ownWebMagic/src/main/java/com/mobai/webMagic/OschinaBlogPageProcessor.java

package com.mobai.webMagic;

import com.mobai.webMagic.util.ImageDownloaderUtil;
import org.apache.commons.lang3.ObjectUtils;
import org.apache.log4j.Logger;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.pipeline.JsonFilePipeline;
import us.codecraft.webmagic.processor.PageProcessor;
import us.codecraft.webmagic.selector.Html;
import us.codecraft.webmagic.selector.Selectable;

import java.util.List;

public class OschinaBlogPageProcessor implements PageProcessor {

    private static final Logger log = Logger.getLogger(OschinaBlogPageProcessor.class);
    //    private Site site = Site.me().setDomain("my.oschina.net");
    private Site site = Site.me().setRetryTimes(3)
//            .setSleepTime(24*60*60*1000);
            .setSleepTime(1000);

    @Override
    public void process(Page page) {
        Selectable url1 = page.getUrl();
//        Selectable xpath = page.getUrl().xpath("http://www.nanshan.edu.cn/nyyw.123.*");
        page.getRequest().getUrl();
        if (url1 == null) {
            log.error("url为空");
            return;
        }
        log.info(url1.get());
        if (url1.get().matches("http://www.nanshan.edu.cn/nyyw.*")) {
//            // 获取烟台南山学院的新闻Url
//            List<String> newsUrls = page.getHtml()
//                    .xpath("/html/body/div[5]/div[1]/div[1]/div[2]/div/ul/li/a").links().all();
//            // 存在分页,将下一页url 添加到待采集列表
//            Selectable nextPage = null;
//            Selectable firstA = page.getHtml().xpath("/html/body/div[5]/div[1]/div[1]/div[2]/div/div[2]/div/table/tbody/tr/td/table/tbody/tr/td[2]/div/a[1]/text()");
//            Selectable secondA = null;
//            if ("首页".equals(firstA)){
//                secondA = page.getHtml().xpath("/html/body/div[5]/div[1]/div[1]/div[2]/div/div[2]/div/table/tbody/tr/td/table/tbody/tr/td[2]/div/a[3]/text()");
//            }
//            if ("下页".equals(firstA)) {
//                nextPage = firstA;
//            } else if ("下页".equals(secondA)) {
//                nextPage = secondA;
//            } else {
//                System.out.println("没有下一页");
//            }
//            if (nextPage != null) {
//                newsUrls.add(nextPage.links().get());
//                Selectable finalNextPage = nextPage;
//                process(new Page() {{
//                    setUrl(finalNextPage);
//                }});
//            }
            // 添加
            page.addTargetRequests(getNewsUrls(page));
            page.setSkip(true);
        } else {
            String url = page.getUrl().toString();
            String title = page.getHtml().xpath("/html/body/div[5]/div[1]/div[1]/div[2]/form/div/h1/text()").get();
            // 日期等信息需分割 包括  来源
            String newsHead = page.getHtml().xpath("/html/body/div[5]/div[1]/div[1]/div[2]/form/div/div[1]/text()").get();
            String date = newsHead.substring(newsHead.indexOf("发布时间")+5, newsHead.indexOf("发布时间") + 15);
            String source = newsHead.substring(newsHead.indexOf("来源")+3, newsHead.indexOf("点击次数")-2);
            String content = page.getHtml().xpath("/html/body/div[5]/div[1]/div[1]/div[2]/form/div/div[2]/allText()").get();
            page.putField("url", url);
            page.putField("title", title);
            page.putField("date", date);
            page.putField("source", source);
            page.putField("content", content);


            //获取图片对应的URL
            List<String> urlList = page.getHtml().xpath("/html/body/div[5]/div[1]/div[1]/div[2]/form/div/div[2]/div/p/img/@src").all();
            // 下载每一张图片
            for (int i = 0; i < urlList.size(); i++) {
                // http://www.nanshan.edu.cn/__local/2/4D/93/76F03CB6EBE3BFB7018397B37D4_C03E3A0C_36A9C.png
                String inputUrl = "http://www.nanshan.edu.cn" + urlList.get(i);
                ImageDownloaderUtil.downLoadImage(inputUrl, "D:/workspace/web-magic-test/news/img/" + inputUrl.split("/")[7]);
            }
        }
        List<String> links = page.getHtml().links().regex("http://my\\.oschina\\.net/flashsword/blog/\\d+").all();
        page.addTargetRequests(links);
        System.out.println("页面提取执行完毕");
    }

    public List<String> getNewsUrls(Page page) {
        // 获取烟台南山学院的新闻Url
        List<String> newsUrls = page.getHtml()
                .xpath("/html/body/div[5]/div[1]/div[1]/div[2]/div/ul/li/a").links().all();
        // 存在分页,将下一页url 添加到待采集列表
        Selectable nextPage = null;
//        Selectable firstA = page.getHtml().xpath("/html/body/div[5]/div[1]/div[1]/div[2]/div/div[2]/div/table/tbody/tr/td/table/tbody/tr/td[2]/div/a[1]/text()");
        Selectable firstA = page.getHtml().xpath("/html/body/div[5]/div[1]/div[1]/div[2]/div/div[2]/div/table/tbody/tr/td/table/tbody/tr/td[2]/div/a[1]");
        Selectable secondA = null;
        if (firstA.get().contains("首页")) {
            try {
                secondA = page.getHtml().xpath("/html/body/div[5]/div[1]/div[1]/div[2]/div/div[2]/div/table/tbody/tr/td/table/tbody/tr/td[2]/div/a[3]");
            } catch (Exception e) {
                log.error("没有下一页了");
            }
        }
        if (firstA.get().contains("下页")) {
            nextPage = firstA.links();
        } else if (ObjectUtils.isNotEmpty(secondA) && secondA.get().contains("下页")) {
            nextPage = secondA.links();
        } else {
            System.out.println("没有下一页");
        }
        if (nextPage != null) {
//            Selectable finalNextPage = nextPage;
//            newsUrls.addAll(getNewsUrls(new Page() {{
//                setUrl(finalNextPage);
//                setHtml(new Html("",finalNextPage.get()));
//            }}));
            newsUrls.add(nextPage.get());
        }
        return newsUrls;
    }

    @Override
    public Site getSite() {
        return site;
    }

    public static void main(String[] args) {
        Spider.create(new OschinaBlogPageProcessor())
                .addUrl("http://www.nanshan.edu.cn/info/1051/8981.htm")
                .addPipeline(new JsonFilePipeline("news/"))
                .run();
    }
}