Last active
December 19, 2023 04:42
-
-
Save agucova/ebafb6743225efaeb9acb1f888757468 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// Clean and simplify HTML | |
function cleanHTML(html: string): string { | |
const div = document.createElement('div'); | |
div.innerHTML = html; | |
// Remove all class attributes and data-* attributes | |
div.querySelectorAll('*').forEach(el => { | |
el.removeAttribute('class'); | |
Array.from(el.attributes).forEach(attr => { | |
if (attr.name.startsWith('data-')) { | |
el.removeAttribute(attr.name); | |
} | |
}); | |
}); | |
// Remove contents of <header> tags | |
div.querySelectorAll('header').forEach(el => el.remove()); | |
// Only keep specific tags supported by Anki | |
const allowedTags = ['p', 'strong', 'sup', 'sub', 'em', 'img', 'ul', 'ol', 'li']; | |
div.querySelectorAll('*').forEach(el => { | |
if (!allowedTags.includes(el.tagName.toLowerCase())) { | |
el.replaceWith(...el.childNodes); | |
} | |
}); | |
return div.innerHTML; | |
} | |
// Function to escape CSV string | |
function escapeCSV(str: string): string { | |
const escapedStr = str.replace(/"/g, '""'); | |
return `"${escapedStr}"`; | |
} | |
// Scrape cards and prepare CSV | |
function scrapeAndPrepareCSV(): string { | |
const rows: string[] = []; | |
rows.push("Question,Answer"); | |
const cardRows = document.querySelectorAll('.smart-card-row'); | |
for (const row of cardRows) { | |
const questionFace = row.querySelector('.question-face'); | |
const answerFace = row.querySelector('.answer-face'); | |
if (!questionFace || !answerFace) continue; | |
const question = cleanHTML(questionFace.innerHTML); | |
const answer = cleanHTML(answerFace.innerHTML); | |
rows.push(`${escapeCSV(question)},${escapeCSV(answer)}`); | |
} | |
return rows.join('\n'); | |
} | |
// Function to get deck and pack names for the filename | |
function getFilename(): string { | |
const deckElement = document.querySelector('.deck-name'); | |
const packElement = document.querySelector('.deck-detail-header .pack-name'); | |
let filename = 'anki_flashcards'; | |
if (deckElement) { | |
filename = deckElement.innerHTML.trim(); | |
} | |
if (packElement) { | |
const packName = packElement.innerHTML.trim(); | |
filename = `${packName}_${filename}`; | |
} | |
return `${filename}.csv`; | |
} | |
// Function to trigger file download | |
function downloadCSV(csvString: string, filename: string): void { | |
const blob = new Blob([csvString], { type: 'text/csv;charset=utf-8;' }); | |
const link = document.createElement('a'); | |
const url = URL.createObjectURL(blob); | |
link.setAttribute('href', url); | |
link.setAttribute('download', filename); | |
link.style.visibility = 'hidden'; | |
document.body.appendChild(link); | |
link.click(); | |
document.body.removeChild(link); | |
URL.revokeObjectURL(url); | |
} | |
downloadCSV(scrapeAndPrepareCSV(), getFilename()); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment