AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-12 17:39:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(scrapeURL/pdf/mu): add timeout and created_at (#1570)

Browse Source
This commit is contained in:
Gergő Móricz 2025-05-19 21:36:15 +02:00 committed by GitHub
parent fab4f00536
commit 192d056bef
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
View File

@ -27,6 +27,8 @@ async function scrapePDFWithRunPodMU(
tempFilePath,
});
const preCacheCheckStartTime = Date.now();
try {
const cachedResult = await getPdfResultFromCache(base64Content);
@ -54,6 +56,8 @@ async function scrapePDFWithRunPodMU(
input: {
file_content: base64Content,
filename: path.basename(tempFilePath) + ".pdf",
timeout: timeToRun ? timeToRun - (Date.now() - preCacheCheckStartTime) : undefined,
created_at: Date.now(),
},
},
logger: meta.logger.child({
@ -103,6 +107,8 @@ export async function scrapePDF(
meta: Meta,
timeToRun: number | undefined,
): Promise<EngineScrapeResult> {
const startTime = Date.now();
if (!meta.options.parsePDF) {
if (meta.pdfPrefetch !== undefined && meta.pdfPrefetch !== null) {
const content = (await readFile(meta.pdfPrefetch.filePath)).toString("base64");
@ -167,7 +173,7 @@ export async function scrapePDF(
}),
},
tempFilePath,
timeToRun,
timeToRun ? (timeToRun - (Date.now() - startTime)) : undefined,
base64Content,
);
} catch (error) {