Creepso/webstreamr-github
1
0
Fork 0
Code Issues 27 Pull requests 7 Projects Releases 240 Packages Wiki Activity Actions

Keep using /d/ URL but get last iframe url match

Browse source
This commit is contained in:
WebStreamr 2025-12-18 15:01:07 +00:00
parent 90e0315f8a
commit b725354c1d
No known key found for this signature in database
1 changed files with 5 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
src/extractor/FileMoon.ts
View file

@ -42,10 +42,7 @@ export class FileMoon extends Extractor {
}
public override normalize(url: URL): URL {
if (url.pathname.startsWith('/d/')) {
return new URL(url.href.replace('/d/', '/e/'));
}
return url;
return new URL(url.href.replace('/e/', '/d/'));
}
protected async extractInternal(ctx: Context, url: URL, meta: Meta, originalUrl?: URL): Promise<UrlResult[]> {
@ -60,9 +57,10 @@ export class FileMoon extends Extractor {
const $ = cheerio.load(html);
const title = $('h3').text().trim();
const iframeUrlMatch = html.match(/iframe.*?src=["'](.*?)["']/);
if (iframeUrlMatch && iframeUrlMatch[1]) {
return await this.extractInternal(ctx, new URL(iframeUrlMatch[1]), { title, ...meta }, url);
const iframeUrlMatches = Array.from(html.matchAll(/iframe.*?src=["'](.*?)["']/g));
if (iframeUrlMatches.length) {
// Use last match because there can be fake adblock catcher urls before
return await this.extractInternal(ctx, new URL((iframeUrlMatches[iframeUrlMatches.length - 1] as RegExpExecArray)[1] as string), { title, ...meta }, url);
}
const playlistUrl = await buildMediaFlowProxyExtractorStreamUrl(ctx, this.fetcher, 'FileMoon', originalUrl as URL, headers);