使用Jsoup解析HTML和文档

      对不需要登陆的网页或者已经获得到的文档的解析可以使用Jsoup，Jsoup提供了相应的API供我们使用。

    Jsoup的官方文档 http://www.open-open.com/jsoup/

    下面是Jsoup的操作，使用见注释

 

  

package Jsoup_SWPU;

import java.io.File;
import java.io.IOException;

import org.jsoup.Jsoup;
import org.jsoup.helper.Validate;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.jsoup.select.Evaluator.Id;

public class Spider {
	public static void main(String[] args) throws IOException {
		Validate.isTrue(args.length == 1, "usage: supply url to fetch");
		String url = args[0];
		print("Fetching %s...", url);
		try {
			Document doc = Jsoup.connect(url).get();
			/*
			 * File in = new File("F:/hao123.html"); Document doc =
			 * Jsoup.parse(in, "UTF-8", "http://www.hao123.com/");
			 */

			// Elements link = doc.select("a[href]");
			Elements links = doc.select("a[href]"); // a是标签，href是属性，属性用方括号
			Elements element = doc.select("div");
			Elements media = doc.select("img[src]");
			Elements imports = doc.select("link[href]");
			Elements classElements = doc.select("div[class]"); // select()返回的是Elements，再对它里的属性进行检索
			print("\nMedia: (%d)", media.size());
			for (Element src : media) {
				/*
				 * if (src.tagName().equals("img"))
				 * print(" * %s: <%s> %sx%s (%s)", src.tagName(),
				 * src.attr("abs:src"), src.attr("width"), src.attr("height"),
				 * trim(src.attr("alt"), 20)); //attr获取属性值，也可以给属性赋值 else
				 * print(" * %s: <%s>", src.tagName(), src.attr("abs:src"));
				 */
			}

			print("\nDiv", element.size());

			for (Element divElement : element) {
				// print(" * %s <%s> (%s)",
				// divElement.tagName(),divElement.attr("id"),
				// divElement.attr("class"));
			}

			print("\nImports: (%d)", imports.size());
			for (Element link : imports) {
				print(" * %s <%s> (%s)", link.tagName(), link.attr("abs:href"),
						link.attr("rel"));
			}

			print("\nLinks: (%d)", links.size());
			print("test a link:<%s>\n", links.last().attr("abs:href"));
			print("the next page:<%s>",
					Jsoup.connect(links.last().attr("abs:href")).get().text());
			for (Element link : links) {
				// print(" * a: <%s>  (%s)", link.attr("abs:href"),
				// trim(link.text(), 35));
				// print("data is :{%s} ", link.data());
				// print("html is:[%s]", link.html());

			}

			print("\nClasses:(%d)", classElements.size());
			for (Element classes : classElements) {
				// print(" * c :<%s>  (%s)",
				// classes.attr("class"),classes.getElementsByIndexEquals(0).text());
			} // 获取它的内容
			System.out
					.println("link size is:" + links.size()
							+ ";import size is:" + imports.size()
							+ ";media size is:" + media.size()
							+ ";classes size is:" + classElements.size());

		} catch (Exception e) {
			// TODO: handle exception
			System.out.println(e.getMessage());
		}
	}

	private static void print(String msg, Object... args) {
		System.out.println(String.format(msg, args));
	}

	private static String trim(String s, int width) {
		if (s.length() > width)
			return s.substring(0, width - 1) + ".";
		else
			return s;
	}

}

 

要注意的是元素