github/v-firecrawl
github/v-firecrawl
0
Fork 0
Code Actions

[feat] improved the scrape for gdrive pdfs

Browse Source
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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
apps/api/src/scraper/WebScraper/custom/handleCustomScraping.ts
View File

@ -1,7 +1,9 @@
import { fetchAndProcessPdf } from "../utils/pdfProcessor";
export async function handleCustomScraping(
text: string,
url: string
): Promise<{ scraper: string; url: string; wait_after_load: number } | null> {
): Promise<{ scraper: string; url: string; wait_after_load?: number } | null> {
// Check for Readme Docs special case
if (text.includes('<meta name="readme-deploy"')) {
console.log(
@ -28,18 +30,21 @@ export async function handleCustomScraping(
// Check for Google Drive PDF links in the raw HTML
const googleDrivePdfPattern =
/https:\/\/drive\.google\.com\/file\/d\/[^\/]+\/view/;
/https:\/\/drive\.google\.com\/file\/d\/([^\/]+)\/view/;
const googleDrivePdfLink = text.match(googleDrivePdfPattern);
if (googleDrivePdfLink) {
console.log(
`Google Drive PDF link detected for ${url}: ${googleDrivePdfLink[0]}`
);
const fileId = googleDrivePdfLink[1];
const pdfUrl = `https://drive.google.com/uc?export=download&id=${fileId}`;
return {
scraper: "fire-engine",
url: url,
wait_after_load: 1000,
scraper: "pdf",
url: pdfUrl
};
}
return null;
}

9
apps/api/src/scraper/WebScraper/single_url.ts
View File

@ -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) {