Jsoup Sınıfı - Request and Parse Data in HTML

Maven

Şöyle yaparız

<dependency>
  <groupId>org.jsoup</groupId>
  <artifactId>jsoup</artifactId>
  <version>1.14.3</version>
</dependency>

Jsoup Sınıfı

get metodu

Document döndürür

Örnek

Şöyle yaparız

String url = "https://www.cnn.com/";    
Document doc = Jsoup.connect(url).userAgent("Mozilla/5.0").get();  

//get the whole page
String  html = doc.html();

//get the links on the page
Elements links = doc.select("a[href]");
for (Element link : links) {
  String line = link.attr("href");
  System.out.println(line);           
}

post metodu

Örnek

Şöyle yaparız

String url = "https://httpbin.org/post";            
Document doc = Jsoup.connect(url).ignoreContentType(true).timeout(1000)
  .data("custname", "google")    
  .data("custtel", "234")
  .userAgent("Mozilla/5.0")
  .post();

String str = doc.html();    
System.out.println(html);

Document Sınıfı

getElementsByTag metodu

Örnek

Şöyle yaparız

String url = "https://www.istockphoto.com/stock-illustrations";


Document document = Jsoup.connect(url).userAgent("Mozilla/5.0").get();        
Elements tag = document.getElementsByTag("img");

for (Element link : tag) {
  String imgurl = link.attr("abs:src");
  ... 
}

select metodu

Örnek

Şöyle yaparız

public Set<String> listLinks(String url, boolean includeMedia) throws IOException {
   Document doc = Jsoup.connect(url).get();
   Elements links = doc.select("a[href]");
   Elements imports = doc.select("link[href]");

   Set<String> result = new TreeSet<>(String.CASE_INSENSITIVE_ORDER);
   if(includeMedia) {
       Elements media = doc.select("[src]");
       for (Element src : media) {
           result.add(src.absUrl("src"));
           //result.add(src.attr("abs:src"));
       }
   }

   for (Element link : imports) {
       result.add(link.absUrl("abs:href"));
   }

   for (Element link : links) {
       result.add(link.absUrl("abs:href"));
   }

   return result;
}

text metodu

Html tag'lerini ayıklar. Şöyle yaparız.

String htmlString = "<div class=\"WordSection1\"> <p class=\"MsoNormal\">Hi<br> 
<br> <br> <br> Data is written in this mail.<br> <br> <br> 
<br> <o:p></o:p></p> </div>";

System.out.println(Jsoup.parse(htmlString).text());

Çıktı olarak şunu alırız

Hi Data is written in this mail.