├── README.md ├── db.sql ├── pom.xml └── src ├── main ├── java │ ├── com │ │ └── zhangwoo │ │ │ └── spider │ │ │ ├── client │ │ │ └── process │ │ │ │ ├── AnalyserTemplate.java │ │ │ │ ├── ClientMessageCenter.java │ │ │ │ ├── ScriptEngineTest.java │ │ │ │ ├── SpiderProcess.java │ │ │ │ ├── SpiderThread.java │ │ │ │ ├── TaskClientHandler.java │ │ │ │ └── XmlAnalyserTemplate.java │ │ │ ├── common │ │ │ ├── BloomFilter.java │ │ │ ├── MessageClientCoder.java │ │ │ └── MessageServerCoder.java │ │ │ ├── po │ │ │ ├── Conversation.java │ │ │ ├── Entity.java │ │ │ ├── Task.java │ │ │ ├── TaskState.java │ │ │ ├── UrlRequest.java │ │ │ └── UrlState.java │ │ │ └── server │ │ │ ├── ConversationSaveHandler.java │ │ │ ├── ResultCenter.java │ │ │ ├── StateManagerHandler.java │ │ │ ├── TaskCenter.java │ │ │ ├── TaskManagerHandler.java │ │ │ ├── TaskQueueHandler.java │ │ │ ├── TaskStateHandler.java │ │ │ ├── UrlSaveHandler.java │ │ │ └── dao │ │ │ ├── ConversationDao.java │ │ │ ├── LogDao.java │ │ │ └── TaskDao.java │ └── plugins │ │ ├── bbs.xmfish.com.xml │ │ ├── category.dangdang.com.xml │ │ ├── dmall │ │ └── dangdang │ │ │ ├── DangdangComment.java │ │ │ └── DangdangCommentFisrt.java │ │ ├── jd.xml │ │ ├── music │ │ └── fivend │ │ │ └── FivendMusicDownload.java │ │ ├── product.dangdang.com.xml │ │ ├── tet.xml │ │ ├── www.5nd.com.xml │ │ ├── www.haha365.com.xml │ │ ├── www.lz13.cn.xml │ │ ├── www.qhwh.com.xml │ │ └── www.weixinso.com.xml ├── resources │ ├── allAgentsHeader │ ├── config │ │ └── config.ini │ ├── log4j.properties │ └── xml-html └── webapp │ ├── index.jsp │ ├── managerTask-e.jsp │ ├── managerTask.jsp │ ├── needRunningUrl.jsp │ ├── runningTask.jsp │ ├── runningUrl.jsp │ └── taskState.jsp └── test └── java └── com └── zhangwoo └── spider └── client └── analyse └── XmlAnalyser.java /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/README.md -------------------------------------------------------------------------------- /db.sql: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/db.sql -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/pom.xml -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/client/process/AnalyserTemplate.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/client/process/AnalyserTemplate.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/client/process/ClientMessageCenter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/client/process/ClientMessageCenter.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/client/process/ScriptEngineTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/client/process/ScriptEngineTest.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/client/process/SpiderProcess.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/client/process/SpiderProcess.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/client/process/SpiderThread.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/client/process/SpiderThread.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/client/process/TaskClientHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/client/process/TaskClientHandler.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/client/process/XmlAnalyserTemplate.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/client/process/XmlAnalyserTemplate.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/common/BloomFilter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/common/BloomFilter.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/common/MessageClientCoder.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/common/MessageClientCoder.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/common/MessageServerCoder.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/common/MessageServerCoder.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/po/Conversation.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/po/Conversation.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/po/Entity.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/po/Entity.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/po/Task.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/po/Task.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/po/TaskState.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/po/TaskState.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/po/UrlRequest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/po/UrlRequest.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/po/UrlState.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/po/UrlState.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/ConversationSaveHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/ConversationSaveHandler.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/ResultCenter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/ResultCenter.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/StateManagerHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/StateManagerHandler.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/TaskCenter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/TaskCenter.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/TaskManagerHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/TaskManagerHandler.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/TaskQueueHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/TaskQueueHandler.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/TaskStateHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/TaskStateHandler.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/UrlSaveHandler.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/UrlSaveHandler.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/dao/ConversationDao.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/dao/ConversationDao.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/dao/LogDao.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/dao/LogDao.java -------------------------------------------------------------------------------- /src/main/java/com/zhangwoo/spider/server/dao/TaskDao.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/com/zhangwoo/spider/server/dao/TaskDao.java -------------------------------------------------------------------------------- /src/main/java/plugins/bbs.xmfish.com.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/bbs.xmfish.com.xml -------------------------------------------------------------------------------- /src/main/java/plugins/category.dangdang.com.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/category.dangdang.com.xml -------------------------------------------------------------------------------- /src/main/java/plugins/dmall/dangdang/DangdangComment.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/dmall/dangdang/DangdangComment.java -------------------------------------------------------------------------------- /src/main/java/plugins/dmall/dangdang/DangdangCommentFisrt.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/dmall/dangdang/DangdangCommentFisrt.java -------------------------------------------------------------------------------- /src/main/java/plugins/jd.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/jd.xml -------------------------------------------------------------------------------- /src/main/java/plugins/music/fivend/FivendMusicDownload.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/music/fivend/FivendMusicDownload.java -------------------------------------------------------------------------------- /src/main/java/plugins/product.dangdang.com.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/product.dangdang.com.xml -------------------------------------------------------------------------------- /src/main/java/plugins/tet.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/tet.xml -------------------------------------------------------------------------------- /src/main/java/plugins/www.5nd.com.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/www.5nd.com.xml -------------------------------------------------------------------------------- /src/main/java/plugins/www.haha365.com.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/www.haha365.com.xml -------------------------------------------------------------------------------- /src/main/java/plugins/www.lz13.cn.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/www.lz13.cn.xml -------------------------------------------------------------------------------- /src/main/java/plugins/www.qhwh.com.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/www.qhwh.com.xml -------------------------------------------------------------------------------- /src/main/java/plugins/www.weixinso.com.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/java/plugins/www.weixinso.com.xml -------------------------------------------------------------------------------- /src/main/resources/allAgentsHeader: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/resources/allAgentsHeader -------------------------------------------------------------------------------- /src/main/resources/config/config.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/resources/config/config.ini -------------------------------------------------------------------------------- /src/main/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/resources/log4j.properties -------------------------------------------------------------------------------- /src/main/resources/xml-html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/resources/xml-html -------------------------------------------------------------------------------- /src/main/webapp/index.jsp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/webapp/index.jsp -------------------------------------------------------------------------------- /src/main/webapp/managerTask-e.jsp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/webapp/managerTask-e.jsp -------------------------------------------------------------------------------- /src/main/webapp/managerTask.jsp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/webapp/managerTask.jsp -------------------------------------------------------------------------------- /src/main/webapp/needRunningUrl.jsp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/webapp/needRunningUrl.jsp -------------------------------------------------------------------------------- /src/main/webapp/runningTask.jsp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/webapp/runningTask.jsp -------------------------------------------------------------------------------- /src/main/webapp/runningUrl.jsp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/webapp/runningUrl.jsp -------------------------------------------------------------------------------- /src/main/webapp/taskState.jsp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/main/webapp/taskState.jsp -------------------------------------------------------------------------------- /src/test/java/com/zhangwoo/spider/client/analyse/XmlAnalyser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matuobasyouca/spider/HEAD/src/test/java/com/zhangwoo/spider/client/analyse/XmlAnalyser.java --------------------------------------------------------------------------------