绿盟扫描报告信息提取

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
package com.zgs.look;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.util.HashMap;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.tags.TableTag;
import org.htmlparser.util.NodeList;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class HtmlLook {
	private static String ENCODE = "UTF-8";
	
	public static void main(String[] args) {
		String szContent = openFile( "d:/index.html");
		try {
			Document doc = Jsoup.parse(szContent);
			Elements elList=doc.getElementsByAttributeValue("id","vulDataTable");
			szContent=elList.outerHtml();
			Parser parser = Parser.createParser(szContent, ENCODE);
			NodeFilter[]  filters = new NodeFilter[2];
	        filters[0] = new NodeClassFilter(TableTag.class); 
	        filters[1] = new NodeClassFilter(LinkTag.class);
			NodeFilter filter =new OrFilter (filters);
	        NodeList list = parser.extractAllNodesThatMatch(filter);
	        String ldName="";String ldJianjie="";
	        for (int i = 0; i < list.size(); i++) {    
	        	Node node =  list.elementAt(i);  
	        	if(node instanceof LinkTag){
	        		String nodeHtml=node.toHtml();
	        		if(nodeHtml.contains("onclick")&&nodeHtml.contains("vul-")){
	        			if(!"".equals(ldName)&&!"".equals(ldJianjie)){
	        				//提交数据
	        				System.out.println("---commit---漏洞名称-------"+ldName);
		        			System.out.println("---commit---漏洞简介-------"+ldJianjie);
		        			ldName="";ldJianjie="";
	        			}
	        			String level="";
	        			if(nodeHtml.contains("vul-vh")){
	        				level="高危漏洞";
	        			}else if(nodeHtml.contains("vul-vm")){
	        				level="中危漏洞";
	        			}else if(nodeHtml.contains("vul-vl")){
	        				level="低危漏洞";
	        			}
	        			ldName=getLinkTagContent(nodeHtml)+"-----"+level+"------";
//	        			System.out.println("---漏洞名称-----"+getLinkTagContent(nodeHtml)+"-----"+level+"------");
	        		}
	        	}else{
	        		ldJianjie=getTableTagContent(node.toHtml());
	        	}
	        }  
	        
	        
		} catch (Exception e) {
            e.printStackTrace();
		}
	}
    /**
     * 提取文件里面的文本信息
     * @param szFileName
     * @return
     */
	public static String openFile(String szFileName) {
		try {
			BufferedReader bis = new BufferedReader(new InputStreamReader(new FileInputStream(new File(szFileName)), ENCODE));
			String szContent = "";
			String szTemp;

			while ((szTemp = bis.readLine()) != null) {
				szContent += szTemp + "n";
			}
			bis.close();
			return szContent;
		} catch (Exception e) {
			return "";
		}
	}
	/**
	 * 提取标签<a>a</a>内的内容
	 * return a;
	 */
	public static String getLinkTagContent(String link){
		String content="";
		Pattern pattern = Pattern.compile("<a[^>]*>(.*?)</a>");
		Matcher matcher = pattern.matcher(link);
		if(matcher.find()){
			content=matcher.group(1);
		}
		return content;
	}
	/**
	 * 解析Table标签内的东西
	 * @param table
	 */
	public static String getTableTagContent(String table){
		Map<String,String> conMap=new HashMap<String,String>();
		String content="";
		Document doc = Jsoup.parse(table);
		Elements elList=doc.getElementsByAttributeValue("class","cmn_table plumb");
		Element el=elList.first();
		Elements trLists = el.select("tr");
		for (int i = 0; i < trLists.size(); i++) {
             Elements tds = trLists.get(i).select("td");
             String key="";String val="";
             for (int j = 0; j < tds.size(); j++) {
                     String text = tds.get(j).text();
                     if(j==0){
                    	 key=text; 
                     }else{
                    	 val=text; 
                     }
             }
             conMap.put(key, val);
             content+="|"+key+"-"+val;
//             System.out.println(key+"-"+val);
		}
		return content;
	}
}