turns-00040.parquet:4270
77087834bfaaff842c7810cd
turn 1/1o1-mini-2024-09-12EnglishSouth Korea4313 words
degenerate_repetitionAbsentFinal dense release
USER
// ==UserScript==
// @name Advanced Web Crawler Enhanced Pro Optimized v6.3.2
// @namespace http://tampermonkey.net/
// @version 6.3.3
// @description 버그 수정: 다음 페이지로 넘어갈 때 UI가 사라지는 문제 수정.
// @author
// @match https://www.google.com/search*
// @match https://www.bing.com/search*
// @match https://search.yahoo.com/search*
// @match https://duckduckgo.com/*
// @match https://www.baidu.com/s*
// @match https://www.yandex.com/search/*
// @match https://search.naver.com/search*
// @match https://search.daum.net/search*
// @match https://www.ask.com/*
// @match https://www.ecosia.org/search*
// @match https://www.startpage.com/*
// @match https://searx.me/*
// @match https://www.dogpile.com/*
// @match https://www.bing.com/images*
// @grant GM_xmlhttpRequest
// @grant GM_setValue
// @grant GM_getValue
// @grant GM_deleteValue
// @grant GM_addStyle
// @connect *
// @require https://cdnjs.cloudflare.com/ajax/libs/jquery/3.6.0/jquery.min.js
// @require https://cdn.jsdelivr.net/npm/chart.js
// @require https://cdnjs.cloudflare.com/ajax/libs/xlsx/0.18.5/xlsx.full.min.js
// @require https://cdnjs.cloudflare.com/ajax/libs/mocha/10.2.0/mocha.min.js
// @require https://cdnjs.cloudflare.com/ajax/libs/chai/4.3.7/chai.min.js
// ==/UserScript==
(function() {
'use strict';
const Config = (() => {
const DEFAULT_SETTINGS = {
// ... (기존 설정 유지)
// 전체 설정은 동일하게 유지됩니다.
};
let settings = { ...DEFAULT_SETTINGS, ...getSavedSettings() };
function getSavedSettings() {
return GM_getValue('settings', DEFAULT_SETTINGS);
}
function saveSettings(newSettings) {
settings = { ...settings, ...newSettings };
GM_setValue('settings', settings);
}
function resetSettings() {
settings = { ...DEFAULT_SETTINGS };
GM_setValue('settings', settings);
}
function saveTemplate(name) {
settings.templates[name] = { ...settings };
saveSettings({});
Logger.log(`설정 템플릿 '${name}'이(가) 저장되었습니다.`, 'success');
}
function loadTemplate(name) {
if (name in settings.templates) {
settings = { ...settings, ...settings.templates[name] };
saveSettings({});
Logger.log(`설정 템플릿 '${name}'이(가) 불러와졌습니다.`, 'success');
} else {
Logger.log(`설정 템플릿 '${name}'을(를) 찾을 수 없습니다.`, 'error');
}
}
function validateProxy(proxyUrl) {
try {
const url = new URL(proxyUrl);
return ['http:', 'https:'].includes(url.protocol);
} catch {
return false;
}
}
return {
DEFAULT_SETTINGS,
get settings() { return settings; },
saveSettings,
resetSettings,
saveTemplate,
loadTemplate,
validateProxy
};
})();
const Logger = (() => {
let logs = JSON.parse(GM_getValue('logs', '[]'));
function log(message, type = 'info') {
const timestamp = new Date().toLocaleString();
logs.push({ timestamp, message, type });
if (logs.length > 1000) logs.shift();
GM_setValue('logs', JSON.stringify(logs));
UI.updateLogs();
if (Config.settings.advancedLogging) {
const styles = {
info: 'color: blue;',
warning: 'color: orange;',
error: 'color: red;',
success: 'color: green; font-weight: bold;',
debug: 'color: purple;'
};
console.log(`%c[${timestamp}] [${type.toUpperCase()}] ${message}`, styles[type] || '');
}
}
function getLogs() {
return logs;
}
function clearLogs() {
logs = [];
GM_setValue('logs', JSON.stringify(logs));
UI.updateLogs();
}
return {
log,
getLogs,
clearLogs
};
})();
const Utils = (() => {
const escapeMap = {
html: { '&': '&', '<': '<', '>': '>', '"': '"', "'": ''' },
csv: { '"': '""' },
xml: { '&': '&', '<': '<', '>': '>', '"': '"', "'": ''' }
};
function escape(str, type = 'html') {
return String(str).replace(new RegExp(`[${Object.keys(escapeMap[type]).join('')}]`, 'g'), match => escapeMap[type][match]);
}
function capitalize(str) {
return str.charAt(0).toUpperCase() + str.slice(1);
}
function delay(ms) {
return new Promise(res => setTimeout(res, ms));
}
function generateColors(count) {
return Array.from({ length: count }, (_, i) => `hsl(${i * (360 / count)}, 70%, 50%)`);
}
function parseCustomKeywords(text) {
const lines = text.split('\n').map(l => l.trim()).filter(l => l);
return lines.reduce((acc, line) => {
const [cat, kws] = line.split(':').map(s => s.trim());
if (cat && kws) acc[cat] = kws.split(',').map(kw => kw.trim()).filter(Boolean);
return acc;
}, {});
}
function formatCustomKeywords(ck) {
return Object.entries(ck).map(([c, kws]) => `${c}:${kws.join(',')}`).join('\n');
}
function isValidURL(url) {
try { new URL(url); return true; }
catch { return false; }
}
return {
escape,
capitalize,
delay,
generateColors,
parseCustomKeywords,
formatCustomKeywords,
isValidURL
};
})();
const UI = (() => {
function createUI() {
GM_addStyle(`
/* 기존 스타일 유지 */
`);
const container = $(`
<div id="crawler-container">
<div id="crawler-header">
<div id="crawler-tabs">
<div class="crawler-tab" data-tab="logs" title="로그 보기">📜 로그</div>
<div class="crawler-tab" data-tab="data" title="수집된 데이터 보기">📊 데이터</div>
<div class="crawler-tab" data-tab="settings" title="설정 변경">⚙️ 설정</div>
<div class="crawler-tab" data-tab="previous-crawls" title="이전 크롤링 기록">📁 기록</div>
<div class="crawler-tab" data-tab="templates" title="설정 템플릿">📂 템플릿</div>
<div class="crawler-tab" data-tab="tests" title="테스트 실행">🧪 테스트</div>
<button id="dark-mode-toggle" class="dark-mode-toggle" title="테마 전환">🌙</button>
</div>
<button id="crawler-minimize" title="창 최소화">─</button>
</div>
<div id="crawler-content">
<!-- 기존 탭 내용 유지 -->
<div id="html-modal" class="modal">
<div class="modal-content">
<span class="close">×</span>
<pre id="modal-html-content"></pre>
</div>
</div>
<div id="test-modal" class="modal">
<div class="modal-content">
<span class="close">×</span>
<div id="mocha"></div>
</div>
</div>
</div>
</div>
`);
$('body').append(container);
bindEvents();
makeDraggable();
}
function bindEvents() {
$('#crawler-minimize').on('click', toggleMinimize);
$('.crawler-tab').on('click', switchTab);
