Austin/firecrawl
1
0
Fork 0
mirror of https://github.com/mendableai/firecrawl.git synced 2024-11-16 11:42:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Fixed PDF match custom scraping

Browse Source 
Now it's working for both `https://getgc.ai/privacy` and `https://prairie.cards/products/wood-designs` usecases.
This commit is contained in:
rafaelsideguide 2024-07-02 11:25:17 -03:00
parent 96de948d6b
commit 0175152577
1 changed files with 15 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
apps/api/src/scraper/WebScraper/custom/handleCustomScraping.ts
View File

@ -29,22 +29,23 @@ export async function handleCustomScraping(
};
}
// Check for Google Drive PDF links in the raw HTML
const googleDrivePdfPattern =
/https:\/\/drive\.google\.com\/file\/d\/([^\/]+)\/view/;
const googleDrivePdfLink = url.match(googleDrivePdfPattern);
if (googleDrivePdfLink) {
console.log(
`Google Drive PDF link detected for ${url}: ${googleDrivePdfLink[0]}`
);
// Check for Google Drive PDF links in meta tags
const googleDriveMetaPattern = /<meta itemprop="url" content="(https:\/\/drive\.google\.com\/file\/d\/[^"]+)"/;
const googleDriveMetaMatch = text.match(googleDriveMetaPattern);
if (googleDriveMetaMatch) {
const url = googleDriveMetaMatch[1];
console.log(`Google Drive PDF link detected: ${url}`);
const fileId = googleDrivePdfLink[1];
const pdfUrl = `https://drive.google.com/uc?export=download&id=${fileId}`;
const fileIdMatch = url.match(/https:\/\/drive\.google\.com\/file\/d\/([^\/]+)\/view/);
if (fileIdMatch) {
const fileId = fileIdMatch[1];
const pdfUrl = `https://drive.google.com/uc?export=download&id=${fileId}`;
return {
scraper: "pdf",
url: pdfUrl
};
return {
scraper: "pdf",
url: pdfUrl
};
}
}
return null;