java+Jsoup 正则过滤html网页标签

[java] view plain copy print ?

1. //门票浏览 url参数 http://www.lvmama.com/dest/lantiancheng
2. public static DataBean getWebData1(String url){
3. DataBean data = null;
4. try {
5. Document docdata = Jsoup.connect(url).timeout(20000).get();
6. String id = ".quick-menu .last a";
7. String city = ".proDetail a";
8. String title = ".proDetail h1";
9. String content = "#Introduction";
10. Elements ele = docdata.select(city);
11. city = (ele.text());
12. ele = docdata.select(title);
13. title = (ele.text()).replace("<", "").replace(">", "").replace("\\/", "");
14. ele = docdata.select(content);
15. content = (ele.text());
16. ele = docdata.select(id);
17. String[] idary = ele.attr("href").split("\\/");
18. id = idary[idary.length-1];
19. String type = "景点门票";
21. List<String> images = new ArrayList<String>();
22. data = new DataBean(id,title,url,content,type,city,images);
23. Dom4jUtil.createFile("data/["+type+"]"+title+".xml", Dom4jUtil.createDocument(data));
25. type = "景点评论";
26. content = ".userComments dl dd:eq(3)";
27. ele = docdata.select(content);
28. content = "";
29. int i = 1;
30. for (Element el : ele) {
31. content += ("|第"+i+":"+el.text());
32. i++;
33. }
34. data = new DataBean(id,title,url,content,type,city,images);
35. //用xml存储数据
36. Dom4jUtil.createFile("data/["+type+"]"+title+".xml", Dom4jUtil.createDocument(data));
37. } catch (Exception e) {
38. e.printStackTrace();
39. }
40. return data;
41. }

//门票浏览  url参数 http://www.lvmama.com/dest/lantiancheng
	public static DataBean getWebData1(String url){
		DataBean data = null;
		try {
			Document docdata = Jsoup.connect(url).timeout(20000).get();
			String id = ".quick-menu .last a";
			String city = ".proDetail a";
			String title = ".proDetail h1";
			String content = "#Introduction";
			Elements ele = docdata.select(city);
			city = (ele.text()); 
			ele = docdata.select(title);
			title = (ele.text()).replace("<", "").replace(">", "").replace("\\/", "");
			ele = docdata.select(content);
			content = (ele.text());
			ele = docdata.select(id);
			String[] idary = ele.attr("href").split("\\/");
			id = idary[idary.length-1];
			String type = "景点门票";

			List<String> images = new ArrayList<String>();
			data = new DataBean(id,title,url,content,type,city,images);
			Dom4jUtil.createFile("data/["+type+"]"+title+".xml", Dom4jUtil.createDocument(data));
			
			type = "景点评论";
			content = ".userComments dl dd:eq(3)";
			ele = docdata.select(content);
			content = "";
			int i = 1;
			for (Element el : ele) {
				content += ("|第"+i+":"+el.text());
				i++;
			}
			data = new DataBean(id,title,url,content,type,city,images);
			//用xml存储数据
			Dom4jUtil.createFile("data/["+type+"]"+title+".xml", Dom4jUtil.createDocument(data));
		} catch (Exception e) {
			e.printStackTrace();
		}
		return data;
	}

整个过程分为几部

1、 获取页面的节点对象

[java] view plain copy print ?

1. Document docdata = Jsoup.connect(url).timeout(20000).get();

Document docdata = Jsoup.connect(url).timeout(20000).get();

2、创建选择器，选择页面节点对象的 text 或 html 。 选择方式跟jquery非常类似。

例如：

String title = ".proDetail h1";

ele = docdata.select(title);

这个就是用来选择 class = proDetail 下 h1 标签的对象。通过 ele.text() 就得到了标签中的文本。

[java] view plain copy print ?

1. Document docdata = Jsoup.connect(url).timeout(20000).get();
2. String id = ".quick-menu .last a";
3. String city = ".proDetail a";
4. String title = ".proDetail h1";
5. String content = "#Introduction";
6. Elements ele = docdata.select(city);
7. city = (ele.text());
8. ele = docdata.select(title);
9. title = (ele.text()).replace("<", "").replace(">", "").replace("\\/", "");
10. ele = docdata.select(content);
11. content = (ele.text());
12. ele = docdata.select(id);
13. String[] idary = ele.attr("href").split("\\/");
14. id = idary[idary.length-1];

Document docdata = Jsoup.connect(url).timeout(20000).get();
			String id = ".quick-menu .last a";
			String city = ".proDetail a";
			String title = ".proDetail h1";
			String content = "#Introduction";
			Elements ele = docdata.select(city);
			city = (ele.text()); 
			ele = docdata.select(title);
			title = (ele.text()).replace("<", "").replace(">", "").replace("\\/", "");
			ele = docdata.select(content);
			content = (ele.text());
			ele = docdata.select(id);
			String[] idary = ele.attr("href").split("\\/");
			id = idary[idary.length-1];

3、通过获取的数据，构造java数据对象 。 然后存入xml或txt文件。 如果有需要也可以存入数据库啦。

[java] view plain copy print ?

1. String type = "景点门票";
3. List<String> images = new ArrayList<String>();
4. data = new DataBean(id,title,url,content,type,city,images);
5. Dom4jUtil.createFile("data/["+type+"]"+title+".xml", Dom4jUtil.createDocument(data));

String type = "景点门票";

			List<String> images = new ArrayList<String>();
			data = new DataBean(id,title,url,content,type,city,images);
			Dom4jUtil.createFile("data/["+type+"]"+title+".xml", Dom4jUtil.createDocument(data));