java jsoup及jsoup+HtmlUnit简单爬虫

以下是两种爬虫方式
**

1.Jsoup简单爬虫

**
首先是普通jsoup爬取网页信息，由于我是搭建的一个简单地maven项目，所以先上maven依赖（以下maven依赖两个代码都适用）：

<dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.10.3</version>
        </dependency>
        
        <dependency>
            <groupId>javax.xml</groupId>
            <artifactId>jaxp-api</artifactId>
            <version>1.4.2</version>
        </dependency>

        <dependency>
            <groupId>net.sourceforge.htmlcleaner</groupId>
            <artifactId>htmlcleaner</artifactId>
            <version>2.9</version>
        </dependency>

        <dependency>
            <groupId>net.sourceforge.htmlunit</groupId>
            <artifactId>htmlunit</artifactId>
            <version>2.29</version>
        </dependency>

代码部分：

package com.jsoup;

import org.htmlcleaner.CleanerProperties;
import org.htmlcleaner.DomSerializer;
import org.htmlcleaner.HtmlCleaner;
import org.htmlcleaner.TagNode;
import org.jsoup.Connection;
import org.jsoup.Jsoup;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathFactory;
import java.io.IOException;
import java.util.ArrayList;
import java.util.LinkedHashMap;
import java.util.List;
import java.util.Map;

public class JsoupHelper {
    public static Object fecthNode(String url, String xpath) throws Exception {
        String html = null;
        try {
            Connection connect = Jsoup.connect(url);
            html = connect.get().body().html();
        } catch (IOException e) {
            e.printStackTrace();
            return null;
        }
        HtmlCleaner hc = new HtmlCleaner();
        TagNode tn = hc.clean(html);
        Document dom = new DomSerializer(new CleanerProperties()).createDOM(tn);
        XPath xPath = XPathFactory.newInstance().newXPath();
        Object result = xPath.evaluate(xpath, dom, XPathConstants.NODESET);
        return result;
    }

    /**
     * 获取xpath下的a标签的文本值及href属性值
     * @param url
     * @param xpath
     * @return
     * @throws Exception
     */
    public static Map<String, String> fecthByMap(String url, String xpath) throws Exception {
        Map<String, String> nodeMap = new LinkedHashMap<>();
        Object result = fecthNode(url, xpath);
        if (result instanceof NodeList) {
            NodeList nodeList = (NodeList) result;
            for (int i = 0; i < nodeList.getLength(); i++) {
                Node node = nodeList.item(i);
                if(node == null){
                    continue;
                }
                nodeMap.put(node.getTextContent(), node.getAttributes().getNamedItem("href")!=null ?
                        node.getAttributes().getNamedItem("href").getTextContent() : "");
                System.out.println(node.getTextContent() + " : " + node.getAttributes().getNamedItem("href"));
            }
        }
        return nodeMap;
    }

    /**
     * 获取xpath下的某个属性值
     * @param url
     * @param xpath
     * @param attr
     * @return
     * @throws Exception
     */
    public static List<String> fecthAttr(String url, String xpath, String attr) throws Exception {
        List<String> list = new ArrayList<>();
        Object result = fecthNode(url, xpath);
        if (result instanceof NodeList) {
            NodeList nodeList = (NodeList) result;
            for (int i = 0; i < nodeList.getLength(); i++) {
                Node node = nodeList.item(i);
                if(node == null){
                    continue;
                }
                list.add(node.getAttributes().getNamedItem(attr).getTextContent());
                System.out.println(node.getTextContent() + " : " + node.getAttributes().getNamedItem("href"));
            }
        }
        return list;
    }
    public static void main(String[] args) throws Exception{
        fecthByMap("https://www.jianshu.com/u/df0f6525c1c5","//ul[@class='note-list']/li//a[@class='title']");
    }

