[feat] improved the scrape for gdrive pdfs

This commit is contained in:
rafaelsideguide
2024-06-04 17:47:28 -03:00
parent a547f9a78e
commit b5045d1661
2 changed files with 18 additions and 8 deletions
@@ -331,8 +331,13 @@ export async function scrapSingleUrl(
// Check for custom scraping conditions
const customScraperResult = await handleCustomScraping(text, url);
if(customScraperResult){
customScrapedContent = await scrapWithFireEngine(customScraperResult.url, customScraperResult.wait_after_load)
if (customScraperResult){
switch (customScraperResult.scraper) {
case "fire-engine":
customScrapedContent = await scrapWithFireEngine(customScraperResult.url, customScraperResult.wait_after_load)
case "pdf":
customScrapedContent = { html: await fetchAndProcessPdf(customScraperResult.url), screenshot }
}
}
if (customScrapedContent) {