Commit 38242321 authored by yihua.huang's avatar yihua.huang

remove site.addStartUrl in samples

parent 8564d51e
...@@ -28,10 +28,10 @@ public class SpiderTest { ...@@ -28,10 +28,10 @@ public class SpiderTest {
// PageProcessor pageProcessor = new MeicanProcessor(); // PageProcessor pageProcessor = new MeicanProcessor();
// Spider.me().pipeline(new FilePipeline()).scheduler(new FileCacheQueueScheduler(pageProcessor.getSite(),"/data/temp/webmagic/cache/")). // Spider.me().pipeline(new FilePipeline()).scheduler(new FileCacheQueueScheduler(pageProcessor.getSite(),"/data/temp/webmagic/cache/")).
// processor(pageProcessor).run(); // processor(pageProcessor).run();
SimplePageProcessor pageProcessor2 = new SimplePageProcessor("http://www.diaoyuweng.com/home.php?mod=space&uid=88304&do=thread&view=me&type=thread&from=space", "http://www.diaoyuweng.com/thread-*-1-1.html"); SimplePageProcessor pageProcessor2 = new SimplePageProcessor( "http://www.diaoyuweng.com/thread-*-1-1.html");
System.out.println(pageProcessor2.getSite().getCharset()); System.out.println(pageProcessor2.getSite().getCharset());
pageProcessor2.getSite().setSleepTime(500); pageProcessor2.getSite().setSleepTime(500);
Spider.create(pageProcessor2).addPipeline(new FilePipeline()).scheduler(new FileCacheQueueScheduler("/data/temp/webmagic/cache/")). Spider.create(pageProcessor2).addUrl("http://www.diaoyuweng.com/home.php?mod=space&uid=88304&do=thread&view=me&type=thread&from=space").addPipeline(new FilePipeline()).scheduler(new FileCacheQueueScheduler("/data/temp/webmagic/cache/")).
run(); run();
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment