携程城市数据的爬取
public void testJsoup(){
Connection connection = Jsoup.connect("http://hotels.ctrip.com/domestic-city-hotel.html");
connection.header("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36");
try {
Document document = connection.timeout(100000).get();
Elements elements = document.getElementsByClass("pinyin_filter_detail");
//包含所有城市的element
Element element = elements.first();
//拼音首字符
Elements elements1 = element.getElementsByTag("dt");
//拼音首字符下所有城市
Elements elements2 = element.getElementsByTag("dd");
for (int i = 0; i < elements1.size(); i++) {
Element pinyin_element = elements1.get(i);
System.out.println(pinyin_element.html());
Element city_element = elements2.get(i);
Elements links = city_element.children();
for (Element link : links) {
String cityName = link.attr("href");
String text = link.text();
System.out.println(cityName+":" + link.attr("title") + ":" +text);
}
System.out.println("end");
}
} catch (IOException e) {
e.printStackTrace();
}
}