sinablogprocessor sample
parent
094f9d1552
commit
be37d8b216
|
@ -1,37 +0,0 @@
|
||||||
package us.codecraft.webmagic.samples;
|
|
||||||
|
|
||||||
import us.codecraft.webmagic.Page;
|
|
||||||
import us.codecraft.webmagic.Site;
|
|
||||||
import us.codecraft.webmagic.Spider;
|
|
||||||
import us.codecraft.webmagic.processor.PageProcessor;
|
|
||||||
|
|
||||||
/**
|
|
||||||
* @author code4crafter@gmail.com <br>
|
|
||||||
*/
|
|
||||||
public class SinaBlogProcesser implements PageProcessor {
|
|
||||||
|
|
||||||
private Site site;
|
|
||||||
|
|
||||||
@Override
|
|
||||||
public void process(Page page) {
|
|
||||||
page.addTargetRequests(page.getHtml().xpath("//div[@class='articalfrontback SG_j_linedot1 clearfix']").links().all());
|
|
||||||
page.putField("title", page.getHtml().xpath("//div[@class='articalTitle']/h2"));
|
|
||||||
page.putField("content",page.getHtml().xpath("//div[@id='articlebody']//div[@class='articalContent']"));
|
|
||||||
page.putField("id",page.getUrl().regex("http://blog\\.sina\\.com\\.cn/s/blog_(\\w+)"));
|
|
||||||
page.putField("date",page.getHtml().xpath("//div[@id='articlebody']//span[@class='time SG_txtc']").regex("\\((.*)\\)"));
|
|
||||||
// page.putField("tags",page.getHtml().xpath("//td[@class='blog_tag']/h3/a"));
|
|
||||||
}
|
|
||||||
|
|
||||||
@Override
|
|
||||||
public Site getSite() {
|
|
||||||
if (site==null){
|
|
||||||
site = Site.me().setDomain("blog.sina.com.cn").addStartUrl("http://blog.sina.com.cn/s/blog_4701280b0102egl0.html").setSleepTime(3000).
|
|
||||||
setUserAgent("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.65 Safari/537.31");
|
|
||||||
}
|
|
||||||
return site;
|
|
||||||
}
|
|
||||||
|
|
||||||
public static void main(String[] args) {
|
|
||||||
Spider.create(new SinaBlogProcesser()).run();
|
|
||||||
}
|
|
||||||
}
|
|
|
@ -0,0 +1,47 @@
|
||||||
|
package us.codecraft.webmagic.samples;
|
||||||
|
|
||||||
|
import us.codecraft.webmagic.Page;
|
||||||
|
import us.codecraft.webmagic.Site;
|
||||||
|
import us.codecraft.webmagic.Spider;
|
||||||
|
import us.codecraft.webmagic.processor.PageProcessor;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @author code4crafter@gmail.com <br>
|
||||||
|
*/
|
||||||
|
public class SinaBlogProcessor implements PageProcessor {
|
||||||
|
|
||||||
|
public static final String URL_LIST = "http://blog\\.sina\\.com\\.cn/s/articlelist_1487828712_0_\\d+\\.html";
|
||||||
|
|
||||||
|
public static final String URL_POST = "http://blog\\.sina\\.com\\.cn/s/blog_\\w+\\.html";
|
||||||
|
|
||||||
|
private Site site = Site
|
||||||
|
.me()
|
||||||
|
.setDomain("blog.sina.com.cn")
|
||||||
|
.setSleepTime(3000)
|
||||||
|
.setUserAgent(
|
||||||
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.65 Safari/537.31");
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public void process(Page page) {
|
||||||
|
if (page.getUrl().regex(URL_LIST).match()) {
|
||||||
|
page.addTargetRequests(page.getHtml().xpath("//div[@class=\"articleList\"]").links().regex(URL_POST).all());
|
||||||
|
page.addTargetRequests(page.getHtml().links().regex(URL_LIST).all());
|
||||||
|
} else {
|
||||||
|
page.putField("title", page.getHtml().xpath("//div[@class='articalTitle']/h2"));
|
||||||
|
page.putField("content", page.getHtml().xpath("//div[@id='articlebody']//div[@class='articalContent']"));
|
||||||
|
page.putField("id", page.getUrl().regex("http://blog\\.sina\\.com\\.cn/s/blog_(\\w+)"));
|
||||||
|
page.putField("date",
|
||||||
|
page.getHtml().xpath("//div[@id='articlebody']//span[@class='time SG_txtc']").regex("\\((.*)\\)"));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public Site getSite() {
|
||||||
|
return site;
|
||||||
|
}
|
||||||
|
|
||||||
|
public static void main(String[] args) {
|
||||||
|
Spider.create(new SinaBlogProcessor()).addUrl("http://blog.sina.com.cn/s/articlelist_1487828712_0_1.html")
|
||||||
|
.run();
|
||||||
|
}
|
||||||
|
}
|
|
@ -5,7 +5,7 @@ import org.junit.Test;
|
||||||
import us.codecraft.webmagic.Spider;
|
import us.codecraft.webmagic.Spider;
|
||||||
import us.codecraft.webmagic.pipeline.FilePipeline;
|
import us.codecraft.webmagic.pipeline.FilePipeline;
|
||||||
import us.codecraft.webmagic.pipeline.JsonFilePipeline;
|
import us.codecraft.webmagic.pipeline.JsonFilePipeline;
|
||||||
import us.codecraft.webmagic.samples.SinaBlogProcesser;
|
import us.codecraft.webmagic.samples.SinaBlogProcessor;
|
||||||
import us.codecraft.webmagic.scheduler.FileCacheQueueScheduler;
|
import us.codecraft.webmagic.scheduler.FileCacheQueueScheduler;
|
||||||
|
|
||||||
import java.io.IOException;
|
import java.io.IOException;
|
||||||
|
@ -20,7 +20,7 @@ public class SinablogProcessorTest {
|
||||||
@Ignore
|
@Ignore
|
||||||
@Test
|
@Test
|
||||||
public void test() throws IOException {
|
public void test() throws IOException {
|
||||||
SinaBlogProcesser sinaBlogProcesser = new SinaBlogProcesser();
|
SinaBlogProcessor sinaBlogProcessor = new SinaBlogProcessor();
|
||||||
//pipeline是抓取结束后的处理
|
//pipeline是抓取结束后的处理
|
||||||
//默认放到/data/webmagic/ftl/[domain]目录下
|
//默认放到/data/webmagic/ftl/[domain]目录下
|
||||||
JsonFilePipeline pipeline = new JsonFilePipeline("/data/webmagic/");
|
JsonFilePipeline pipeline = new JsonFilePipeline("/data/webmagic/");
|
||||||
|
@ -29,7 +29,7 @@ public class SinablogProcessorTest {
|
||||||
//ConsolePipeline输出结果到控制台
|
//ConsolePipeline输出结果到控制台
|
||||||
//FileCacheQueueSchedular保存url,支持断点续传,临时文件输出到/data/temp/webmagic/cache目录
|
//FileCacheQueueSchedular保存url,支持断点续传,临时文件输出到/data/temp/webmagic/cache目录
|
||||||
//Spider.run()执行
|
//Spider.run()执行
|
||||||
Spider.create(sinaBlogProcesser).pipeline(new FilePipeline()).pipeline(pipeline).scheduler(new FileCacheQueueScheduler("/data/temp/webmagic/cache/")).
|
Spider.create(sinaBlogProcessor).pipeline(new FilePipeline()).pipeline(pipeline).scheduler(new FileCacheQueueScheduler("/data/temp/webmagic/cache/")).
|
||||||
run();
|
run();
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue