diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/selector/PlainText.java b/webmagic-core/src/main/java/us/codecraft/webmagic/selector/PlainText.java index d06a531..6fabd99 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/selector/PlainText.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/selector/PlainText.java @@ -6,10 +6,11 @@ import java.util.ArrayList; import java.util.List; /** - * 可抽取的纯文本,不包括xpath和css selector实现。
+ * Selectable plain text.
+ * Can not be selected by XPath or CSS Selector. + * * @author code4crafter@gmail.com
- * Date: 13-4-21 - * Time: 上午7:54 + * @since 0.1.0 */ public class PlainText implements Selectable { @@ -59,7 +60,7 @@ public class PlainText implements Selectable { List results = new ArrayList(); for (String string : strings) { String result = selector.select(string); - if (result!=null){ + if (result != null) { results.add(result); } } diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/Experimental.java b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/Experimental.java index 265f869..2022d29 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/Experimental.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/Experimental.java @@ -1,8 +1,8 @@ package us.codecraft.webmagic.utils; /** + * Stands for features unstable. * @author code4crafter@gmail.com
- * Stands for features not stable. */ public @interface Experimental { } diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/FilePersistentBase.java b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/FilePersistentBase.java index 509a71f..e65e2f9 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/FilePersistentBase.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/FilePersistentBase.java @@ -3,11 +3,10 @@ package us.codecraft.webmagic.utils; import java.io.File; /** - * 文件持久化的基础类。
+ * Base object of file persistence. * * @author code4crafter@gmail.com
- * Date: 13-8-11
- * Time: 下午4:21
+ * @since 0.2.0 */ public class FilePersistentBase { diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/ThreadUtils.java b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/ThreadUtils.java index d6876c7..0d5666c 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/ThreadUtils.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/ThreadUtils.java @@ -6,10 +6,8 @@ import java.util.concurrent.ThreadPoolExecutor; import java.util.concurrent.TimeUnit; /** - * 线程工具类。
* @author code4crafer@gmail.com - * Date: 13-6-23 - * Time: 下午7:11 + * @since 0.1.0 */ public class ThreadUtils { diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/UrlUtils.java b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/UrlUtils.java index 9f038bc..7dae1f2 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/UrlUtils.java +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/UrlUtils.java @@ -6,20 +6,20 @@ import java.util.regex.Matcher; import java.util.regex.Pattern; /** - * url及html处理工具类。
+ * url and html utils. + * * @author code4crafter@gmail.com
- * Date: 13-4-21 - * Time: 下午1:52 + * @since 0.1.0 */ public class UrlUtils { private static Pattern relativePathPattern = Pattern.compile("^([\\.]+)/"); /** - * 将url想对地址转化为绝对地址 - * @param url url地址 - * @param refer url地址来自哪个页面 - * @return url绝对地址 + * canonicalizeUrl + * @param url + * @param refer + * @return canonicalizeUrl */ public static String canonicalizeUrl(String url, String refer) { if (StringUtils.isBlank(url) || StringUtils.isBlank(refer)) { diff --git a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/package.html b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/package.html index bfbe8df..6b970ee 100644 --- a/webmagic-core/src/main/java/us/codecraft/webmagic/utils/package.html +++ b/webmagic-core/src/main/java/us/codecraft/webmagic/utils/package.html @@ -1,5 +1,5 @@ -提供一些处理链接的静态工具类。 +Static utils of webmagic.