Commit 8cef8774 authored by yihua.huang's avatar yihua.huang

change author info

parent 672db58d
......@@ -10,7 +10,7 @@ import java.util.Map;
import java.util.concurrent.ConcurrentHashMap;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午11:22
*/
......
package us.codecraft.webmagic;
/**
* User: cairne
* Request对象是
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午11:37
*/
......
......@@ -4,7 +4,7 @@ import java.util.HashSet;
import java.util.Set;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午12:13
*/
......
......@@ -14,7 +14,7 @@ import java.util.ArrayList;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午6:53
*/
......
......@@ -5,11 +5,18 @@ import us.codecraft.webmagic.Request;
import us.codecraft.webmagic.Site;
/**
* User: cairne
* Downloader是webmagic抓取页面的核心接口。
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午12:14
*/
public interface Downloader {
/**
*
* @param request
* @param site
* @return
*/
public Page download(Request request,Site site);
}
......@@ -14,7 +14,7 @@ import us.codecraft.webmagic.utils.UrlUtils;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午12:15
*/
......
......@@ -13,7 +13,7 @@ import org.apache.http.params.*;
import us.codecraft.webmagic.Site;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午12:29
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.selector.Selectable;
import java.util.Map;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:45
*/
......
......@@ -13,7 +13,7 @@ import java.io.PrintWriter;
import java.util.Map;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午6:28
*/
......
......@@ -4,7 +4,7 @@ import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:39
*/
......
......@@ -4,7 +4,7 @@ import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午11:42
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.utils.UrlUtils;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-22
* Time: 下午9:15
*/
......
......@@ -16,7 +16,7 @@ import java.util.concurrent.atomic.AtomicBoolean;
import java.util.concurrent.atomic.AtomicInteger;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:13
*/
......
......@@ -10,7 +10,7 @@ import java.util.concurrent.BlockingQueue;
import java.util.concurrent.LinkedBlockingQueue;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:13
*/
......
......@@ -4,7 +4,7 @@ import us.codecraft.webmagic.Request;
import us.codecraft.webmagic.Site;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:12
*/
......
......@@ -4,7 +4,7 @@ import java.util.ArrayList;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午7:54
*/
......
......@@ -6,7 +6,7 @@ import java.util.ArrayList;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午7:54
*/
......
package us.codecraft.webmagic.selector;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午7:39
*/
......
......@@ -9,7 +9,7 @@ import java.util.regex.Pattern;
import java.util.regex.PatternSyntaxException;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午7:09
*/
......
......@@ -6,7 +6,7 @@ import java.util.regex.Pattern;
import java.util.regex.PatternSyntaxException;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午7:09
*/
......
......@@ -3,7 +3,7 @@ package us.codecraft.webmagic.selector;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-20
* Time: 下午7:51
*/
......
......@@ -3,7 +3,7 @@ package us.codecraft.webmagic.selector;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-20
* Time: 下午8:02
*/
......
......@@ -7,7 +7,7 @@ import java.util.Map;
import java.util.concurrent.ConcurrentHashMap;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午7:56
*/
......
......@@ -10,7 +10,7 @@ import java.util.concurrent.atomic.AtomicInteger;
/**
* readability算法,基础是找到所有p标签的父节点
* 写的比较乱,最终效果还在尝试中
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午4:42
*/
......
......@@ -6,7 +6,7 @@ import java.util.ArrayList;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午9:39
*/
......
......@@ -6,7 +6,7 @@ import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:52
*/
......
......@@ -5,7 +5,7 @@ import org.junit.Test;
import us.codecraft.webmagic.selector.Html;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午8:42
*/
......
......@@ -4,7 +4,7 @@ import junit.framework.Assert;
import org.junit.Test;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 上午7:13
*/
......
......@@ -4,7 +4,7 @@ import org.junit.Assert;
import org.junit.Test;
/**
* User: cairne Date: 13-4-21 Time: 上午10:06
* Author: code4crafter@gmail.com Date: 13-4-21 Time: 上午10:06
*/
public class XpathSelectorTest {
......
......@@ -4,7 +4,7 @@ import org.junit.Assert;
import org.junit.Test;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午2:22
*/
......
......@@ -11,7 +11,7 @@ import us.codecraft.webmagic.utils.UrlUtils;
import java.io.*;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-6-8
* Time: 下午9:00
*/
......
......@@ -6,7 +6,7 @@ import us.codecraft.webmagic.pipeline.FreemarkerPipeline;
import java.io.IOException;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-6-9
* Time: 上午7:14
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午8:08
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午8:08
*/
......
......@@ -8,7 +8,7 @@ import us.codecraft.webmagic.selector.PlainText;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午8:08
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:48
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午8:08
*/
......
......@@ -5,7 +5,7 @@ import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.processor.PageProcessor;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-5-20
* Time: 下午5:31
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-5-20
* Time: 下午5:31
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午8:08
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:48
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:48
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午8:08
*/
......
......@@ -5,7 +5,7 @@ import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.processor.PageProcessor;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:48
*/
......
......@@ -7,7 +7,7 @@ import us.codecraft.webmagic.processor.PageProcessor;
import java.util.List;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-21
* Time: 下午1:48
*/
......
......@@ -8,7 +8,7 @@ import us.codecraft.webmagic.samples.HuxiuProcessor;
import us.codecraft.webmagic.schedular.FileCacheQueueSchedular;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-4-20
* Time: 下午7:46
*/
......
......@@ -11,7 +11,7 @@ import us.codecraft.webmagic.schedular.FileCacheQueueSchedular;
import java.io.IOException;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-6-9
* Time: 上午8:02
*/
......
......@@ -11,7 +11,7 @@ import us.codecraft.webmagic.schedular.FileCacheQueueSchedular;
import java.io.IOException;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-6-9
* Time: 上午8:02
*/
......
......@@ -11,7 +11,7 @@ import us.codecraft.webmagic.schedular.FileCacheQueueSchedular;
import java.io.IOException;
/**
* User: cairne
* Author: code4crafter@gmail.com
* Date: 13-6-9
* Time: 上午8:02
*/
......
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