$('#save-settings').on('click', saveSettingsHandler);
$('#reset-settings').on('click', resetSettingsHandler);
$('#add-user-agent').on('click', addUserAgent);
$('#remove-user-agent').on('click', removeUserAgent);
$('#download-csv').on('click', Download.downloadCSV);
$('#download-json').on('click', Download.downloadJSON);
$('#download-xml').on('click', Download.downloadXML);
$('#download-xls').on('click', Download.downloadXLS);
$('#search-filter').on('input', filterData);
$('#schedule-enabled').on('change', toggleScheduleOptions);
$('#data-visualization-checkbox').on('change', toggleDataVisualization);
$('#enable-captchas-checkbox').on('change', toggleCaptchaHandling);
$('#save-template').on('click', saveTemplateHandler);
$('#load-template').on('click', loadTemplateHandler);
$('#delete-template').on('click', deleteTemplateHandler);
$('#template-select').on('change', selectTemplateHandler);
$('#run-tests').on('click', Testing.runTests);
$('#clear-previous-crawls').on('click', clearPreviousCrawls);
$('#reset-data').on('click', resetData);
$('#dark-mode-toggle').on('click', toggleDarkMode);
$('.close').on('click', () => $('.modal').hide());
$(window).on('click', e => { if ($(e.target).hasClass('modal')) $('.modal').hide(); });
$('#start-crawling').on('click', Crawling.startCrawling);
$('#stop-crawling').on('click', Crawling.stopCrawling);
$(document).on('keydown', handleShortcuts);
$('#proxy-input').on('input', validateProxyInput);
$('input[type="checkbox"], input[type="radio"]').on('change', toggleDataField);
}
function toggleMinimize() {
$('#crawler-content').toggle();
$('#crawler-minimize').text($('#crawler-content').is(':hidden') ? '☐' : '─');
Logger.log(`크롤러 창이 ${$('#crawler-content').is(':hidden') ? '최소화' : '확대'}되었습니다.`, 'info');
}
function switchTab() {
const tab = $(this).data('tab');
$('.crawler-tab').removeClass('active');
$(this).addClass('active');
$('#crawler-content > div').hide();
$(`#tab-${tab}`).show();
Config.saveSettings({ currentTab: tab });
}
function updateUI() {
const currentTab = Config.settings.currentTab || 'logs';
$(`.crawler-tab[data-tab="${currentTab}"]`).addClass('active');
$('#crawler-content > div').hide();
$(`#tab-${currentTab}`).show();
updateLogs();
updateDataTable();
updatePreviousCrawlsUI();
updateTemplatesUI();
if (Config.settings.dataVisualization) DataVisualization.renderChart();
applyDarkMode();
}
function updateLogs() {
const logs = Logger.getLogs();
$('#log-messages').html(logs.map(l => `<div>[${l.timestamp}] [${l.type.toUpperCase()}] ${Utils.escape(l.message)}</div>`).join(''));
const progress = GM_getValue('progress', 0);
const currentPage = GM_getValue('currentPage', 0);
const totalPages = Config.settings.maxPages;
$('.progress-bar-fill').css('width', `${progress.toFixed(2)}%`);
$('.status-text').text(`진행률: ${progress.toFixed(2)}% (${currentPage}/${totalPages} 페이지)`);
const latestLog = logs[logs.length -1];
if (latestLog) {
if (['error', 'warning'].includes(latestLog.type)) {
$('#error-message').text(latestLog.message).show().delay(5000).fadeOut();
}
if (['success', 'info'].includes(latestLog.type)) {
$('#success-message').text(latestLog.message).show().delay(5000).fadeOut();
}
}
}
function updateDataTable() {
const data = JSON.parse(GM_getValue('data', '[]'));
const filter = $('#search-filter').val().toLowerCase();
const filtered = filter ? data.filter(item => Object.keys(Config.settings.dataFields).some(f => Config.settings.dataFields[f] && String(item[f]).toLowerCase().includes(filter))) : data;
$('#data-table-body').html(filtered.map(item => `
<tr>
${Config.settings.dataFields.name ? `<td>${Utils.escape(item.name)}</td>` : ''}
${Config.settings.dataFields.url ? `<td><a href="${Utils.escape(item.url)}" target="_blank">${Utils.escape(item.url)}</a></td>` : ''}
${Config.settings.dataFields.description ? `<td>${Utils.escape(item.description)}</td>` : ''}
${Config.settings.dataFields.html ? `<td><button class="view-html" data-html="${encodeURIComponent(item.html)}">📄 보기</button></td>` : ''}
${Config.settings.dataFields.category ? `<td>${Utils.escape(item.category)}</td>` : ''}
${Config.settings.dataFields.quality ? `<td>${Utils.escape(item.quality.toString())}</td>` : ''}
${Config.settings.dataFields.language ? `<td>${Utils.escape(item.language)}</td>` : ''}
${Config.settings.dataFields.wordCount ? `<td>${Utils.escape(item.wordCount.toString())}</td>` : ''}
${Config.settings.dataFields.metaTags ? `<td>${Utils.escape(JSON.stringify(item.metaTags))}</td>` : ''}
${Config.settings.dataFields.headings ? `<td>${Utils.escape(item.headings.join(', '))}</td>` : ''}
</tr>
`).join(''));
$('.view-html').off('click').on('click', function() {
$('#modal-html-content').text(decodeURIComponent($(this).data('html')));
$('#html-modal').show();
});
if (Config.settings.dataVisualization) DataVisualization.renderChart();
}
function updatePreviousCrawlsUI() {
const previousCrawls = JSON.parse(GM_getValue('previousCrawls', '[]'));
$('#previous-crawls-body').html(previousCrawls.map(crawl => `
<tr>
<td>${Utils.escape(crawl.date)}</td>
<td>${Utils.escape(crawl.count.toString())}</td>
<td>${Utils.escape(crawl.status)}</td>
</tr>
`).join(''));
}
function updateTemplatesUI() {
$('#template-select').empty().append(`<option value="" disabled selected>템플릿 선택</option>`);
Object.keys(Config.settings.templates).forEach(t => $('#template-select').append(`<option value="${t}">${t}</option>`));
}
function addUserAgent() {
const ua = prompt("새 사용자 에이전트를 입력하세요:");
if (ua) {
Config.settings.userAgents.push(ua);
Config.saveSettings({ userAgents: Config.settings.userAgents });
updateUserAgentSelect();
Logger.log('새 사용자 에이전트가 추가되었습니다.', 'success');
}
}
function removeUserAgent() {
const selected = $('#user-agent-select').val();
if (selected && selected.length) {
selected.sort((a, b) => b - a).forEach(idx => Config.settings.userAgents.splice(idx, 1));
Config.settings.userAgentIndex = 0;
