LemmyNet/lemmy
2
0
Fork 0
mirror of https://github.com/LemmyNet/lemmy.git synced 2024-11-22 12:21:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Adding back in doctype check.

Browse source
This commit is contained in:
Dessalines 2024-08-03 09:22:44 -04:00
parent b60e511493
commit b93f76b157
1 changed files with 12 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
crates/api_common/src/request.rs
View file

@ -184,6 +184,18 @@ pub async fn generate_post_link_metadata(
fn extract_opengraph_data(html_bytes: &[u8], url: &Url) -> LemmyResult<OpenGraphData> {
let html = String::from_utf8_lossy(html_bytes);
// Make sure the first line is doctype html
let first_line = html
.trim_start()
.lines()
.next()
.ok_or(LemmyErrorType::NoLinesInHtml)?
.to_lowercase();
if !first_line.starts_with("<!doctype html") {
Err(LemmyErrorType::SiteMetadataPageIsNotDoctypeHtml)?
}
let mut page = HTML::from_string(html.to_string(), None)?;
// If the web page specifies that it isn't actually UTF-8, re-decode the received bytes with the