GitHub-Proxy/jina_reader
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/jina-ai/reader.git synced 2025-08-19 05:05:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: remove select element from markdown to walk around turndown performance issue

Browse Source
This commit is contained in:
Yanlong Wang 2024-08-09 10:55:36 +08:00
parent e4ef6cb0f9
commit eb74e9c6f8
No known key found for this signature in database
GPG Key ID: C0A623C0BADF9F37
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
backend/functions/src/cloud-functions/crawler.ts
View File

@ -151,7 +151,7 @@ export class CrawlerHost extends RPCHost {
} as any);
if (!options?.noRules) {
turnDownService.addRule('remove-irrelevant', {
filter: ['meta', 'style', 'script', 'noscript', 'link', 'textarea'],
filter: ['meta', 'style', 'script', 'noscript', 'link', 'textarea', 'select'],
replacement: () => ''
});
turnDownService.addRule('truncate-svg', {