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
chore(api): export gdocs as HTML instead of PDF (#2652)
tomdca920257163
diff --git a/apps/api/src/scraper/scrapeURL/lib/rewriteUrl.ts b/apps/api/src/scraper/scrapeURL/lib/rewriteUrl.tsindex 9264c3238..1a56429f7 100644--- a/apps/api/src/scraper/scrapeURL/lib/rewriteUrl.ts+++ b/apps/api/src/scraper/scrapeURL/lib/rewriteUrl.ts@@ -11,7 +11,7 @@ export function rewriteUrl(url: string): string | undefined {}const id = url.match(/\/document\/d\/([-\w]+)/)?.[1];if (id) {- return `https://docs.google.com/document/d/${id}/export?format=pdf`;+ return `https://docs.google.com/document/d/${id}/export?format=html`;}} else if (url.startsWith("https://docs.google.com/presentation/d/") ||@@ -23,7 +23,7 @@ export function rewriteUrl(url: string): string | undefined {}const id = url.match(/\/presentation\/d\/([-\w]+)/)?.[1];if (id) {- return `https://docs.google.com/presentation/d/${id}/export?format=pdf`;+ return `https://docs.google.com/presentation/d/${id}/export?format=html`;}} else if (url.startsWith("https://drive.google.com/file/d/") ||