diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/model/ExtractBy.java b/webmagic-core/src/main/java/us/codecraft/webmagic/model/ExtractBy.java index 4c37c9b..661fd67 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/model/ExtractBy.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/model/ExtractBy.java @@ -5,6 +5,7 @@ import java.lang.annotation.Retention; import java.lang.annotation.Target; /** + * 定义类或者字段的抽取规则。
* @author code4crafter@gmail.com
* @date: 13-8-1
* Time: 下午8:40
diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/model/ExtractByUrl.java b/webmagic-core/src/main/java/us/codecraft/webmagic/model/ExtractByUrl.java index 9f77676..f443c0e 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/model/ExtractByUrl.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/model/ExtractByUrl.java @@ -5,6 +5,7 @@ import java.lang.annotation.Retention; import java.lang.annotation.Target; /** + * 定义类或者字段的抽取规则(从url中抽取,只支持正则表达式)。
* @author code4crafter@gmail.com
* @date: 13-8-1
* Time: 下午8:40
diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/model/HelpUrl.java b/webmagic-core/src/main/java/us/codecraft/webmagic/model/HelpUrl.java index 9dee05b..808d58a 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/model/HelpUrl.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/model/HelpUrl.java @@ -5,6 +5,7 @@ import java.lang.annotation.Retention; import java.lang.annotation.Target; /** + * 定义辅助爬取的url。
* @author code4crafter@gmail.com
* @date: 13-8-1
* Time: 下午8:40
diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/model/TargetUrl.java b/webmagic-core/src/main/java/us/codecraft/webmagic/model/TargetUrl.java index 96ca864..3622f55 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/model/TargetUrl.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/model/TargetUrl.java @@ -5,6 +5,7 @@ import java.lang.annotation.Retention; import java.lang.annotation.Target; /** + * 定义某个类抽取的范围和来源,sourceRegion可以用xpath语法限定抽取区域。
* @author code4crafter@gmail.com
* @date: 13-8-1
* Time: 下午8:40
diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/DoubleKeyMap.java b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/DoubleKeyMap.java index 500573a..a834528 100755 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/DoubleKeyMap.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/DoubleKeyMap.java @@ -3,7 +3,7 @@ package us.codecraft.webmagic.utils; import java.util.Map; /** - * @author yihua.huang@dianping.com + * @author code4crafter@gmail.com * @date Dec 14, 2012 */ public class DoubleKeyMap extends MultiKeyMapBase { diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/MultiKeyMapBase.java b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/MultiKeyMapBase.java index e0b5c64..256097a 100755 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/MultiKeyMapBase.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/MultiKeyMapBase.java @@ -1,7 +1,7 @@ package us.codecraft.webmagic.utils; /** - * @author yihua.huang@dianping.com + * @author code4crafter@gmail.com * @date Dec 14, 2012 */ diff --git a/webmagic-samples/src/main/java/us/codecraft/webmagic/model/samples/News163.java b/webmagic-samples/src/main/java/us/codecraft/webmagic/model/samples/News163.java index bf26930..07b1e8e 100644 --- a/webmagic-samples/src/main/java/us/codecraft/webmagic/model/samples/News163.java +++ b/webmagic-samples/src/main/java/us/codecraft/webmagic/model/samples/News163.java @@ -46,7 +46,7 @@ public class News163 implements PagedModel, AfterExtractor { @Override public String getPage() { if (page == null) { - return "0"; + return "1"; } return page; }