本站木有非理性广告和有害内容,请大度地将本站加入广告屏蔽白名单吧~~~

Java版HTML解析器

:: 代码生涯 泥塘塘主 312℃ 0评论

这是一个对HTML进行分析的快速实时的解析器,可以通过DOM或CSS选择器来查找,提取数据。

下面例子展示此解析器的用法,例子还用到了上方提到的Java采集引擎

package cfw.test;

import cfw.html.TagSearchRange;
import cfw.html.HtmlParser;
import cfw.html.HtmlTag;
import cfw.http.ResponseResult;
import cfw.http.UserAgentPack;
import cfw.http.WebClient;
import cfw.http.WebRequest;
import cfw.model.FinancialNewsListModel;
import com.alibaba.fastjson.JSONArray;
import com.sun.jndi.toolkit.url.Uri;

import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;


public class HtmlParserTest {


    public static void main(String[] args) {

        // 【新浪财经要闻文章列表】抓取
        List<FinancialNewsListModel> sinaNews = crawlSinaFinancialNewsList();
        System.out.println(String.format("【新浪财经-要闻列表页】抓取到%s个文章列表", sinaNews.size()));
        String json  = JSONArray.toJSON(sinaNews).toString();
        System.out.println(json);

        // 【凤凰财经文章列表】抓取

        List<FinancialNewsListModel> ifengNews = crawlIFengFinancialNewsList();
        System.out.println(String.format("【凤凰财经-文章列表页】抓取到%s个文章列表", ifengNews.size()));
        String json2 = JSONArray.toJSON(ifengNews).toString();
        System.out.println(json2);

    }


    /**
     * 【新浪财经要闻文章列表】抓取
     *
     * @return
     */
    private static List<FinancialNewsListModel> crawlSinaFinancialNewsList() {
            /*
             抓取地址: http://finance.sina.com.cn/
             */

        List<FinancialNewsListModel> fnews = new ArrayList<FinancialNewsListModel>();
        try {
            String url = "http://finance.sina.com.cn/";
            WebRequest req = new WebRequest();
            req.setUrl(url);
            req.setMethod("GET");
            req.setUserAgent(UserAgentPack.getUserAgentRandom());
            Map<String, String> dic = new HashMap<String, String>();
            dic.put("Upgrade-Insecure-Requests", "1");
            dic.put("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8");
            dic.put("Accept-Encoding", "gzip, deflate");
            dic.put("Accept-Language", "zh-CN,zh;q=0.8,en;q=0.6");
            req.setSpecialHeadCollection(dic);
            ResponseResult sr = WebClient.download(req);
            String html = sr.getResponseHtmlStr();
            HtmlParser parser = new HtmlParser(html);
            HtmlTag htmlTag = parser.parse();

            // 要闻
            HtmlTag finTag = htmlTag.getElementById("fin_tabs0_c0");
            List<HtmlTag> aTags = finTag.getElementsByTagName("a");
            for (HtmlTag aTag : aTags) {
                FinancialNewsListModel list = new FinancialNewsListModel();
                list.setArticalUrl(aTag.getAttribute("href"));
                list.setArticalTitle(aTag.getValue());
                Uri uri = new Uri(list.getArticalUrl());
                String[] strs = uri.getPath().split("/");
                if (strs.length > 1) {
                    list.setArticalMD("sina-" + strs[strs.length - 1].replace(".html", "").replace(".shtml", ""));
                    fnews.add(list);
                }
            }
        } catch (Exception ex) {
            System.out.println("【新浪财经-要闻列表页】抓取失败" + ex.getMessage());
        }

        return fnews;
    }


    /**
     * 【凤凰财经文章列表】抓取
     *
     * @return
     */
    private static List<FinancialNewsListModel> crawlIFengFinancialNewsList() {
            /*
             抓取地址: http://finance.ifeng.com/    
             */

        List<FinancialNewsListModel> fnews = new ArrayList<>();
        try {
            String url = "http://finance.ifeng.com/";
            WebRequest req = new WebRequest();
            req.setUrl(url);
            req.setMethod("GET");
            req.setUserAgent(UserAgentPack.getUserAgentRandom());
            Map<String, String> dic = new HashMap<>();
            dic.put("Upgrade-Insecure-Requests", "1");
            dic.put("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8");
            dic.put("Accept-Encoding", "gzip, deflate");
            dic.put("Accept-Language", "zh-CN,zh;q=0.8,en;q=0.6");
            req.setSpecialHeadCollection(dic);
            ResponseResult sr = WebClient.download(req);
            String html = sr.getResponseHtmlStr();
            HtmlParser parser = new HtmlParser(html);

            HtmlTag htmlTag = parser.parse();

            HtmlTag listTag = htmlTag.search(t -> t.getAttribute("class").equals("list-tab"), TagSearchRange.AllElements).get(0);
            List<HtmlTag> divTags = listTag.search(s -> s.getAttribute("class").equals("list_L z20 clearfix"), TagSearchRange.AllElements);
            for (HtmlTag divTag : divTags) {
                HtmlTag list_textTag = divTag.search(d -> d.getAttribute("class").equals("list_text"), TagSearchRange.AllElements).get(0);
                HtmlTag aTag = list_textTag.getElementsByTagName("a").get(0);

                FinancialNewsListModel list = new FinancialNewsListModel();
                list.setArticalUrl(aTag.getAttribute("href"));
                list.setArticalTitle(aTag.getValue());
                Uri uri = new Uri(list.getArticalUrl());
                String[] strs = uri.getPath().split("/");
                list.setArticalMD("ifeng-" + strs[strs.length - 1].replace(".html", "").replace(".shtml", ""));
                fnews.add(list);
            }


        } catch (Exception ex) {
            System.out.println("【凤凰财经-文章列表页】抓取失败" + ex.getMessage());
        }

        return fnews;
    }

}

运行结果如下:

Java版HTML解析器

最后

源码下载。

 

转载请注明:泥塘·物语 » Java版HTML解析器

喜欢 (3)
发表我的评论
取消评论

表情

Hi,您需要填写昵称和邮箱!

  • 昵称 (必填)
  • 邮箱 (必填)
  • 网址