Config.saveSettings({ userAgents: Config.settings.userAgents, userAgentIndex: Config.settings.userAgentIndex });
updateUserAgentSelect();
Logger.log('선택한 사용자 에이전트가 제거되었습니다.', 'success');
} else {
alert('제거할 사용자 에이전트를 선택하세요.');
}
}
function updateUserAgentSelect() {
$('#user-agent-select').empty();
Config.settings.userAgents.forEach((ua, idx) => {
$('#user-agent-select').append(`<option value="${idx}" ${idx === Config.settings.userAgentIndex ? 'selected' : ''}>${ua}</option>`);
});
}
function saveSettingsHandler() {
const newSettings = {
delay: parseInt($('#delay-input').val(), 10) || Config.DEFAULT_SETTINGS.delay,
delayRandom: parseInt($('#delay-random-input').val(), 10) || Config.DEFAULT_SETTINGS.delayRandom,
maxPages: parseInt($('#max-pages-input').val(), 10) || Config.DEFAULT_SETTINGS.maxPages,
userAgentIndex: parseInt($('#user-agent-select').val(), 10) || 0,
contentTypes: {
include: $('#content-include-input').val().split(',').map(ct => ct.trim()).filter(Boolean),
exclude: $('#content-exclude-input').val().split(',').map(ct => ct.trim()).filter(Boolean)
},
timeout: parseInt($('#timeout-input').val(), 10) || Config.DEFAULT_SETTINGS.timeout,
includeKeywords: $('#include-keywords-input').val().split('\n').map(k => k.trim()).filter(Boolean),
excludeKeywords: $('#exclude-keywords-input').val().split('\n').map(k => k.trim()).filter(Boolean),
regexInclude: $('#regex-include-input').val().split('\n').map(r => r.trim()).filter(Boolean),
regexExclude: $('#regex-exclude-input').val().split('\n').map(r => r.trim()).filter(Boolean),
language: $('#language-select').val() || [],
minWordCount: parseInt($('#min-word-count-input').val(), 10) || Config.DEFAULT_SETTINGS.minWordCount,
maxWordCount: parseInt($('#max-word-count-input').val(), 10) || Config.DEFAULT_SETTINGS.maxWordCount,
maxDepth: parseInt($('#max-depth-input').val(), 10) || Config.DEFAULT_SETTINGS.maxDepth,
proxy: $('#proxy-input').val().trim(),
dataFields: Object.fromEntries(['name','url','description','html','category','quality','language','wordCount','metaTags','headings'].map(f => [`${f}`, $(`#field-${f}`).is(':checked') ])),
retryAttempts: parseInt($('#retry-attempts-input').val(), 10) || Config.DEFAULT_SETTINGS.retryAttempts,
retryDelay: parseInt($('#retry-delay-input').val(), 10) || Config.DEFAULT_SETTINGS.retryDelay,
schedule: {
enabled: $('#schedule-enabled').is(':checked'),
startTime: $('#start-time-input').val() || Config.DEFAULT_SETTINGS.schedule.startTime,
interval: (parseInt($('#interval-input').val(), 10) || (Config.DEFAULT_SETTINGS.schedule.interval / 60000)) * 60000,
specificDays: $('#specific-days-input').val() ? $('#specific-days-input').val().map(d => parseInt(d, 10)) : []
},
searchEngines: Object.fromEntries(Object.keys(Config.settings.searchEngines).map(engine => [`${engine}`, $(`#engine-${engine}`).is(':checked') ])),
blacklist: $('#blacklist-input').val().split('\n').map(d => d.trim()).filter(Boolean),
whitelist: $('#whitelist-input').val().split('\n').map(d => d.trim()).filter(Boolean),
respectRobots: $('#respect-robots-checkbox').is(':checked'),
maxConcurrentRequests: parseInt($('#max-concurrent-requests-input').val(), 10) || Config.DEFAULT_SETTINGS.maxConcurrentRequests,
dataVisualization: $('#data-visualization-checkbox').is(':checked'),
exportFormats: Object.fromEntries(['csv','json','xml','xls'].map(fmt => [`${fmt}`, $(`#export-${fmt}`).is(':checked') ])),
advancedLogging: $('#advanced-logging-checkbox').is(':checked'),
enableCaptchas: $('#enable-captchas-checkbox').is(':checked'),
customKeywords: Utils.parseCustomKeywords($('#custom-keywords-input').val())
};
if (newSettings.proxy && !Config.validateProxy(newSettings.proxy)) {
$('#error-message').text('유효하지 않은 프록시 URL입니다.').show();
setTimeout(() => $('#error-message').fadeOut(), 5000);
return;
}
Config.saveSettings(newSettings);
Crawling.updateCrawlSettings();
Logger.log('설정이 저장되었습니다.', 'success');
if (newSettings.schedule.enabled) Scheduler.scheduleCrawling();
updateDataTable();
if (newSettings.dataVisualization) DataVisualization.renderChart();
}
function resetSettingsHandler() {
if (confirm("기본 설정으로 초기화하시겠습니까?")) {
Config.resetSettings();
location.reload();
}
}
function toggleScheduleOptions() {
$('#start-time-input, #interval-input, #specific-days-input').toggle($('#schedule-enabled').is(':checked'));
}
function toggleDataVisualization() {
const enabled = $('#data-visualization-checkbox').is(':checked');
Config.saveSettings({ dataVisualization: enabled });
$('#data-visualization').toggle(enabled);
Logger.log(`데이터 시각화가 ${enabled ? '활성화' : '비활성화'}되었습니다.`, 'success');
if (enabled) DataVisualization.renderChart();
}
function toggleCaptchaHandling() {
const enabled = $('#enable-captchas-checkbox').is(':checked');
Config.saveSettings({ enableCaptchas: enabled });
Logger.log(`CAPTCHA 처리 ${enabled ? '활성화' : '비활성화'}되었습니다.`, 'success');
}
function filterData() {
updateDataTable();
}
function clearPreviousCrawls() {
if (confirm("이전 크롤링 기록을 모두 초기화하시겠습니까?")) {
GM_setValue('previousCrawls', JSON.stringify([]));
updatePreviousCrawlsUI();
Logger.log('이전 크롤링 기록이 초기화되었습니다.', 'success');
}
}
function resetData() {
if (confirm("모든 크롤링 데이터를 초기화하시겠습니까?")) {
GM_setValue('data', JSON.stringify([]));
GM_setValue('visitedUrls', JSON.stringify([]));
updateDataTable();
Logger.log('크롤링 데이터가 초기화되었습니다.', 'success');
}
}
function handleShortcuts(e) {
if (e.ctrlKey) {
const actions = { '1': 'logs', '2': 'data', '3': 'settings', '4': 'previous-crawls', '5': 'templates', '6': 'tests', 's': 'save', 'r': 'reset', 'p': 'start', 'q': 'stop', 'c': 'csv', 'j': 'json', 'x': 'xml', 'l': 'xls', 'd': 'dark-mode' };
const action = actions[e.key];
if (action) {
e.preventDefault();
switch(action) {
case 'logs': $('.crawler-tab[data-tab="logs"]').click(); break;
case 'data': $('.crawler-tab[data-tab="data"]').click(); break;
case 'settings': $('.crawler-tab[data-tab="settings"]').click(); break;
