Google 根据标头值返回不同的内容,例如User-Agent
.
public static void main(String... args) throws IOException {
{
System.out.println("-- Default header");
Connection conn = Jsoup.connect("http://www.google.it/");
Document document = conn.get();
{
Elements elems = document.select("input");
System.out.println("input - " + elems.size());
for (Element elem : elems) {
System.out.println("input [" + elem.attributes() + "]");
}
}
{
Elements elems = document.select("button");
System.out.println("button - " + elems.size());
for (Element elem : elems) {
System.out.println("button [" + elem.attributes() + "]");
}
}
}
{
System.out.println("-- Custom header");
Connection conn = Jsoup.connect("http://www.google.it/");
conn.header("User-Agent", "Firefox/20.0");
Document document = conn.get();
{
Elements elems = document.select("input");
System.out.println("input - " + elems.size());
for (Element elem : elems) {
System.out.println("input [" + elem.attributes() + "]");
}
}
{
Elements elems = document.select("button");
System.out.println("button - " + elems.size());
for (Element elem : elems) {
System.out.println("button [" + elem.attributes() + "]");
}
}
{
Element elem = document.select("button#gbqfbb").first();
System.out.println();
System.out.println("button#gbqfbb = " + elem);
}
}
}
输出
-- Default header
input - 7
input [ name="ie" value="ISO-8859-1" type="hidden"]
input [ value="it" name="hl" type="hidden"]
input [ name="source" type="hidden" value="hp"]
input [ autocomplete="off" class="lst" value="" title="Cerca con Google" maxlength="2048" name="q" size="57" style="color:#000;margin:0;padding:5px 8px 0 6px;vertical-align:top"]
input [ class="lsb" value="Cerca con Google" name="btnG" type="submit"]
input [ class="lsb" value="Mi sento fortunato" name="btnI" type="submit" onclick="if(this.form.q.value)this.checked=1; else top.location='/doodles/'"]
input [ type="hidden" id="gbv" name="gbv" value="1"]
button - 0
-- Custom header
input - 4
input [ type="hidden" name="output" value="search"]
input [ type="hidden" name="ie" value="UTF-8"]
input [ type="hidden" name="sclient" value="psy-ab"]
input [ id="gbqfq" class="gbqfif" name="q" type="text" autocomplete="off" value=""]
button - 3
button [ id="gbqfb" aria-label="Cerca con Google" class="gbqfb" name="btnG"]
button [ id="gbqfba" aria-label="Cerca con Google" name="btnK" class="gbqfba"]
button [ id="gbqfbb" aria-label="Mi sento fortunato" name="btnI" class="gbqfba" onclick="if(this.form.q.value)this.checked=1;else window.top.location='/doodles/'"]
button#gbqfbb = <button id="gbqfbb" aria-label="Mi sento fortunato" name="btnI" class="gbqfba" onclick="if(this.form.q.value)this.checked=1;else window.top.location='/doodles/'"><span id="gbqfsb">Mi sento fortunato</span></button>