首先,这需要JSoup。
try {
// Regexp pattern used to strip the links
Pattern p = Pattern.compile("\'([^\']*)\'");
// First, let's find the IFRAME from the main page
Document doc = Jsoup.connect("http://blich.co.il/timetable-shahaf").get();
Elements iframe = doc.select("iframe");
if (!iframe.isEmpty()) {
String src = iframe.get(0).absUrl("src");
if (!TextUtils.isEmpty(src)) {
// Now we need to fetch the contents of the IFRAME
doc = Jsoup.connect(src).get();
// This is where we manipulate the <select ..> statement. There's only
// one on this page, so this will be done quick and dirty
Elements selects = doc.select("select.HeaderClasses");
Elements options = selects.select("option");
if (!options.isEmpty()) {
// There's a lot of options here.. dunno what they mean, so let's just
// select a **random** and go with that. Your code should probably let the user
// choose from a dialog or something.
Collections.shuffle(options);
Element option = options.get(0);
String name=selects.get(0).attr("name");
if (!TextUtils.isEmpty(name)) {
doc = Jsoup.connect(src)
.data("__EVENTTARGET", name)
.data("__EVENTARGUMENT", "")
.data(name, option.attr("value")) // Add random option value
.data("__VIEWSTATE",
doc.select("input#__VIEWSTATE").attr("value"))
.data("__LASTFOCUS", "")
.post();
}
}
// All the relevant links are stored in a td with the class "HeaderCell"
Elements links = doc.select("td.HeaderCell a");
for (Element link : links) {
// These are all links to a silly java-script method, _doPostBack(..)
// function __doPostBack(eventTarget, eventArgument) {
// if (!theForm.onsubmit || (theForm.onsubmit() != false)) {
// theForm.__EVENTTARGET.value = eventTarget;
// theForm.__EVENTARGUMENT.value = eventArgument;
// theForm.submit();
// }
// }
// The important bits appear to be eventTarget and eventArgument at least,
// but none of the links define an eventArgument in any case - so we just
// need "eventTarget".
// Naïve splitting, take the first quoted string
Matcher m = p.matcher(link.attr("href"));
if (m.find()) {
String eventTarget = m.group(1);
// The eventTarget you're looking for ends with 'ChangesTable'
if (eventTarget != null && eventTarget.endsWith("ChangesTable")) {
// Now we need to do a POST :-D - this API requires us to retain
// __VIEWSTATE - so we need to post that to.
doc = Jsoup.connect(src)
.data("__EVENTTARGET", eventTarget)
.data("__EVENTARGUMENT", "")
.data("__VIEWSTATE",
doc.select("input#__VIEWSTATE").attr("value"))
.data("__LASTFOCUS", "")
.post();
// All the lesson information is stored in a div with the class
// TTLesson, so let's select those
Elements lessons = doc.select("div.TTLesson");
if (lessons.isEmpty()) {
Log.w(TAG, "Unable to list any lessons");
} else {
for (Element lesson : lessons) {
// This is were knowledge of Hebrew would come in handy -
// but this will list all lessons. You should be able
// to figure out how to find the one you want.
System.out.println(lesson);
}
}
}
}
}
} else {
Log.w(TAG, "Unable to find iframe src");
}
} else {
Log.w(TAG, "Unable to find iframe");
}
} catch (IOException e) {
Log.w(TAG, "Error reading timetable", e);
}
这将列出您想要的页面上的所有课程。由于我不知道足够的希伯来语来辨别任何单元格包含什么,所以我会留下找到正确的教训。
编辑:现在这个例子会在<中选择一个选项>并刷新页面。
如果您要附加页面的URL,将会更容易帮助您。 – Jens 2012-08-15 12:52:36
http://blich.co.il/timetable-shahaf 这是在希伯来语,所以你不会理解xD – 2012-08-15 12:54:13
好吧,HTML是幸运的不是写在希伯来=) - 对于初学者来说,该页面包含一个IFRAME,其中包含的东西你在之后。 – Jens 2012-08-15 13:03:44