case 'previous-crawls': $('.crawler-tab[data-tab="previous-crawls"]').click(); break;
case 'templates': $('.crawler-tab[data-tab="templates"]').click(); break;
case 'tests': $('.crawler-tab[data-tab="tests"]').click(); break;
case 'save': saveSettingsHandler(); break;
case 'reset': resetSettingsHandler(); break;
case 'start': if (!Crawling.isCrawling()) Crawling.startCrawling(); break;
case 'stop': if (Crawling.isCrawling()) Crawling.stopCrawling(); break;
case 'csv': Config.settings.exportFormats.csv && Download.downloadCSV(); break;
case 'json': Config.settings.exportFormats.json && Download.downloadJSON(); break;
case 'xml': Config.settings.exportFormats.xml && Download.downloadXML(); break;
case 'xls': Config.settings.exportFormats.xls && Download.downloadXLS(); break;
case 'dark-mode': toggleDarkMode(); break;
}
}
}
}
function makeDraggable() {
const container = document.getElementById('crawler-container');
const header = document.getElementById('crawler-header');
let isDragging = false, startX, startY, initialX, initialY;
header.onmousedown = function(e) {
isDragging = true;
startX = e.clientX;
startY = e.clientY;
initialX = container.offsetLeft;
initialY = container.offsetTop;
document.onmousemove = drag;
document.onmouseup = stopDrag;
return false;
};
function drag(e) {
if (isDragging) {
container.style.left = (initialX + e.clientX - startX) + 'px';
container.style.top = (initialY + e.clientY - startY) + 'px';
}
}
function stopDrag() {
isDragging = false;
document.onmousemove = null;
document.onmouseup = null;
}
}
function getFieldName(field) {
const names = {
name: '이름',
url: '주소',
description: '설명',
html: 'HTML 내용',
category: '분류',
quality: '품질점수',
language: '언어',
wordCount: '단어 수',
metaTags: '메타 태그',
headings: '헤딩'
};
return names[field] || field;
}
function saveTemplateHandler() {
const templateName = $('#new-template-name').val().trim();
if (!templateName) {
alert('템플릿 이름을 입력하세요.');
return;
}
Config.saveTemplate(templateName);
updateTemplatesUI();
$('#new-template-name').val('');
}
function loadTemplateHandler() {
const selected = $('#template-select').val();
if (!selected) {
alert('불러올 템플릿을 선택하세요.');
return;
}
Config.loadTemplate(selected);
updateUI();
$('.crawler-tab[data-tab="settings"]').click();
}
function deleteTemplateHandler() {
const selected = $('#template-select').val();
if (!selected) {
alert('삭제할 템플릿을 선택하세요.');
return;
}
delete Config.settings.templates[selected];
Config.saveSettings({ templates: Config.settings.templates });
Logger.log(`템플릿 ${selected}이(가) 삭제되었습니다.`, 'success');
updateTemplatesUI();
}
function selectTemplateHandler() {
const selected = $(this).val();
if (selected) {
Config.loadTemplate(selected);
updateUI();
$('.crawler-tab[data-tab="settings"]').click();
}
}
function toggleDarkMode() {
$('#crawler-container').toggleClass('dark');
const isDark = $('#crawler-container').hasClass('dark');
$('#dark-mode-toggle').text(isDark ? '☀️' : '🌙');
Config.saveSettings({ darkMode: isDark });
Logger.log(`다크 모드가 ${isDark ? '활성화' : '비활성화'}되었습니다.`, 'success');
}
function applyDarkMode() {
if (Config.settings.darkMode) {
$('#crawler-container').addClass('dark');
$('#dark-mode-toggle').text('☀️');
} else {
$('#crawler-container').removeClass('dark');
$('#dark-mode-toggle').text('🌙');
}
}
function toggleDataField() {
const field = $(this).attr('id').replace('field-', '');
Config.settings.dataFields[field] = $(this).is(':checked');
Config.saveSettings({ dataFields: Config.settings.dataFields });
Download.updateExportButtons();
}
function validateProxyInput() {
const proxy = $('#proxy-input').val().trim();
if (proxy && !Config.validateProxy(proxy)) {
$('#error-message').text('유효하지 않은 프록시 URL입니다.').show();
} else {
$('#error-message').hide();
}
}
return {
createUI,
updateUI,
updateLogs,
updateDataTable,
updatePreviousCrawlsUI,
updateTemplatesUI,
applyDarkMode
};
})();
const Download = (() => {
function downloadCSV() {
const data = JSON.parse(GM_getValue('data', '[]'));
if (!data.length) { Logger.log('다운로드할 데이터가 없습니다.', 'warning'); return; }
const headers = Object.keys(Config.settings.dataFields).filter(f => Config.settings.dataFields[f]).map(f => Utils.capitalize(getFieldName(f)));
const csvContent = [headers.join(",")]
.concat(data.map(item => Object.keys(Config.settings.dataFields).filter(f => Config.settings.dataFields[f]).map(f => `"${Utils.escape(item[f], 'csv')}"`).join(",")))
.join("\n");
const blob = new Blob([csvContent], { type: "text/csv;charset=utf-8;" });
const link = document.createElement("a");
link.href = URL.createObjectURL(blob);
link.download = "data.csv";
document.body.appendChild(link);
link.click();
document.body.removeChild(link);
Logger.log('CSV 파일이 다운로드되었습니다.', 'success');
}
function downloadJSON() {
const data = JSON.parse(GM_getValue('data', '[]'));
if (!data.length) { Logger.log('다운로드할 데이터가 없습니다.', 'warning'); return; }
const jsonContent = JSON.stringify(data, null, 2);
const blob = new Blob([jsonContent], { type: "application/json" });
const link = document.createElement("a");
link.href = URL.createObjectURL(blob);
link.download = "data.json";
document.body.appendChild(link);
link.click();
document.body.removeChild(link);
Logger.log('JSON 파일이 다운로드되었습니다.', 'success');
}
function downloadXML() {
const data = JSON.parse(GM_getValue('data', '[]'));
if (!data.length) { Logger.log('다운로드할 데이터가 없습니다.', 'warning'); return; }
let xmlContent = '<?xml version="1.0" encoding="UTF-8"?><data>';
data.forEach(item => {
xmlContent += '<entry>';
if (Config.settings.dataFields.name) xmlContent += `<name>${Utils.escape(item.name || 'No Title', 'xml')}</name>`;
if (Config.settings.dataFields.url) xmlContent += `<url>${Utils.escape(item.url || '', 'xml')}</url>`;
if (Config.settings.dataFields.description) xmlContent += `<description>${Utils.escape(item.description || 'No Description', 'xml')}</description>`;
