Compare commits
4 Commits
af4eb5bb88
...
v3
| Author | SHA1 | Date | |
|---|---|---|---|
| f34db1c6e8 | |||
|
e78ee594a0
|
|||
|
16f6eef215
|
|||
|
4a3f1e9f4e
|
913
package-lock.json
generated
913
package-lock.json
generated
File diff suppressed because it is too large
Load Diff
10
package.json
10
package.json
@@ -10,9 +10,13 @@
|
||||
"test": "node tests/test.js",
|
||||
"start": "concurrently \"node server.js\" \"node cron-runner.js\"",
|
||||
"build": "cd web && hugo --gc --minify",
|
||||
"dev-web": "cd web && hugo serve"
|
||||
"dev-web": "cd web && hugo serve",
|
||||
"setup-static": "node scripts/loadstaticschedule.js"
|
||||
},
|
||||
"dependencies": {
|
||||
"@google/genai": "^1.38.0",
|
||||
"axios": "^1.13.4",
|
||||
"axios-cookiejar-support": "^6.0.5",
|
||||
"body-parser": "^2.2.0",
|
||||
"cheerio": "^1.1.2",
|
||||
"concurrently": "^9.2.0",
|
||||
@@ -21,6 +25,8 @@
|
||||
"exceljs": "^4.4.0",
|
||||
"express": "^5.1.0",
|
||||
"node-cron": "^4.2.1",
|
||||
"puppeteer": "^24.10.0"
|
||||
"node-fetch": "^3.3.2",
|
||||
"puppeteer": "^24.10.0",
|
||||
"tough-cookie": "^6.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,7 +13,9 @@
|
||||
*/
|
||||
|
||||
import parseV1V2 from "./parse/v1_v2.js";
|
||||
import parseV3 from "./parse/v3/v3.js";
|
||||
|
||||
export default async function parseThisShit(downloadedFilePath) {
|
||||
await parseV1V2(downloadedFilePath)
|
||||
await parseV1V2(downloadedFilePath);
|
||||
await parseV3("db/v2.json"); // NEEDS TO BE RAN AFTER V2 (uses its format)
|
||||
}
|
||||
|
||||
73
scrape/parse/v3/call.js
Normal file
73
scrape/parse/v3/call.js
Normal file
@@ -0,0 +1,73 @@
|
||||
/*
|
||||
* Copyright (C) 2025 Jakub Žitník
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
* the Free Software Foundation, either version 3 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*/
|
||||
|
||||
import { GoogleGenAI } from "@google/genai";
|
||||
import fs from "fs/promises";
|
||||
|
||||
const TIMETABLE_PATH = "db/persistent/timetables.json";
|
||||
|
||||
export async function setup() {
|
||||
const timetable = JSON.parse(
|
||||
await fs.readFile(TIMETABLE_PATH, { encoding: "utf8" })
|
||||
);
|
||||
|
||||
const ai = new GoogleGenAI({
|
||||
apiKey: process.env.GEMINI_API_KEY
|
||||
});
|
||||
|
||||
const systemPrompt = await fs.readFile("./prompt.txt", "utf-8");
|
||||
|
||||
/**
|
||||
* @param {Object} changesByClass
|
||||
* {
|
||||
* "1A": [ ...changes... ],
|
||||
* "2B": [ ...changes... ]
|
||||
* }
|
||||
* @param {number} dayIndex
|
||||
*/
|
||||
return async (changesByClass, dayIndex) => {
|
||||
const input = {};
|
||||
|
||||
for (const cls of Object.keys(changesByClass)) {
|
||||
input[cls] = {
|
||||
stableSchedule: timetable[cls][dayIndex],
|
||||
changes: changesByClass[cls]
|
||||
};
|
||||
}
|
||||
|
||||
const response = await ai.models.generateContent({
|
||||
model: "gemini-3-flash-preview",
|
||||
config: {
|
||||
systemInstruction: {
|
||||
parts: [{ text: systemPrompt }]
|
||||
},
|
||||
temperature: 0
|
||||
},
|
||||
contents: [
|
||||
{
|
||||
role: "user",
|
||||
parts: [{ text: JSON.stringify(input) }]
|
||||
}
|
||||
]
|
||||
});
|
||||
|
||||
const aiOutput = response.text ?? "";
|
||||
|
||||
try {
|
||||
return JSON.parse(aiOutput);
|
||||
} catch {
|
||||
return { invalid: true, reason: "AI output could not be parsed" };
|
||||
}
|
||||
};
|
||||
}
|
||||
130
scrape/parse/v3/v3.js
Normal file
130
scrape/parse/v3/v3.js
Normal file
@@ -0,0 +1,130 @@
|
||||
/*
|
||||
* Copyright (C) 2025 Jakub Žitník
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
* the Free Software Foundation, either version 3 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*/
|
||||
|
||||
import fs from "fs/promises";
|
||||
import { setup } from "./call.js";
|
||||
|
||||
const PREVIOUS = "db/v3/_previous.json";
|
||||
const FINAL = "db/v3/v3.json";
|
||||
const EXCLUDE_CLASSES = new Set(["ABSENCE"]);
|
||||
|
||||
async function checkFileExists(filePath) {
|
||||
try {
|
||||
await fs.access(filePath);
|
||||
return true;
|
||||
} catch (err) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
function arraysAreEqual(arr1, arr2) {
|
||||
if (arr1.length !== arr2.length) return false;
|
||||
for (let i = 0; i < arr1.length; i++) {
|
||||
if (arr1[i] !== arr2[i]) return false;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
function getTime() {
|
||||
const currentDate = new Date();
|
||||
return currentDate.getHours().toString().padStart(2, "0") + ":" + currentDate.getMinutes().toString().padStart(2, "0");
|
||||
}
|
||||
|
||||
function setupFinal() {
|
||||
return {
|
||||
schedule: [],
|
||||
status: {
|
||||
lastUpdated: getTime(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
export default async function parseV3(fileV2Path) {
|
||||
const call = await setup();
|
||||
|
||||
let clearRun = false;
|
||||
let previousStr = "{}";
|
||||
|
||||
if (await checkFileExists(PREVIOUS)) {
|
||||
previousStr = await fs.readFile(PREVIOUS, "utf8");
|
||||
} else {
|
||||
clearRun = true;
|
||||
}
|
||||
|
||||
const now = JSON.parse(await fs.readFile(fileV2Path, "utf8"));
|
||||
const previous = JSON.parse(previousStr);
|
||||
const previousDays = previous.props?.map(p => p.date) || [];
|
||||
|
||||
let final;
|
||||
if (await checkFileExists(FINAL)) {
|
||||
final = JSON.parse(await fs.readFile(FINAL, "utf8"));
|
||||
} else {
|
||||
final = setupFinal();
|
||||
clearRun = true;
|
||||
}
|
||||
|
||||
let i = 0;
|
||||
for (const prop of now.props) {
|
||||
const date = new Date(prop.date);
|
||||
const dayIndex = (date.getDay() + 6) % 7;
|
||||
|
||||
if (!final.schedule[i]) {
|
||||
final.schedule[i] = {};
|
||||
}
|
||||
|
||||
const day = now.schedule[i];
|
||||
const batch = {};
|
||||
|
||||
for (const cls of Object.keys(day)) {
|
||||
if (EXCLUDE_CLASSES.has(cls)) continue;
|
||||
|
||||
const newClass = day[cls];
|
||||
|
||||
if (clearRun || !previousDays.includes(prop.date)) {
|
||||
batch[cls] = newClass;
|
||||
continue;
|
||||
}
|
||||
|
||||
const oldPropIndex = previous.props.findIndex(
|
||||
p => p.date === prop.date
|
||||
);
|
||||
const oldClass = previous.schedule[oldPropIndex]?.[cls] || [];
|
||||
|
||||
if (!arraysAreEqual(oldClass, newClass)) {
|
||||
batch[cls] = newClass;
|
||||
}
|
||||
}
|
||||
|
||||
if (Object.keys(batch).length > 0) {
|
||||
const results = await call(batch, dayIndex);
|
||||
|
||||
for (const cls of Object.keys(results)) {
|
||||
final.schedule[i][cls] = results[cls];
|
||||
}
|
||||
}
|
||||
|
||||
i++;
|
||||
}
|
||||
|
||||
if (!clearRun) {
|
||||
final.status.lastUpdated = getTime();
|
||||
}
|
||||
|
||||
final.props = now.props;
|
||||
|
||||
