map<String, String> replaceMap = new HashMap<String, String>();
        for (String imgUrl : imgUrlList) {
            CloseableHttpClient httpClient = HttpClients.createDefault();
            HttpGet httpGet = new HttpGet(imgUrl);
            RequestConfig config = RequestConfig.custom().setConnectTimeout(5000).setSocketTimeout(8000).build();
            httpGet.setConfig(config);
            CloseableHttpResponse response = null;
            try {
                response = httpClient.execute(httpGet);
                if (response == null) {
                    logger.info(HOMEURL + ":爬取无响应");
                }else {
                    if (response.getStatusLine().getStatusCode() == 200) {
                        HttpEntity entity = response.getEntity();
                        String blogImagesPath = PropertiesUtil.getValue("blogImages");
                        String dateDir = DateUtil.getCurrentDatePath();
                        String uuid = UUID.randomUUID().toString();
                        String subfix = entity.getContentType().getValue().split("/")[1];
                        String fileName = blogImagesPath + dateDir + "/" + uuid + "." + subfix;
                        
                        FileUtils.copyInputStreamToFile(entity.getContent(), new File(fileName));
                        replaceMap.put(imgUrl, fileName);
                    }
                }
            } catch (ClientProtocolException e) {
                logger.error(imgUrl + "-ClientProtocolException", e);
            } catch (IOException e) {
                logger.error(imgUrl + "-IOException", e);
            } catch (Exception e) {
                logger.error(imgUrl + "-Exception", e);
            } finally {
                try {
                    if (response != null) {
                        response.close();
                    }
                } catch (IOException e) {
                    logger.error(imgUrl + "-IOException", e);
                }
            }
        
        }
        return replaceMap;
    }

    public static void start() {
        while(true) {
            DbUtil dbUtil = new DbUtil();
            try {
                con = dbUtil.getCon();
                parseHomePage();
            } catch (Exception e) {
                logger.error("数据库连接势失败！");
            } finally {
                try {
                    if (con != null) {
                        con.close();
                    }
                } catch (SQLException e) {
                    logger.error("数据关闭异常-SQLException：",e);
                }
            }
            try {
                Thread.sleep(1000*60);
            } catch (InterruptedException e) {
                logger.error("主线程休眠异常-InterruptedException：",e);
            }
        }
    }

    public static void main(String[] args) {
        start();
    }
}

数据库中