Description: Web crawler to complete the page resolution, can extract the desired content, use technology jsoup,
To Search:
File list (Check if you may need any files):
Parse\.classpath
.....\.project
.....\.settings\org.eclipse.jdt.core.prefs
.....\Analysis.xls
.....\bin\analysis\Analysis.class
.....\...\........\AnalysisJsoup.class
.....\...\........\MkDir.class
.....\...\........\ToExcel.class
.....\...\com\Convert.class
.....\...\...\EffectiveHref.class
.....\...\...\FileInLine.class
.....\...\...\FileOut.class
.....\...\...\HttpConnect.class
.....\...\host\Host.class
.....\...\....\JsoupHost.class
.....\...\post\HtmlParser.class
.....\...\....\JsoupHtml.class
.....\...\test\AstroExtractTest.class
.....\...\....\FilterTest.class
.....\...\....\Next.class
.....\...\....\ReadFromFile.class
.....\...\....\SimpleRegex.class
.....\...\....\TM.class
.....\...\....\TYExtractor.class
.....\...\url\Href.class
.....\...\...\MyMain.class
.....\...\visited\UrlWrite.class
.....\...\.......\Visited.class
.....\...\wap\HostId.class
.....\...\...\HostMain.class
.....\...\...\InitId.class
.....\...\...\JsoupWapHost.class
.....\...\...\WapIdList.class
.....\develop.xls
.....\feeling.xls
.....\free.xls
.....\funinfo.xls
.....\lib\commons-httpclient-3.1.jar
.....\...\commons-io-1.4.jar
.....\...\commons-logging-1.1.1.jar
.....\...\filterbuilder.jar
.....\...\htmllexer.jar
.....\...\htmlparser.jar
.....\...\jsoup-1.7.1.jar
.....\...\org.apache.httpcomponents.httpclient_4.2.1.jar
.....\...\org.apache.httpcomponents.httpcore_4.2.1.jar
.....\...\poi-3.9-20121203.jar
.....\...\sitecapturer.jar
.....\...\thumbelina.jar
.....\post-develop\HrefList.txt
.....\............\Visited.txt
.....\.....feeling\HrefList.txt
.....\............\Visited.txt
.....\......ree\HrefList.txt
.....\.........\Visited.txt
.....\......uninfo\HrefList.txt
.....\............\Visited.txt
.....\.....id\Id.txt
.....\.......\IdList.txt
.....\.......\Visited.txt
.....\.....worldlook\HrefList.txt
.....\..............\Visited.txt
.....\src\analysis\Analysis.java
.....\...\........\AnalysisJsoup.java
.....\...\........\MkDir.java
.....\...\........\ToExcel.java
.....\...\com\Convert.java
.....\...\...\EffectiveHref.java
.....\...\...\FileInLine.java
.....\...\...\FileOut.java
.....\...\...\HttpConnect.java
.....\...\host\Host.java
.....\...\....\JsoupHost.java
.....\...\post\HtmlParser.java
.....\...\....\JsoupHtml.java
.....\...\test\AstroExtractTest.java
.....\...\....\Filename.java
.....\...\....\FilterTest.java
.....\...\....\Next.java
.....\...\....\ReadFromFile.java
.....\...\....\SimpleRegex.java
.....\...\....\TM.java
.....\...\....\TYExtractor.java
.....\...\url\Href.java
.....\...\...\MyMain.java
.....\...\visited\UrlWrite.java
.....\...\.......\Visited.java
.....\...\wap\HostId.java
.....\...\...\HostMain.java
.....\...\...\InitId.java
.....\...\...\JsoupWapHost.java
.....\...\...\WapIdList.java
.....\worldlook.xls
.....\bin\analysis
.....\...\com
.....\...\host
.....\...\post
.....\...\test
.....\...\url
.....\...\visited