}

效果如下：

2.jsoup+HtmlUnit动态获取页面信息

maven依赖参考文章开头配置

代码部分：

package com.jsoup;
import com.gargoylesoftware.htmlunit.WebClient;
import com.gargoylesoftware.htmlunit.html.HtmlElement;
import com.gargoylesoftware.htmlunit.html.HtmlInput;
import com.gargoylesoftware.htmlunit.html.HtmlPage;
import java.util.List;
public class JsoupHttpClient {
	/**
    * Xpath:级联选择 ✔
    * ① //：从匹配选择的当前节点选择文档中的节点，而不考虑它们的位置
    * ② h3：匹配<h3>标签
    * ③ [@class='name']：属性名为class的值为name
    * ④ a：匹配<a>标签
    */
    public static void main(String[] args) {
//        jsoup("http://wwww.baidu.com","kw","jsoup","su","//h3[@class='t']/a");
        jsoup("https://cn.bing.com/","sb_form_q","jsoup","sb_form_go","//li[@class='b_algo']");
    }

	 /**
     *
     * @param url 网址
     * @param inputId 获取搜索输入框
     * @param inputVal 往输入框 “填值”
     * @param btnId “点击” 搜索
     * @param xpath 选择元素
     */
    public static void jsoup(String url, String inputId, String inputVal, String btnId, String xpath){
        try {
            //创建webclient
            WebClient webClient = new WebClient();
            //取消JS支持
            webClient.getOptions().setJavaScriptEnabled(false);
            //取消CSS支持
            webClient.getOptions().setCssEnabled(false);
            //获取指定网页实体
            HtmlPage page = (HtmlPage) webClient.getPage(url);
            //获取搜索输入按钮
            HtmlInput input  = page.getHtmlElementById(inputId);
            //往输入框填值
            input.setValueAttribute(inputVal);
            //获取搜索按钮
            HtmlInput btn = page.getHtmlElementById(btnId);
            //点击搜索
            HtmlPage page1 = btn.click();
            //选择元素
            List<HtmlElement> elementList = page1.getByXPath(xpath);
            System.out.println("----begin----");
            for(int i=0;i<elementList.size();i++) {
                // 输出新页面的文本
                System.out.println(i+1+"、"+elementList.get(i).asText());
            }
            System.out.println("----end----");
        }catch (Exception e){
            e.printStackTrace();
        }
    }
}

效果：

这里外加一个jsoup爬取豆瓣的小例子：

package com.jsoup;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import java.io.IOException;

public class JsoupMovie {
    public static void main(String[] args) {
        crawlMovieinfo();
    }
    public static void crawlMovieinfo() {
        // 1.获取网页
        final String URL = "https://movie.douban.com/top250";
        Document document = null;
        try {
            document = Jsoup.connect(URL).get();
        } catch (IOException e) {
            e.printStackTrace();
        }
        // 2.选择具体的电影的项，注意first方法，这里先只选取第一个进行测试
        Element itemElement = document.select("ol li").first();
        // 3.1电影排名
        Element rankElement = itemElement.select("em").first();
        String rankString = rankElement.text();
        System.out.println("排行榜:" + rankString.toString());
        // 3.2电影网址
        Element urlElement = itemElement.select("div.hd a").first();
        String urlString = urlElement.attr("href");
        System.out.println("电影介绍网址:" + urlString.toString());
        // 3.3电影名
        Element titleElement = urlElement.select("span.title").first();
        String titleString = titleElement.text();
        System.out.println("电影名:" + titleString.toString());
        // 3.4评分
        Element ratingNumElement = itemElement.select("div.star span.rating_num").first();
        String ratingNumString = ratingNumElement.text();
        System.out.println("评分:" + ratingNumString.toString());
        // 3.5评价人数
        Element ratingPeopleNumElement = itemElement.select("div.star span").last();
        String ratingPeopleNumString = ratingPeopleNumElement.text();
        System.out.println("人数:" + ratingPeopleNumString.toString());
        // 3.6 一句话简评
        Element quoteElement = itemElement.select("p.quote span.inq").first();
        String quoteString = quoteElement.text();
        System.out.println("简评:" + quoteString.toString());
    }
}

效果：