转载:
https://www.javatpoint.com/jsoup-examples
Get title of URL
Document doc = Jsoup.connect("http://www.javatpoint.com").get();
String title = doc.title();
Get title from HTML file
Document doc = Jsoup.parse(new File("e:\\register.html"),"utf-8");//assuming register.html file in e drive
String title = doc.title();
Get total links of URL
Document doc = Jsoup.connect("http://www.javatpoint.com").get();
Elements links = doc.select("a[href]");
for (Element link : links) {
System.out.println("\nlink : " + link.attr("href"));
System.out.println("text : " + link.text());
}
Get meta information of URL
Document doc = Jsoup.connect("http://www.javatpoint.com").get();
String keywords = doc.select("meta[name=keywords]").first().attr("content");
System.out.println("Meta keyword : " + keywords);
String description = doc.select("meta[name=description]").get(0).attr("content");
System.out.println("Meta description : " + description);
Get total images of URL
Document doc = Jsoup.connect("http://www.javatpoint.com").get();
Elements images = doc.select("img[src~=(?i)\\.(png|jpe?g|gif)]");
for (Element image : images) {
System.out.println("src : " + image.attr("src"));
System.out.println("height : " + image.attr("height"));
System.out.println("width : " + image.attr("width"));
System.out.println("alt : " + image.attr("alt"));
}
Get form parameters
Document doc = Jsoup.parse(new File("e:\\register.html"),"utf-8");
Element loginform = doc.getElementById("registerform");
Elements inputElements = loginform.getElementsByTag("input");
for (Element inputElement : inputElements) {
String key = inputElement.attr("name");
String value = inputElement.attr("value");
System.out.println("Param name: "+key+" \nParam value: "+value);
}