rixty/SillyTavern
1
0
Fork 0
mirror of https://github.com/SillyTavern/SillyTavern.git synced 2025-06-05 21:59:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add prerequisites for websearch extension

Browse Source
This commit is contained in:
Cohee
2023-12-12 01:08:47 +02:00
parent 1b11ddc26a
commit 299749a4e7
5 changed files with 69 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
public/scripts/utils.js
View File

@@ -1143,11 +1143,13 @@ export async function extractTextFromPDF(blob) {
* @param {Blob} blob HTML content blob
* @returns {Promise<string>} A promise that resolves to the parsed text.
*/
export async function extractTextFromHTML(blob) {
export async function extractTextFromHTML(blob, textSelector = 'body') {
const html = await blob.text();
const domParser = new DOMParser();
const document = domParser.parseFromString(DOMPurify.sanitize(html), 'text/html');
const text = postProcessText(document.body.textContent);
const elements = document.querySelectorAll(textSelector);
const rawText = Array.from(elements).map(e => e.textContent).join('\n');
const text = postProcessText(rawText);
return text;
}