geckon01/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-06-12 05:04:00 +03:00
Code Issues Packages Projects Releases Wiki Activity

Youtube loader whitespace fix (#2051)

Browse Source 
youtube loader whitespace fix
This commit is contained in:
Sean Hatfield
2024-08-06 10:16:17 -07:00
committed by GitHub
parent f787502755
commit be3b0b4916
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
collector/utils/extensions/YoutubeTranscript/YoutubeLoader/youtube-transcript.js
View File

@@ -47,10 +47,12 @@ class YoutubeTranscript {
let transcript = "";
const chunks = transcriptXML.getElementsByTagName("text");
for (const chunk of chunks) {
transcript += chunk.textContent;
// Add space after each text chunk
transcript += chunk.textContent + " ";
}
return transcript;
// Trim extra whitespace
return transcript.trim().replace(/\s+/g, " ");
} catch (e) {
throw new YoutubeTranscriptError(e);
}