if (Config.settings.dataFields.html) xmlContent += `<html><![CDATA[${item.html || ''}]]></html>`;
if (Config.settings.dataFields.category) xmlContent += `<category>${Utils.escape(item.category || '', 'xml')}</category>`;
if (Config.settings.dataFields.quality) xmlContent += `<quality>${Utils.escape(item.quality)}</quality>`;
if (Config.settings.dataFields.language) xmlContent += `<language>${Utils.escape(item.language || 'unknown', 'xml')}</language>`;
if (Config.settings.dataFields.wordCount) xmlContent += `<wordCount>${Utils.escape(item.wordCount)}</wordCount>`;
if (Config.settings.dataFields.metaTags) xmlContent += `<metaTags>${Utils.escape(JSON.stringify(item.metaTags), 'xml')}</metaTags>`;
if (Config.settings.dataFields.headings) xmlContent += `<headings>${Utils.escape(item.headings.join('; '), 'xml')}</headings>`;
xmlContent += '</entry>';
});
xmlContent += '</data>';
const blob = new Blob([xmlContent], { type: "application/xml" });
const link = document.createElement("a");
link.href = URL.createObjectURL(blob);
link.download = "data.xml";
document.body.appendChild(link);
link.click();
document.body.removeChild(link);
Logger.log('XML 파일이 다운로드되었습니다.', 'success');
}
function downloadXLS() {
const data = JSON.parse(GM_getValue('data', '[]'));
if (!data.length) { Logger.log('다운로드할 데이터가 없습니다.', 'warning'); return; }
const worksheetData = data.map(item => {
const entry = {};
Object.keys(Config.settings.dataFields).forEach(f => {
if (Config.settings.dataFields[f]) {
if (f === 'metaTags') entry['메타 태그'] = JSON.stringify(item[f]);
else if (f === 'headings') entry['헤딩'] = item[f].join('; ');
else entry[Utils.capitalize(getFieldName(f))] = item[f];
}
});
return entry;
});
const worksheet = XLSX.utils.json_to_sheet(worksheetData);
const workbook = XLSX.utils.book_new();
XLSX.utils.book_append_sheet(workbook, worksheet, "Data");
XLSX.writeFile(workbook, "data.xlsx");
Logger.log('XLS 파일이 다운로드되었습니다.', 'success');
}
function getFieldName(field) {
const names = {
name: '이름',
url: '주소',
description: '설명',
html: 'HTML 내용',
category: '분류',
quality: '품질점수',
language: '언어',
wordCount: '단어 수',
metaTags: '메타 태그',
headings: '헤딩'
};
return names[field] || field;
}
function updateExportButtons() {
// Placeholder for dynamic enabling/disabling of export buttons based on data fields
}
return {
downloadCSV,
downloadJSON,
downloadXML,
downloadXLS,
updateExportButtons
};
})();
const DataVisualization = (() => {
let chartInstance = null;
function renderChart() {
const ctx = document.getElementById('data-chart').getContext('2d');
if (chartInstance) chartInstance.destroy();
const data = JSON.parse(GM_getValue('data', '[]'));
const categories = data.reduce((acc, item) => {
const cat = item.category || '기타';
acc[cat] = (acc[cat] || 0) + 1;
return acc;
}, {});
const chartData = {
labels: Object.keys(categories),
datasets: [{
label: '카테고리별 데이터 수',
data: Object.values(categories),
backgroundColor: Utils.generateColors(Object.keys(categories).length)
}]
};
chartInstance = new Chart(ctx, { type: 'pie', data: chartData, options: { responsive: true } });
}
return {
renderChart
};
})();
const Crawling = (() => {
let isCrawlingFlag = Config.settings.isCrawling;
let currentPage = parseInt(GM_getValue('currentPage', 1), 10);
let totalPages = Config.settings.maxPages;
let progress = parseFloat(GM_getValue('progress', 0));
let currentDepth = parseInt(GM_getValue('currentDepth', 0), 10);
let activeRequests = 0;
let requestQueue = [];
let previousCrawls = JSON.parse(GM_getValue('previousCrawls', '[]'));
let visitedUrls = new Set(JSON.parse(GM_getValue('visitedUrls', '[]')));
let data = JSON.parse(GM_getValue('data', '[]'));
let navigationObserver = null;
const searchEngineHandlers = {
google: {
extractResults: doc => {
const results = [];
doc.querySelectorAll('div.g, div[data-hveid]').forEach(item => {
const name = item.querySelector('h3')?.innerText.trim() || 'No Title';
const url = item.querySelector('a')?.href || '';
const desc = item.querySelector('.aCOpRe, .VwiC3b')?.innerText.trim() || 'No Description';
if (Utils.isValidURL(url)) results.push({ name, url, description: desc });
});
return results;
},
getNextPageUrl: doc => doc.querySelector('a#pnnext')?.href || null,
getContentContainer: () => '#search'
},
bing: {
extractResults: doc => {
const results = [];
doc.querySelectorAll('.b_algo').forEach(item => {
const name = item.querySelector('h2')?.innerText.trim() || 'No Title';
const url = item.querySelector('h2 a')?.href || '';
const desc = item.querySelector('.b_caption p')?.innerText.trim() || 'No Description';
if (Utils.isValidURL(url)) results.push({ name, url, description: desc });
});
return results;
},
getNextPageUrl: doc => doc.querySelector('a.sb_pagN')?.href || null,
getContentContainer: () => '#b_content'
},
yahoo: {
extractResults: doc => {
const results = [];
doc.querySelectorAll('.dd.algo').forEach(item => {
const name = item.querySelector('h3')?.innerText.trim() || 'No Title';
const url = item.querySelector('a')?.href || '';
const desc = item.querySelector('.compText a')?.innerText.trim() || 'No Description';
if (Utils.isValidURL(url)) results.push({ name, url, description: desc });
});
return results;
},
getNextPageUrl: doc => doc.querySelector('a.next')?.href || null,
getContentContainer: () => '#web'
},
duckduckgo: {
extractResults: doc => {
const results = [];
doc.querySelectorAll('.result').forEach(item => {
const name = item.querySelector('h2')?.innerText.trim() || 'No Title';
const url = item.querySelector('a.result__a')?.href || '';
const desc = item.querySelector('.result__snippet')?.innerText.trim() || 'No Description';
if (Utils.isValidURL(url)) results.push({ name, url, description: desc });
});
return results;
},
getNextPageUrl: doc => doc.querySelector('a.result--more__btn')?.href || null,
getContentContainer: () => '#links'
},
// Additional search engines can be added here...
