AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-04 16:30:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update pdfProcessor.ts

Browse Source
This commit is contained in:
Nicolas 2024-07-26 17:21:09 -04:00
parent 542270f4c2
commit ff4266f09e
1 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
apps/api/src/scraper/WebScraper/utils/pdfProcessor.ts
View File

@ -12,10 +12,15 @@ import { Logger } from "../../../lib/logger";
dotenv.config(); dotenv.config();
export async function fetchAndProcessPdf(url: string, parsePDF: boolean): Promise<{ content: string, pageStatusCode?: number, pageError?: string }> { export async function fetchAndProcessPdf(url: string, parsePDF: boolean): Promise<{ content: string, pageStatusCode?: number, pageError?: string }> {
try {
const { tempFilePath, pageStatusCode, pageError } = await downloadPdf(url); const { tempFilePath, pageStatusCode, pageError } = await downloadPdf(url);
const content = await processPdfToText(tempFilePath, parsePDF); const content = await processPdfToText(tempFilePath, parsePDF);
fs.unlinkSync(tempFilePath); // Clean up the temporary file fs.unlinkSync(tempFilePath); // Clean up the temporary file
return { content, pageStatusCode, pageError }; return { content, pageStatusCode, pageError };
} catch (error) {
Logger.error(`Failed to fetch and process PDF: ${error.message}`);
return { content: "", pageStatusCode: 500, pageError: error.message };
}
} }
async function downloadPdf(url: string): Promise<{ tempFilePath: string, pageStatusCode?: number, pageError?: string }> { async function downloadPdf(url: string): Promise<{ tempFilePath: string, pageStatusCode?: number, pageError?: string }> {