有一个website,我试图从JSoup库中获取信息。问题在于响应中仅页面的一部分。
这是我的代码:
Connection.Response loginForm = Jsoup.connect(
String.format("https://student.utm.utoronto.ca/timetable/timetable?yos=%s&session=20199", i))
.userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36")
.method(Connection.Method.GET)
.timeout(600000)
.header("Accept-Encoding", "gzip, deflate, br")
.header("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9")
.header("Accept-Language", "en-US,en;q=0.9,fr;q=0.8")
.header("Cache-Control","max-age=0")
.header("Connection", "keep-alive")
.header("Host", "student.utm.utoronto.ca")
.header("Sec-Fetch-Mode","navigate")
.execute();
我尝试从浏览器的请求标头中复制尽可能多的标头。
我怀疑最初加载页面后运行了javascript,这就是为什么我没有在响应中得到整个页面的原因。
这是带有tr
标签的最后一个元素:
<tr id="tr_MAT102H5FTUT0125" class=" TUT W1 meeting_section OL0 todAft">
<td> </td>
<td> <label for="MAT102H5FTUT0125">TUT0125</label> </td>
<td class="instrTD"> </td>
<td class="hideEnrolTD"> 29 </td>
<td class="hideEnrolTD"> 35 </td>
<td class="hideEnrolTD"> 0 </td>
<td class="enrolTD"> 29/35, wait:0 </td>
<td> <abbr title="Wednesday">WE</abbr><br> </td>
<td class="start_time"> 13:00<br> </td>
<td> 14:00<br> </td>
<td> MN 2100<br> </td>
<td class="noteTD"> </td>
<td class="text-right">
<!-- <input type='checkbox' name='courses' id='$checkbox_id' value='MAT102H5F-TUT0125-313:0014:00' aria-label='MAT102H5F TUT0125' /> --> <button name="courses" id="MAT102H5FTUT0125" value="MAT102H5F-TUT0125-313:0014:00" onclick="addCourse($(this))" aria-label="MAT102H5F TUT0125" class="addButton btn btn-sm btn-primary"><span class="glyphicon glyphicon-plus"></span><span class="button-text"> Add to Plan</span></button> </td>
</tr>
<tr id="tr_MAT102H5FTUT0126" class=" TUT W1 meeting_section OL0 todAft">
<td> </td>
<td> <label for="MAT102H5FTUT0126">TUT0126</label> </td> <
</tr>
</tbody>
</table>
</div>
</div>
</body>
</html>
我希望最后一个tr
标记表示页面中加载的最后一个表,即课程WGS102H5S
而不是MAT102H5F
。
不确定这是否有用,但是我目前正在android studio中进行编程。
JSoup中对此有任何修复程序吗?如果没有,我应该使用更好的库吗?
答案 0 :(得分:0)
将const subBtn = document.getElementById("btn");
const inptTxt = document.getElementById("text");
const contDiv = document.getElementById("container");
//check input box is empty or not and enable Colorize button
subBtn.disabled = true
// FIX: make a dedicated function for validation
function validateInput() {
const value = inptTxt.value.trim()
if (value) {
inptTxt.dataset.state = 'valid'
subBtn.disabled = false
} else {
inptTxt.dataset.state = 'invalid'
subBtn.disabled = true
}
}
// FIX: call the validation function when the input is changed
inptTxt.addEventListener('input', validateInput);
var xhttp = new XMLHttpRequest();
subBtn.addEventListener("click", function () {
xhttp.onload = function () {
var crd = document.createElement("div");
var div = contDiv.getElementsByTagName("div");
var crdCount = div.length;
crd.setAttribute("id", "card" + crdCount);
crd.innerHTML = inptTxt.value;
//change html title with input text
document.title = inptTxt.value;
contDiv.appendChild(crd);
document.getElementById("card" + crdCount).style.background = JSON.parse(this.responseText).color;
//getting inverse value of hex color
const inv = (hex) => '#' + hex.match(/[a-f0-9]{2}/ig).map(e => (255 - parseInt(e, 16) | 0).toString(16).replace(/^([a-f0-9])$/, '0$1')).join('')
const invert = () =>
document.querySelectorAll('circle')
.forEach(c =>
(hex = c.getAttribute('fill')) &&
c.setAttribute('fill', inv(hex))
)
var invColor = inv(JSON.parse(this.responseText).color);
//setting the inverse value to card text
var crdText = document.getElementById("card" + crdCount).innerHTML;
var setColor = "<span style='color:" + invColor + "'>" + crdText + "</span>";
document.getElementById("card" + crdCount).innerHTML = setColor;
//clear input and refocus
inptTxt.value = "";
inptTxt.focus();
inptTxt.select();
// FIX: call the validation function when the input is cleared
validateInput();
};
xhttp.onerror = function () {
var crd = document.createElement("div");
var div = contDiv.getElementsByTagName("div");
var crdCount = div.length;
crd.setAttribute("id", "card" + crdCount);
crd.innerHTML = inptTxt.value;
//change html title with input text
document.title = inptTxt.value;
contDiv.appendChild(crd);
document.getElementById("card" + crdCount).style.background = "#6d4298";
var crdText = document.getElementById("card" + crdCount).innerHTML;
var setColor = "<span style='color:#ffffff'>" + crdText + "</span>";
document.getElementById("card" + crdCount).innerHTML = setColor;
};
xhttp.open("GET", "http://api.creativehandles.com/getRandomColor");
xhttp.send();
})
//submit quote using Enter key
inptTxt.addEventListener("keyup", function (event) {
if (event.keyCode === 13) {
event.preventDefault();
subBtn.click();
}
});
更改为.execute();
https://jsoup.org/apidocs/org/jsoup/Connection.html#maxBodySize-int-
https://jsoup.org/apidocs/org/jsoup/Connection.Response.html#bufferUp--