};
function identifySearchEngine() {
const host = window.location.hostname;
if (host.includes('google.com')) return 'google';
if (host.includes('bing.com') && !window.location.pathname.includes('/images')) return 'bing';
if (host.includes('yahoo.com')) return 'yahoo';
if (host.includes('duckduckgo.com')) return 'duckduckgo';
// Add more as needed
return null;
}
async function startCrawling() {
if (isCrawlingFlag) {
Logger.log('이미 크롤링이 진행 중입니다.', 'warning');
return;
}
if (!Object.values(Config.settings.searchEngines).some(v => v)) {
Logger.log('사용할 검색 엔진이 하나도 선택되지 않았습니다.', 'error');
return;
}
isCrawlingFlag = true;
Config.saveSettings({ isCrawling: isCrawlingFlag });
Logger.log('크롤링을 시작합니다.', 'info');
UI.updateLogs();
if (!previousCrawls.some(crawl => crawl.status === '진행 중')) {
previousCrawls.push({ date: new Date().toLocaleString(), count: 0, status: '진행 중' });
GM_setValue('previousCrawls', JSON.stringify(previousCrawls));
UI.updatePreviousCrawlsUI();
}
setButtonStates();
await crawlPages(currentDepth);
// Navigation Observer는 페이지 변경을 감지하지 않습니다.
}
function stopCrawling() {
if (!isCrawlingFlag) {
Logger.log('크롤링이 진행 중이지 않습니다.', 'warning');
return;
}
isCrawlingFlag = false;
Config.saveSettings({ isCrawling: isCrawlingFlag });
Logger.log('크롤링이 중지되었습니다.', 'warning');
finalizeCrawl('중지됨');
UI.updateLogs();
setButtonStates();
}
function setButtonStates() {
$('#start-crawling').prop('disabled', isCrawlingFlag);
$('#stop-crawling').prop('disabled', !isCrawlingFlag);
}
async function crawlPages(depth) {
try {
while (isCrawlingFlag && currentPage <= totalPages && depth <= Config.settings.maxDepth) {
Logger.log(`페이지 ${currentPage} 크롤링 시작. (깊이: ${depth})`, 'info');
if (Config.settings.respectRobots && !(await Robots.checkRobotsTxt(window.location.href))) {
Logger.log(`robots.txt에 의해 크롤링이 금지된 페이지: ${window.location.href}`, 'warning');
break;
}
const searchEngine = identifySearchEngine();
if (!searchEngine || !searchEngineHandlers[searchEngine]) {
Logger.log(`지원되지 않는 검색 엔진: ${window.location.hostname}`, 'error');
break;
}
const handler = searchEngineHandlers[searchEngine];
const results = handler.extractResults(document);
if (!results) { Logger.log('검색 결과를 찾을 수 없습니다.', 'error'); break; }
results.forEach(result => {
if (!isCrawlingFlag) return;
const { name, url, description } = result;
if (shouldSkip(url, description)) return;
requestQueue.push({ url, depth });
if (activeRequests >= Config.settings.maxConcurrentRequests) return;
});
if (previousCrawls.length && previousCrawls[previousCrawls.length -1].status === '진행 중') {
previousCrawls[previousCrawls.length -1].count += results.length;
GM_setValue('previousCrawls', JSON.stringify(previousCrawls));
UI.updatePreviousCrawlsUI();
}
await processQueue();
progress = (currentPage / totalPages) * 100;
Config.saveSettings({ progress });
UI.updateLogs();
if (currentPage < totalPages && isCrawlingFlag) {
const nextUrl = handler.getNextPageUrl(document);
if (nextUrl) {
currentPage++;
Config.saveSettings({ currentPage });
depth++;
Config.saveSettings({ currentDepth: depth });
Logger.log(`다음 페이지로 이동: ${currentPage}`, 'info');
await Utils.delay(Config.settings.delay + Math.random() * Config.settings.delayRandom);
const nextPageContent = await Fetch.fetchPageContent(nextUrl);
if (nextPageContent) {
const parser = new DOMParser();
const doc = parser.parseFromString(nextPageContent, 'text/html');
// 현재 페이지의 내용을 변경하지 않고 데이터만 추출
handler.extractResults(doc).forEach(result => {
if (!isCrawlingFlag) return;
const { name, url, description } = result;
if (shouldSkip(url, description)) return;
requestQueue.push({ url, depth });
});
if (previousCrawls.length && previousCrawls[previousCrawls.length -1].status === '진행 중') {
previousCrawls[previousCrawls.length -1].count += handler.extractResults(doc).length;
GM_setValue('previousCrawls', JSON.stringify(previousCrawls));
UI.updatePreviousCrawlsUI();
}
await processQueue();
progress = (currentPage / totalPages) * 100;
Config.saveSettings({ progress });
UI.updateLogs();
continue;
} else {
Logger.log('다음 페이지 내용을 가져올 수 없습니다.', 'error');
break;
}
} else { Logger.log('다음 페이지 링크를 찾을 수 없습니다.', 'error'); break; }
} else { break; }
}
if (isCrawlingFlag && currentPage > totalPages && activeRequests === 0 && requestQueue.length === 0) {
Logger.log('크롤링이 완료되었습니다.', 'success');
finalizeCrawl('완료됨');
isCrawlingFlag = false;
Config.saveSettings({ isCrawling: isCrawlingFlag });
setButtonStates();
Config.saveSettings({ progress: 100 });
UI.updateLogs();
}
} catch (error) {
Logger.log(`크롤링 중 오류 발생: ${error.message}`, 'error');
finalizeCrawl('오류 발생');
}
}
function shouldSkip(url, desc) {
if (visitedUrls.has(url) || !Utils.isValidURL(url)) return true;
if (Config.settings.whitelist.length && !Config.settings.whitelist.some(d => url.includes(d))) return true;
if (Config.settings.blacklist.some(d => url.includes(d))) return true;
if (Config.settings.includeKeywords.length && !Config.settings.includeKeywords.some(k => url.includes(k) || desc.includes(k))) return true;
if (Config.settings.excludeKeywords.some(k => url.includes(k) || desc.includes(k))) return true;
if (Config.settings.regexInclude.length && !Config.settings.regexInclude.some(r => new RegExp(r).test(url) || new RegExp(r).test(desc))) return true;
if (Config.settings.regexExclude.length && Config.settings.regexExclude.some(r => new RegExp(r).test(url) || new RegExp(r).test(desc))) return true;
return false;
}
async function processQueue() {
while (requestQueue.length && activeRequests < Config.settings.maxConcurrentRequests && isCrawlingFlag) {
const { url, depth } = requestQueue.shift();
activeRequests++;
handleRequest(url, depth).finally(() => { activeRequests--; processQueue(); });
}
}
async function handleRequest(url, depth) {
if (!isCrawlingFlag || visitedUrls.has(url)) return;
try {
