jsoup 是一款Java 的HTML解析器,可直接解析某个URL地址、HTML文本内容。
请参考:jsoup.org
例如: beanshell 抓取CSDN极客头条内容 soup.bsh
// package org.jsoup.examples; 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 java.io.IOException; /** * closure program to list links from a URL. */ ListLinks() { run(String url){ if(url.length() <10) return; print(url); Document doc = Jsoup.connect(url).get(); Elements links = doc.select("h4 a"); // direct a after h4 print("Links: "+ links.size() +"\n"); for (Element link : links) { print(link.attr("abs:href")); print(link.text()); } } return this; } lslinks = ListLinks(); lslinks.run("http://geek.csdn.net/hot");cmd 运行 java bsh.Interpreter soup.bsh
jsoup: Java HTML 解析器,布布扣,bubuko.com
原文地址:http://blog.csdn.net/belldeep/article/details/25079751