AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-13 08:29:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' of https://github.com/mendableai/firecrawl

Browse Source
This commit is contained in:
rafaelmmiller 2025-01-27 14:31:18 -03:00
commit ad06cde422
2 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
apps/api/sharedLibs/html-transformer/src/lib.rs
View File

@ -128,7 +128,9 @@ pub unsafe extern "C" fn extract_metadata(html: *const libc::c_char) -> *mut i8
if let Some(v) = out.get(name) { if let Some(v) = out.get(name) {
match v { match v {
Value::String(_) => { Value::String(_) => {
out.insert(name.to_string(), Value::Array(vec! [v.clone(), Value::String(content.to_string())])); if name != "title" { // preserve title tag in metadata
out.insert(name.to_string(), Value::Array(vec! [v.clone(), Value::String(content.to_string())]));
}
}, },
Value::Array(_) => { Value::Array(_) => {
match out.get_mut(name) { match out.get_mut(name) {

2
apps/api/src/controllers/v1/types.ts
View File

@ -34,7 +34,7 @@ export const url = z.preprocess(
.url() .url()
.regex(/^https?:\/\//, "URL uses unsupported protocol") .regex(/^https?:\/\//, "URL uses unsupported protocol")
.refine( .refine(
(x) => /\.[a-z]{2,}(:\d+)?([\/?#]|$)/i.test(x), (x) => /\.[a-zA-Z\u0400-\u04FF\u0500-\u052F\u2DE0-\u2DFF\uA640-\uA69F]{2,}(:\d+)?([\/?#]|$)/i.test(x),
"URL must have a valid top-level domain or be a valid path", "URL must have a valid top-level domain or be a valid path",
) )
.refine((x) => { .refine((x) => {