const response = await Fetch.fetchWithRetry(url, Config.settings.retryAttempts, Config.settings.retryDelay);
const contentType = Fetch.getContentType(response);
if (!Fetch.isContentTypeAllowed(contentType, Config.settings.contentTypes)) {
Logger.log(`허용되지 않은 콘텐츠 유형(${contentType})의 URL: ${url}`, 'warning');
return;
}
const parser = new DOMParser();
const doc = parser.parseFromString(response.responseText, 'text/html');
const text = doc.body?.innerText || '';
if (Config.settings.enableCaptchas && Robots.detectCaptcha(doc)) { await Robots.handleCaptcha(url); return; }
const wc = text.split(/\s+/).length;
if (wc < Config.settings.minWordCount || wc > Config.settings.maxWordCount) {
Logger.log(`단어 수 조건에 맞지 않는 URL: ${url} (${wc} 단어)`, 'warning');
return;
}
const quality = Evaluate.evaluateContentQuality(text);
const lang = doc.documentElement.lang || 'unknown';
const category = Classifier.classifyKeywords(text);
const meta = Extractor.extractMetaTags(doc);
const headings = Extractor.extractHeadings(doc);
if (category !== '기타' || quality > 100) {
const entry = { url, quality, language: lang, wordCount: wc, category };
Config.settings.dataFields.name && (entry.name = Extractor.extractName(doc) || 'No Title');
Config.settings.dataFields.description && (entry.description = Extractor.extractDescription(doc) || 'No Description');
Config.settings.dataFields.html && (entry.html = response.responseText);
Config.settings.dataFields.metaTags && (entry.metaTags = meta);
Config.settings.dataFields.headings && (entry.headings = headings);
data.push(entry);
GM_setValue('data', JSON.stringify(data));
UI.updateDataTable();
Logger.log(`데이터 수집 완료: ${url}`, 'success');
Config.settings.dataVisualization && DataVisualization.renderChart();
}
if (depth < Config.settings.maxDepth) {
Extractor.extractLinks(doc).forEach(link => { if (!visitedUrls.has(link) && Utils.isValidURL(link)) requestQueue.push({ url: link, depth: depth + 1 }); });
}
} catch (error) {
Logger.log(`데이터 수집 실패: ${url} - ${error.message}`, 'error');
}
visitedUrls.add(url);
GM_setValue('visitedUrls', JSON.stringify([...visitedUrls]));
}
function finalizeCrawl(status) {
if (previousCrawls.length) {
previousCrawls[previousCrawls.length -1].status = status;
GM_setValue('previousCrawls', JSON.stringify(previousCrawls));
UI.updatePreviousCrawlsUI();
}
if (navigationObserver) {
navigationObserver.disconnect();
navigationObserver = null;
}
}
function updateCrawlSettings() {
// Placeholder for any settings update needed during crawling
}
return {
startCrawling,
stopCrawling,
isCrawling: () => isCrawlingFlag,
updateCrawlSettings
};
})();
const Fetch = (() => {
async function fetchWithRetry(url, attempts, delayMs) {
for (let i = 1; i <= attempts; i++) {
try {
return await GM_xmlhttpRequestPromise(url);
} catch (e) {
Logger.log(`요청 실패 (${i}/${attempts}): ${url} - ${e.message}`, 'warning');
if (i < attempts) await Utils.delay(delayMs);
}
}
throw new Error('모든 재시도 시도가 실패했습니다.');
}
function GM_xmlhttpRequestPromise(url) {
return new Promise((resolve, reject) => {
let reqUrl = Config.settings.proxy ? `${Config.settings.proxy}?url=${encodeURIComponent(url)}` : url;
GM_xmlhttpRequest({
method: "GET",
url: reqUrl,
headers: { 'User-Agent': getCurrentUserAgent(), 'Accept': '*/*' },
timeout: Config.settings.timeout,
onload: res => (res.status >= 200 && res.status < 300) ? resolve(res) : reject(new Error(`HTTP ${res.status}`)),
onerror: () => reject(new Error('Request failed')),
ontimeout: () => reject(new Error('Request timed out'))
});
});
}
function getCurrentUserAgent() {
const index = Config.settings.userAgentIndex % Config.settings.userAgents.length;
return Config.settings.userAgents[index];
}
function getContentType(res) {
return res.responseHeaders.split('\n').find(h => h.toLowerCase().startsWith('content-type'))?.split(':')[1].trim().split(';')[0] || '';
}
function isContentTypeAllowed(ct, contentTypes) {
if (contentTypes.include.length && !contentTypes.include.includes(ct)) return false;
if (contentTypes.exclude.includes(ct)) return false;
return true;
}
async function fetchPageContent(url) {
try {
const response = await fetchWithRetry(url, Config.settings.retryAttempts, Config.settings.retryDelay);
return response.responseText;
} catch (error) {
Logger.log(`페이지 내용 가져오기 실패: ${url} - ${error.message}`, 'error');
return null;
}
}
return {
fetchWithRetry,
getCurrentUserAgent,
getContentType,
isContentTypeAllowed,
fetchPageContent
};
})();
const Robots = (() => {
async function checkRobotsTxt(url) {
try {
const parsed = new URL(url);
const robotsUrl = `${parsed.origin}/robots.txt`;
const res = await Fetch.fetchWithRetry(robotsUrl, 2, 2000);
return new RobotsParser(res.responseText).isAllowed(url, Fetch.getCurrentUserAgent());
} catch {
Logger.log('robots.txt 확인 실패, 기본 허용.', 'warning');
return true;
}
}
function detectCaptcha(doc) {
return !!doc.querySelector('iframe[src*="captcha"], form[action*="captcha"]');
}
async function handleCaptcha(url) {
Logger.log(`CAPTCHA 감지됨: ${url}`, 'warning');
await Utils.delay(5000);
Logger.log(`CAPTCHA 처리 완료: ${url}`, 'info');
}
class RobotsParser {
constructor(text) { this.rules = []; this.parse(text); }
parse(text) {
let agents = [];
text.split('\n').forEach(line => {
const [key, ...val] = line.split(':').map(s => s.trim());
if (!key) return;
if (key.toLowerCase() === 'user-agent') agents = [val.join(':').toLowerCase()];
else if (['disallow','allow'].includes(key.toLowerCase())) this.rules.push({ agents, type: key.toLowerCase(), path: val.join(':') });
});
}
isAllowed(url, ua) {
const parsedUrl = new URL(url);
const path = parsedUrl.pathname;
let allowed = true;
this.rules.forEach(rule => {
if (rule.agents.includes('*') || rule.agents.includes(ua.toLowerCase())) {
if (rule.type === 'disallow' && path.startsWith(rule.path)) allowed = false;
