AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-12 14:19:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(map): do not remove query parameters from results (FIR-1015) (#1191)

Browse Source 
* fix(map): do not remove query parameters from results

* feat(map): add tests for query parameter handling
This commit is contained in:
Gergő Móricz 2025-02-17 16:34:58 +01:00 committed by GitHub
parent 5cb2918368
commit 7ecbff3b20
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 21 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
apps/api/src/__tests__/snips/map.test.ts
View File

@ -39,4 +39,24 @@ describe("Map tests", () => {
expect(response.body.success).toBe(false); expect(response.body.success).toBe(false);
expect(response.body.error).toBe("Request timed out"); expect(response.body.error).toBe("Request timed out");
}, 10000); }, 10000);
it("handles query parameters correctly", async () => {
let response = await map({
url: "https://www.hfea.gov.uk",
sitemapOnly: true,
});
expect(response.statusCode).toBe(200);
expect(response.body.success).toBe(true);
expect(response.body.links.some(x => x.match(/^https:\/\/www\.hfea\.gov\.uk\/choose-a-clinic\/clinic-search\/results\/?\?options=\d+$/))).toBe(true);
response = await map({
url: "https://www.hfea.gov.uk",
ignoreSitemap: false,
});
expect(response.statusCode).toBe(200);
expect(response.body.success).toBe(true);
expect(response.body.links.some(x => x.match(/^https:\/\/www\.hfea\.gov\.uk\/choose-a-clinic\/clinic-search\/results\/?\?options=\d+$/))).toBe(true);
}, 300000); // TODO: mocks
}); });

2
apps/api/src/lib/validateUrl.ts
View File

@ -147,7 +147,7 @@ export const checkAndUpdateURLForMap = (url: string) => {
} }
// remove any query params // remove any query params
url = url.split("?")[0].trim(); // url = url.split("?")[0].trim();
return { urlObj: typedUrlObj, url: url }; return { urlObj: typedUrlObj, url: url };
}; };