在页面https://www.jogossantacasa.pt/web/Placard/placard上,我正在尝试获取Futebol->...
. 我可以,但这只会在for
循环中刮掉一页。谢谢大家。
public class main {
static List<String> links=new ArrayList<>();
static List<String> ligas=new ArrayList<>();
static String url="https://www.jogossantacasa.pt"; //main link
public static void main(String[] args) {
// TODO Auto-generated method stub
Document doc;
// Here i get the links
try {
doc = Jsoup.connect(url+"/web/Placard/placard").get();
Elements a = doc.getElementsByClass("width9");
boolean qwerty = true;
for(Element ele : a) {
Elements k = ele.select("li");
for(Element d : k)
{
String hj = d.select("a").text();
if(hj.contains("Ténis")) qwerty = false;
if(qwerty) {
if(!hj.contains("Futebol")) {
links.add(d.select("a").attr("href"));
ligas.add(hj);
}
}
}
}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
// Here I try to scrape each country page and error is only the last page is scraped
for(int i = 0 ; i < links.size() ; i++) {
String urlEach=url+links.get(i);
Document docEach;
try {
docEach = Jsoup.connect(urlEach).get();
System.out.println(docEach.toString());
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
相关分类