Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
TypeScript aiai-agentsai-crawlerai-scrapingai-searchcrawlerdata-extractionhtml-to-markdownllmmarkdownscraperscrapingweb-crawlerweb-dataweb-data-extractionweb-scraperweb-scrapingweb-searchwebscraping
feat(scrape): support Google Slides (#1693)
Meet Soni2082243cb50c
diff --git a/apps/api/src/__tests__/snips/scrape.test.ts b/apps/api/src/__tests__/snips/scrape.test.tsindex 3a2f0e796..27ea6b2a7 100644--- a/apps/api/src/__tests__/snips/scrape.test.ts+++ b/apps/api/src/__tests__/snips/scrape.test.ts@@ -777,6 +777,15 @@ describe("Scrape tests", () => {expect(response.markdown).toContain("This is a test to confirm Google Docs scraping abilities.");}, 310000);++ it.concurrent("scrapes Google Slides links as PDFs", async () => {+ const response = await scrape({+ url: "https://docs.google.com/presentation/d/1pDKL1UULpr6siq_eVWE1hjqt5MKCgSSuKS_MWahnHAQ/view",+ timeout: 300000,+ });++ expect(response.markdown).toContain("This is a test to confirm Google Slides scraping abilities.");+ }, 310000);});}diff --git a/apps/api/src/scraper/scrapeURL/index.ts b/apps/api/src/scraper/scrapeURL/index.tsindex a2a822d6f..65b697b42 100644--- a/apps/api/src/scraper/scrapeURL/index.ts+++ b/apps/api/src/scraper/scrapeURL/index.ts@@ -163,6 +163,11 @@ async function buildMetaObject(if (id) {rewrittenUrl = `https://docs.google.com/document/d/${id}/export?format=pdf`;}+ } else if (url.startsWith("https://docs.google.com/presentation/d/") || url.startsWith("http://docs.google.com/presentation/d/")) {+ const id = url.match(/\/presentation\/d\/([-\w]+)/)?.[1];+ if (id) {+ rewrittenUrl = `https://docs.google.com/presentation/d/${id}/export?format=pdf`;+ }}return {