Example
String html = "<!DOCTYPE html>" +
"<html>" +
"<head>" +
"<title>Hello world!</title>" +
"</head>" +
"<body>" +
"<h1>Hello there!</h1>" +
"<p>First paragraph</p>" +
"<p class=\"not-first\">Second paragraph</p>" +
"<p class=\"not-first third\">Third <a href=\"page.html\">paragraph</a></p>" +
"</body>" +
"</html>";
// Parse the document
Document doc = Jsoup.parse(html);
// Get document title
String title = doc.select("head > title").first().text();
System.out.println(title); // Hello world!
Element firstParagraph = doc.select("p").first();
// Get all paragraphs except from the first
Elements otherParagraphs = doc.select("p.not-first");
// Same as
otherParagraphs = doc.select("p");
otherParagraphs.remove(0);
// Get the third paragraph (second in the list otherParagraphs which
// excludes the first paragraph)
Element thirdParagraph = otherParagraphs.get(1);
// Alternative:
thirdParagraph = doc.select("p.third");
// You can also select within elements, e.g. anchors with a href attribute
// within the third paragraph.
Element link = thirdParagraph.select("a[href]");
// or the first <h1> element in the document body
Element headline = doc.select("body").first().select("h1").first();
You can find a detailed overview of supported selectors here.