if (rule.type === 'allow' && path.startsWith(rule.path)) allowed = true;
}
});
return allowed;
}
}
return {
checkRobotsTxt,
detectCaptcha,
handleCaptcha
};
})();
const Extractor = (() => {
function extractMetaTags(doc) {
const metas = {};
doc.querySelectorAll('meta[name], meta[property]').forEach(meta => {
const name = meta.getAttribute('name') || meta.getAttribute('property');
const content = meta.getAttribute('content');
if (name && content) metas[name.toLowerCase()] = content;
});
return metas;
}
function extractHeadings(doc) {
const hs = [];
for (let i = 1; i <= 6; i++) doc.querySelectorAll(`h${i}`).forEach(h => hs.push(h.innerText.trim()));
return hs;
}
function extractName(doc) { return doc.querySelector('title')?.innerText || 'No Title'; }
function extractDescription(doc) { return doc.querySelector('meta[name="description"]')?.getAttribute('content') || 'No Description'; }
function extractLinks(doc) { return Array.from(doc.querySelectorAll('a[href]')).map(a => a.href).filter(Utils.isValidURL); }
return {
extractMetaTags,
extractHeadings,
extractName,
extractDescription,
extractLinks
};
})();
const Classifier = (() => {
function classifyKeywords(text) {
const kws = combineKeywords();
for (const [cat, keywords] of Object.entries(kws)) {
if (keywords.some(kw => text.includes(kw))) return cat;
}
return '기타';
}
function combineKeywords() {
const standard = {
'교육': ['학교', '교육', '학생', '교수', '강의'],
'기술': ['기술', '소프트웨어', '하드웨어', '프로그래밍', '개발'],
'뉴스': ['뉴스', '속보', '기사', '보도'],
'엔터테인먼트': ['영화', '음악', '연예', '게임', '드라마'],
'스포츠': ['축구', '야구', '농구', '경기', '토너먼트'],
'비즈니스': ['비즈니스', '경제', '주식', '투자', '시장'],
'건강': ['건강', '의료', '헬스', '운동', '영양'],
'과학': ['과학', '연구', '실험', '발견', '이론'],
'문학': ['소설', '시', '문학', '작가', '책'],
'여행': ['여행', '관광', '숙박', '비행기', '여권']
};
const custom = Config.settings.customKeywords || {};
for (const [cat, kws] of Object.entries(custom)) {
standard[cat] = standard[cat] ? [...new Set([...standard[cat], ...kws])] : kws;
}
return standard;
}
return {
classifyKeywords
};
})();
const Evaluate = (() => {
function evaluateContentQuality(text) { return text.split(/\s+/).length; }
return {
evaluateContentQuality
};
})();
const Scheduler = (() => {
let scheduleInterval = null;
function scheduleCrawling() {
clearInterval(scheduleInterval);
const now = new Date();
const [startHour, startMinute] = Config.settings.schedule.startTime.split(':').map(Number);
const startTime = new Date(now.getFullYear(), now.getMonth(), now.getDate(), startHour, startMinute, 0);
if (startTime < now) startTime.setDate(startTime.getDate() + 1);
const initialDelay = startTime - now;
setTimeout(() => {
if (Config.settings.schedule.specificDays.length === 0 || Config.settings.schedule.specificDays.includes(startTime.getDay())) {
Crawling.startCrawling();
}
scheduleInterval = setInterval(() => {
const currentDay = new Date().getDay();
if (Config.settings.schedule.specificDays.length === 0 || Config.settings.schedule.specificDays.includes(currentDay)) {
Crawling.startCrawling();
}
}, Config.settings.schedule.interval);
}, initialDelay);
Logger.log(`크롤링 스케줄이 설정되었습니다. 시작 시간: ${startTime.toLocaleString()}, 간격: ${Config.settings.schedule.interval / 60000}분`, 'info');
}
return {
scheduleCrawling
};
})();
const Testing = (() => {
function runTests() {
$('#test-modal').show();
$('#mocha').html('');
$('head').append('<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/mocha/10.2.0/mocha.min.css" />');
mocha.setup('bdd');
const assert = chai.assert;
describe('Utils Module', function() {
it('should escape HTML correctly', function() {
const input = '<div>Hello & "World"!</div>';
const expected = '<div>Hello & "World"!</div>';
assert.equal(Utils.escape(input, 'html'), expected);
});
it('should capitalize strings correctly', function() {
const input = 'test';
const expected = 'Test';
assert.equal(Utils.capitalize(input), expected);
});
it('should validate URLs correctly', function() {
assert.isTrue(Utils.isValidURL('https://www.example.com'));
assert.isFalse(Utils.isValidURL('htp:/invalid-url'));
});
});
describe('Config Module', function() {
it('should save and load settings correctly', function() {
const originalDelay = Config.settings.delay;
Config.saveSettings({ delay: 3000 });
assert.equal(Config.settings.delay, 3000);
Config.saveSettings({ delay: originalDelay });
});
it('should add and remove templates correctly', function() {
const templateName = 'TestTemplate';
Config.saveTemplate(templateName);
assert.property(Config.settings.templates, templateName);
Config.loadTemplate(templateName);
Config.settings.templates[templateName] = undefined;
delete Config.settings.templates[templateName];
assert.notProperty(Config.settings.templates, templateName);
});
});
describe('Logger Module', function() {
it('should log messages correctly', function() {
Logger.log('Test log message', 'info');
const logs = Logger.getLogs();
assert.isAtLeast(logs.length, 1);
assert.equal(logs[logs.length -1].message, 'Test log message');
});
it('should clear logs correctly', function() {
Logger.clearLogs();
assert.equal(Logger.getLogs().length, 0);
});
});
mocha.run();
}
return {
runTests
};
})();
function init() {
UI.createUI();
UI.updateUI();
if (Config.settings.dataVisualization) DataVisualization.renderChart();
if (Config.settings.schedule.enabled) Scheduler.scheduleCrawling();
if (Config.settings.isCrawling) {
Logger.log('크롤링 재개됨.', 'info');
Crawling.startCrawling();
} else {
Logger.log('크롤러 초기화됨.', 'info');
}
}
window.addEventListener('load', init);
})(); 이 ㅋㅗㄷㅡㅣㅇㅣㅅㅏㅇㅎㅏㄴ ㅈㅓㅁ ㄱㄱASSISTANT
안녕하세요! 제공해 주신 코드가 꽤 복잡하고 방대해 보입니다. 현재 어떤 문제를 겪고 계신지, 또는 어떤 도움을 필요로 하시는지 구체적으로 말씀해 주시면 더 효과적으로 도와드릴 수 있을 것 같습니다. 예를 들어: - 특정 오류 메시지가 발생하고 있나요? - 기능 중 원하는 대로 동작하지 않는 부분이 있나요? - 코드 최적화나 개선에 대한 조언이 필요하신가요? 원하시는 방향이나 문제점을 좀 더 자세히 알려주시면, 최대한 도와드리겠습니다!