await fs.writeFile(FINAL, JSON.stringify(final), "utf8");
|
||||
await fs.copyFile(fileV2Path, PREVIOUS);
|
||||
}
|
||||
|
||||
parseV3("db/v2.json");
|
||||
182
scripts/loadstaticschedule.js
Normal file
182
scripts/loadstaticschedule.js
Normal file
@@ -0,0 +1,182 @@
|
||||
/*
|
||||
* Copyright (C) 2025 Jakub Žitník
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
* the Free Software Foundation, either version 3 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*/
|
||||
|
||||
import axios from "axios";
|
||||
import { CookieJar } from "tough-cookie";
|
||||
import { wrapper } from "axios-cookiejar-support";
|
||||
import * as cheerio from "cheerio";
|
||||
import { URLSearchParams } from "url";
|
||||
import fs from "fs";
|
||||
|
||||
const BASE = "https://www.spsejecna.cz";
|
||||
const PATHS = {
|
||||
SET_ROLE: "/user/role",
|
||||
LOGIN: "/user/login",
|
||||
TEACHERS: "/ucitel",
|
||||
TEACHER: teacherCode => `/ucitel/${teacherCode}`
|
||||
};
|
||||
const DB_PATH = "db/persistent/timetables.json";
|
||||
|
||||
const jar = new CookieJar();
|
||||
|
||||
const client = wrapper(axios.create({
|
||||
baseURL: BASE,
|
||||
jar,
|
||||
withCredentials: true,
|
||||
headers: {
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:120.0) Gecko/20100101 Firefox/120.0",
|
||||
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"
|
||||
}
|
||||
}));
|
||||
|
||||
globalThis.File = class File {};
|
||||
|
||||
async function login(username, password) {
|
||||
await client.get("/");
|
||||
|
||||
await client.get(PATHS.SET_ROLE, {
|
||||
params: { role: "student" }
|
||||
});
|
||||
|
||||
const token3Res = await client.get("/");
|
||||
const token3 = token3Res.data.match(/"token3"\s+value="(\d+)"/)[1];
|
||||
|
||||
const form = new URLSearchParams();
|
||||
form.append('user', username);
|
||||
form.append('pass', password);
|
||||
form.append('token3', token3);
|
||||
form.append('submit', 'Přihlásit+se');
|
||||
|
||||
try {
|
||||
const response = await client.post(PATHS.LOGIN, form.toString(), {
|
||||
headers: {
|
||||
"Content-Type": "application/x-www-form-urlencoded"
|
||||
},
|
||||
maxRedirects: 0
|
||||
});
|
||||
|
||||
if (response.status == 200) {
|
||||
console.log("INVALID CREDENTIALS!");
|
||||
process.exit(1);
|
||||
}
|
||||
} catch {}
|
||||
}
|
||||
|
||||
async function getAllTeacherCodes() {
|
||||
const list = new Set();
|
||||
const response = await client.get(PATHS.TEACHERS);
|
||||
const $ = cheerio.load(response.data);
|
||||
|
||||
$("main .contentLeftColumn li, main .contentRightColumn li").each((_, el) => {
|
||||
const link = $(el).find("a");
|
||||
const href = link.attr("href");
|
||||
|
||||
if (href) {
|
||||
const key = href.split("/").pop().toLowerCase();
|
||||
list.add(key);
|
||||
}
|
||||
});
|
||||
|
||||
return list;
|
||||
}
|
||||
|
||||
async function constructSchedules(allTeachers) {
|
||||
const classes = {};
|
||||
|
||||
function setupClass(className) {
|
||||
function generateArray(width, height) {
|
||||
return Array.from({ length: height }, () => Array.from({ length: width }, () => []));
|
||||
}
|
||||
classes[className] = generateArray(10, 5);
|
||||
}
|
||||
|
||||
let idk = 0;
|
||||
for (const key of allTeachers) {
|
||||
idk++;
|
||||
const response = await client.get(PATHS.TEACHER(key));
|
||||
const $ = cheerio.load(response.data);
|
||||
|
||||
const tbody = $('table.timetable > tbody');
|
||||
if (!tbody.length) {
|
||||
console.log(`ERROR: ${key}`)
|
||||
continue;
|
||||
}
|
||||
|
||||
tbody.find('tr').slice(1).each((dayIndex, tr) => {
|
||||
const $tr = $(tr);
|
||||
|
||||
let currentHour = 0;
|
||||
|
||||
$tr.find('td').each((_, td) => {
|
||||
const $td = $(td);
|
||||
|
||||
const colspan = parseInt($td.attr('colspan') || '1', 10);
|
||||
|
||||
const $subject = $td.find('span.subject');
|
||||
const $class = $td.find('span.class');
|
||||
const $group = $td.find('span.group');
|
||||
const $room = $td.find('a.room');
|
||||
const $employee = $td.find('a.employee');
|
||||
|
||||
const hasData = $subject.length && $class.length && $room.length && $employee.length;
|
||||
|
||||
let cellData = null;
|
||||
let classText = '';
|
||||
|
||||
if (hasData) {
|
||||
classText = $class.text().trim();
|
||||
cellData = {
|
||||
subject: $subject.text().trim(),
|
||||
title: $subject.attr('title')?.trim() || '',
|
||||
group: $group.length ? $group.text().trim() : null,
|
||||
room: $room.text().trim(),
|
||||
teacher: {
|
||||
code: $employee.text().trim().toLowerCase(),
|
||||
name: $employee.attr('title')?.trim() || ''
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
for (let i = 0; i < colspan; i++) {
|
||||
if (currentHour >= 10) {
|
||||
break;
|
||||
}
|
||||
|
||||
if (hasData && cellData) {
|
||||
if (classes[classText] === undefined) {
|
||||
setupClass(classText);
|
||||
}
|
||||
|
||||
classes[classText][dayIndex][currentHour].push(cellData);
|
||||
}
|
||||
|
||||
currentHour++;
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
console.log(`DONE: ${idk}/${allTeachers.size}`)
|
||||
}
|
||||
|
||||
return classes;
|
||||
}
|
||||
|
||||
await login(process.env.USERNAME, process.env.PASSWORD);
|
||||
const allTeachers = await getAllTeacherCodes();
|
||||
const schedule = await constructSchedules(allTeachers)
|
||||
const str = JSON.stringify(schedule);
|
||||
|
||||
fs.writeFileSync(DB_PATH, str, {
|
||||
encoding: "utf8"
|
||||
});
|
||||
28
scripts/setup.js
Normal file
28
scripts/setup.js
Normal file
@@ -0,0 +1,28 @@
|
||||
/*
|
||||
* Copyright (C) 2025 Jakub Žitník
|
||||
*
|
||||
* This program is free software: you can redistribute it and/or modify
|
||||
* it under the terms of the GNU General Public License as published by
|
||||
* the Free Software Foundation, either version 3 of the License, or
|
||||
* (at your option) any later version.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*/
|
||||
|
||||
import fs from "fs";
|
||||
|
||||
const DIRS = [
|
||||
"db/persistent",
|
||||
"db/v3",
|
||||
];
|
||||
|
||||
for (const dir of DIRS) {
|
||||
try {
|
||||
fs.mkdirSync(dir);
|
||||
} catch {}
|
||||
}
|
||||
|
||||
// LEAVE ME ALONE I KNOW THIS CODE IS SHIT
|
||||
@@ -49,15 +49,6 @@ app.get('/', async (req, res) => {
|
||||
}
|
||||
});
|
||||
|
||||
app.get('/versioned/v1', async (_, res) => {
|
||||
const dataStr = await fs.readFile(path.join(process.cwd(), "db", "v1.json"), "utf8");
|
||||
const data = JSON.parse(dataStr);
|
||||
|
||||
data["status"]["currentUpdateSchedule"] = getCurrentInterval();
|
||||
|
||||
res.json(data);
|
||||
});
|
||||
|
||||
VERSIONS.forEach((version) => {
|
||||
app.get(`/versioned/${version}`, async (_, res) => {
|
||||
try {
|
||||
|
||||
Reference in New Issue
Block a user