AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-12 22:49:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(rust): further select fixes

Browse Source
This commit is contained in:
Gergő Móricz 2025-01-25 18:48:40 +01:00
parent 02caa72f02
commit 4d8f4109b5
1 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
apps/api/sharedLibs/html-transformer/src/lib.rs
View File

@ -268,7 +268,8 @@ fn _transform_html_inner(opts: TranformHTMLOptions) -> Result<String, ()> {
} }
} }
for img in document.select("img[srcset]")? { let srcset_images: Vec<_> = document.select("img[srcset]")?.collect();
for img in srcset_images {
let mut sizes: Vec<ImageSource> = img.attributes.borrow().get("srcset").ok_or(())?.split(",").filter_map(|x| { let mut sizes: Vec<ImageSource> = img.attributes.borrow().get("srcset").ok_or(())?.split(",").filter_map(|x| {
let tok: Vec<&str> = x.trim().split(" ").collect(); let tok: Vec<&str> = x.trim().split(" ").collect();
let tok_1 = if tok.len() > 1 && !tok[1].is_empty() { let tok_1 = if tok.len() > 1 && !tok[1].is_empty() {
@ -306,14 +307,16 @@ fn _transform_html_inner(opts: TranformHTMLOptions) -> Result<String, ()> {
let url = Url::parse(&opts.url).map_err(|_| ())?; let url = Url::parse(&opts.url).map_err(|_| ())?;
for img in document.select("img[src]")? { let src_images: Vec<_> = document.select("img[src]")?.collect();
for img in src_images {
let old = img.attributes.borrow().get("src").map(|x| x.to_string()).ok_or(())?; let old = img.attributes.borrow().get("src").map(|x| x.to_string()).ok_or(())?;
if let Ok(new) = url.join(&old) { if let Ok(new) = url.join(&old) {
img.attributes.borrow_mut().insert("src", new.to_string()); img.attributes.borrow_mut().insert("src", new.to_string());
} }
} }
for anchor in document.select("a[href]")? { let href_anchors: Vec<_> = document.select("a[href]")?.collect();
for anchor in href_anchors {
let old = anchor.attributes.borrow().get("href").map(|x| x.to_string()).ok_or(())?; let old = anchor.attributes.borrow().get("href").map(|x| x.to_string()).ok_or(())?;
if let Ok(new) = url.join(&old) { if let Ok(new) = url.join(&old) {
anchor.attributes.borrow_mut().insert("href", new.to_string()); anchor.attributes.borrow_mut().insert("href", new.to_string());