📄 channelparser.java
字号:
package cn.myvideosite.exe.parser;
import java.util.ArrayList;
import java.util.List;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.AndFilter;
import org.htmlparser.filters.HasAttributeFilter;
import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;
import cn.myvideosite.commons.Constant;
import cn.myvideosite.data.model.bean.ChannelClass;
import cn.myvideosite.data.model.services.ChannelService;
import cn.myvideosite.util.HttpUtil;
public class ChannelParser {
/**
* 定义<div id="ListTags">标签过滤器常量 抓取56频道首页的所有频道名html代码
* 根据div
*/
private static final NodeFilter FILTER_DIV_LISTTAGS=
new AndFilter(new TagNameFilter("div"),new HasAttributeFilter("id","ListTags"));
/**
* <div class="Tag2">
*
*/
private static final NodeFilter FILTER_DIV_TAG2=
new AndFilter(new TagNameFilter("div"),new HasAttributeFilter("class","Tag2"));
/**
* A标签
*/
//private static final NodeFilter FILTER_DIV_LI=new TagNameFilter("li");
/**
* <a></a>抓取连接 A标签
*/
private static final NodeFilter FILTER_DIV_A=new TagNameFilter("a");
public static ChannelClass parser(String url){
String page=HttpUtil.request(url, Constant.CHARSET_GB2312);
Parser pageParser=Parser.createParser(page,Constant.CHARSET_GB2312);
ChannelClass channelclass=null;
try {
NodeList nl=pageParser.parse(FILTER_DIV_LISTTAGS);
pageParser=Parser.createParser(nl.toHtml(), Constant.CHARSET_GB2312);
NodeList tag2NL=pageParser.parse(FILTER_DIV_TAG2);
if(tag2NL!=null && tag2NL.size()>0){
for(int i=0;i<tag2NL.size();i++){
Node tag2Node=tag2NL.elementAt(i);
pageParser=Parser.createParser(tag2Node.toHtml(), Constant.CHARSET_GB2312);
NodeList aNL=pageParser.parse(FILTER_DIV_A);
if(aNL!=null && aNL.size()>0){
List<ChannelClass> list =new ArrayList<ChannelClass>(aNL.size());
for(int ia=0;ia<aNL.size();ia++){
LinkTag link=(LinkTag)aNL.elementAt(ia);
System.out.println(link.getLinkText());
channelclass=new ChannelClass();
channelclass.setChannelName(link.getLinkText());
list.add(channelclass);
}
ChannelService.save(list);
}
}
}
} catch (ParserException e) {
e.printStackTrace();
}
return channelclass;
}
public static void main(String[] args){
parser("http://www.56.com/w/show_channel.phtml");
}
}
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -