Я пытаюсь решить это упражнение:
а) Перейдите на страницу https://datatables.net/, введя "datatables" в поиске Google и нажав кнопку правильный результат.
б) Вы найдете пример таблицы с некоторыми данными. Пожалуйста, извлеките/извлеките данные из таблицы в массив. В массиве у вас будут объекты. Объект будет строкой из таблицы. Свойства объекта будут представлять собой данные из каждого столбца таблицы.
c) Экспортируйте массив в формате CSV.
Поскольку я никогда не работал с кошмаром.js, я погуглил и нашел именно то, что мне нужно https://github.com/XanderGriff/webscraping-with-nightmare/blob/master/main.mjs , но в начале не работало и я немного меняю код, но все же есть ошибка.
// Package Definitions
var csvWriter = require('csv-write-stream');
var fs = require('fs');
var Nightmare = require('nightmare');
// Constant Definitions
const GOOGLE = 'https://www.google.com';
const QUERY = 'datatables';
const SEARCHBAR = 'form[action*="/search"] [name=q]';
const SEARCHBUTTON = 'form[action*="/search"] [type=submit]';
const SEARCH_RESULT_ID = 'h3.r > a';
const DATATABLES_LINK = 'https://datatables.net/';
const DATATABLES_SIZE_SELECTOR = 'select[name="example_length"]';
const DATATABLES_DATA_SELECTOR = 'table#example tr';
(async ()=>{
let nightmare;
try {
nightmare = Nightmare({ show: true });
await nightmare
// Navigate to Google
.goto(GOOGLE)
.type(SEARCHBAR, QUERY)
.click(SEARCHBUTTON)
.wait(SEARCH_RESULT_ID)
await nightmare.evaluate( (SEARCH_RESULT_ID,
DATATABLES_LINK) => {
// filter results based on css selectors to choose link with
proper url
// indexed at 0 to access element from single-element array
produced in above instruction
(Array.from(document.querySelectorAll(SEARCH_RESULT_ID))).filter(a
=> a.href === DATATABLES_LINK)[0].click();
}, SEARCH_RESULT_ID, DATATABLES_LINK)
// Adjust datatable to show all entries
await nightmare
.wait(DATATABLES_SIZE_SELECTOR)
.select(DATATABLES_SIZE_SELECTOR, 100);
// Retrieve values from datatable
await nightmare.evaluate( (DATATABLES_DATA_SELECTOR) => {
let table_rows =
Array.from(document.querySelectorAll(DATATABLES_DATA_SELECTOR));
// delineate between keys and vals from retrieved table data
let table_keys_row =
Array.from((table_rows[0]).querySelectorAll('th')).map(e =>
e.innerHTML); //array of strings
let table_data_rows = table_rows.slice(1,58); //array
of arrays of HTML elements
let array_of_row_objects = [];
let row_object = {};
let formatted_values = [];
table_data_rows.forEach( row => {
// grab innerHTML from each element in the row
formatted_values =
Array.from(row.querySelectorAll('td')).map(e => e.innerHTML);
// place each of the element values in an object with each value
associated with its respective key
row_object = {};
for(i = 0; i < table_keys_row.length; i++) {
row_object[table_keys_row[i]] =
formatted_values[i];
}
array_of_row_objects.push(row_object);
})
return array_of_row_objects;
}, DATATABLES_DATA_SELECTOR)
// Write to CSV
writer.pipe(fs.createWriteStream('output.csv'));
result.forEach( obj => {
writer.write(obj);
});
writer.end();
console.log("Wrote values to CSV...")
} catch (error) {
console.error(error);
throw error;
} finally {
await nightmare.end();
}
})();
Я запускаю код с DEBUG=nightmare и получаю это:
nightmare queuing process start +0ms
nightmare queueing action "goto" for https://www.google.com +3ms
nightmare queueing action "type" +0ms
nightmare queueing action "click" +0ms
nightmare queueing action "wait" +0ms
nightmare running +1ms
nightmare queueing action "evaluate" +5s
nightmare running +1ms
{ TypeError: Cannot read property 'click' of undefined
at fn (<anonymous>:8:106)
at javascript (<anonymous>:23:21)
at <anonymous>:38:3
at EventEmitter.electron.ipcRenderer.on
(/home/anna/automation/node_modules/electron/dist/resources/electron.a
sar/renderer/web-frame-init.js:36:30)
at emitMany (events.js:147:13)
at EventEmitter.emit (events.js:224:7) code: -1 }
nightmare running +12ms
nightmare electron child process exited with code 0: success!
+55ms
(node:10610) UnhandledPromiseRejectionWarning: TypeError: Cannot
read property 'click' of undefined
at fn (<anonymous>:8:106)
at javascript (<anonymous>:23:21)
at <anonymous>:38:3
at EventEmitter.electron.ipcRenderer.on
(/home/anna/automation/node_modules/electron/dist/resources/electron.
asar/renderer/web-frame-init.js:36:30)
at emitMany (events.js:147:13)
at EventEmitter.emit (events.js:224:7)
(node:10610) UnhandledPromiseRejectionWarning: Unhandled promise
rejection. This error originated either by throwing inside of an
async function without a catch block, or by rejecting a promise
which was not handled with .catch(). (rejection id: 1)
(node:10610) [DEP0018] DeprecationWarning: Unhandled promise
rejections are deprecated. In the future, promise rejections that
are not handled will terminate the Node.js process with a non-zero
exit code.
Если кто-то знает или сталкивался с этой проблемой, помогите разобраться.