Merge branch 'dev' into vidsrcto

src/dev-cli/scraper.ts

@@ -41,6 +41,7 @@ async function runBrowserScraping(
       args: ['--no-sandbox', '--disable-setuid-sandbox'],
     });
     const page = await browser.newPage();
+    page.on('console', (message) => console.log(`${message.type().slice(0, 3).toUpperCase()} ${message.text()}`));
     await page.goto(server.resolvedUrls.local[0]);
     await page.waitForFunction('!!window.scrape', { timeout: 5000 });
 

src/dev-cli/validate.ts

@@ -81,6 +81,7 @@ export async function processOptions(sources: Array<Embed | Sourcerer>, options:
   const providerOptions: ProviderMakerOptions = {
     fetcher,
     target: targets.ANY,
+    consistentIpForRequests: true,
   };
 
   return {

src/entrypoint/providers.ts

@@ -2,9 +2,9 @@ import { gatherAllEmbeds, gatherAllSources } from '@/providers/all';
 import { Embed, Sourcerer } from '@/providers/base';
 
 export function getBuiltinSources(): Sourcerer[] {
-  return gatherAllSources();
+  return gatherAllSources().filter((v) => !v.disabled);
 }
 
 export function getBuiltinEmbeds(): Embed[] {
-  return gatherAllEmbeds();
+  return gatherAllEmbeds().filter((v) => !v.disabled);
 }

src/fetchers/types.ts

@@ -4,7 +4,7 @@ export type FetcherOptions = {
   baseUrl?: string;
   headers?: Record<string, string>;
   query?: Record<string, string>;
-  method?: 'GET' | 'POST';
+  method?: 'HEAD' | 'GET' | 'POST';
   readHeaders?: string[];
   body?: Record<string, any> | string | FormData | URLSearchParams;
 };
@@ -17,7 +17,7 @@ export type DefaultedFetcherOptions = {
   headers: Record<string, string>;
   query: Record<string, string>;
   readHeaders: string[];
-  method: 'GET' | 'POST';
+  method: 'HEAD' | 'GET' | 'POST';
 };
 
 export type FetcherResponse<T = any> = {
@@ -28,12 +28,12 @@ export type FetcherResponse<T = any> = {
 };
 
 // This is the version that will be inputted by library users
-export type Fetcher<T = any> = {
-  (url: string, ops: DefaultedFetcherOptions): Promise<FetcherResponse<T>>;
+export type Fetcher = {
+  <T = any>(url: string, ops: DefaultedFetcherOptions): Promise<FetcherResponse<T>>;
 };
 
 // This is the version that scrapers will be interacting with
-export type UseableFetcher<T = any> = {
-  (url: string, ops?: FetcherOptions): Promise<T>;
-  full: (url: string, ops?: FetcherOptions) => Promise<FetcherResponse<T>>;
+export type UseableFetcher = {
+  <T = any>(url: string, ops?: FetcherOptions): Promise<T>;
+  full: <T = any>(url: string, ops?: FetcherOptions) => Promise<FetcherResponse<T>>;
 };

src/index.ts

@@ -1,6 +1,6 @@
 export type { EmbedOutput, SourcererOutput } from '@/providers/base';
 export type { Stream, StreamFile, FileBasedStream, HlsBasedStream, Qualities } from '@/providers/streams';
-export type { Fetcher, FetcherOptions, FetcherResponse } from '@/fetchers/types';
+export type { Fetcher, DefaultedFetcherOptions, FetcherOptions, FetcherResponse } from '@/fetchers/types';
 export type { RunOutput } from '@/runners/runner';
 export type { MetaOutput } from '@/entrypoint/utils/meta';
 export type { FullScraperEvents } from '@/entrypoint/utils/events';
@@ -9,6 +9,8 @@ export type { MediaTypes, ShowMedia, ScrapeMedia, MovieMedia } from '@/entrypoin
 export type { ProviderControls, RunnerOptions, EmbedRunnerOptions, SourceRunnerOptions } from '@/entrypoint/controls';
 export type { ProviderBuilder } from '@/entrypoint/builder';
 export type { ProviderMakerOptions } from '@/entrypoint/declare';
+export type { MovieScrapeContext, ShowScrapeContext, EmbedScrapeContext, ScrapeContext } from '@/utils/context';
+export type { SourcererOptions, EmbedOptions } from '@/providers/base';
 
 export { NotFoundError } from '@/utils/errors';
 export { makeProviders } from '@/entrypoint/declare';

src/providers/all.ts

@@ -3,15 +3,18 @@ import { febboxHlsScraper } from '@/providers/embeds/febbox/hls';
 import { febboxMp4Scraper } from '@/providers/embeds/febbox/mp4';
 import { mixdropScraper } from '@/providers/embeds/mixdrop';
 import { mp4uploadScraper } from '@/providers/embeds/mp4upload';
+import { streambucketScraper } from '@/providers/embeds/streambucket';
 import { streamsbScraper } from '@/providers/embeds/streamsb';
 import { upcloudScraper } from '@/providers/embeds/upcloud';
 import { upstreamScraper } from '@/providers/embeds/upstream';
+import { vidsrcembedScraper } from '@/providers/embeds/vidsrc';
 import { flixhqScraper } from '@/providers/sources/flixhq/index';
 import { goMoviesScraper } from '@/providers/sources/gomovies/index';
 import { kissAsianScraper } from '@/providers/sources/kissasian/index';
 import { lookmovieScraper } from '@/providers/sources/lookmovie';
 import { remotestreamScraper } from '@/providers/sources/remotestream';
 import { showboxScraper } from '@/providers/sources/showbox/index';
+import { vidsrcScraper } from '@/providers/sources/vidsrc/index';
 import { zoechipScraper } from '@/providers/sources/zoechip';
 
 import { fileMoonScraper } from './embeds/filemoon';
@@ -30,6 +33,7 @@ export function gatherAllSources(): Array<Sourcerer> {
     showboxScraper,
     goMoviesScraper,
     zoechipScraper,
+    vidsrcScraper,
     lookmovieScraper,
     smashyStreamScraper,
     vidSrcToScraper,
@@ -46,6 +50,8 @@ export function gatherAllEmbeds(): Array<Embed> {
     febboxMp4Scraper,
     febboxHlsScraper,
     mixdropScraper,
+    vidsrcembedScraper,
+    streambucketScraper,
     smashyStreamFScraper,
     smashyStreamDScraper,
     fileMoonScraper,

src/providers/embeds/febbox/hls.ts

@@ -1,5 +1,4 @@
 import { MediaTypes } from '@/entrypoint/utils/media';
-import { flags } from '@/entrypoint/utils/targets';
 import { makeEmbed } from '@/providers/base';
 import { parseInputUrl } from '@/providers/embeds/febbox/common';
 import { getStreams } from '@/providers/embeds/febbox/fileList';
@@ -16,6 +15,7 @@ export const febboxHlsScraper = makeEmbed({
   id: 'febbox-hls',
   name: 'Febbox (HLS)',
   rank: 160,
+  disabled: true,
   async scrape(ctx) {
     const { type, id, season, episode } = parseInputUrl(ctx.url);
     const sharelinkResult = await ctx.proxiedFetcher<{
@@ -40,7 +40,7 @@ export const febboxHlsScraper = makeEmbed({
         {
           id: 'primary',
           type: 'hls',
-          flags: [flags.CORS_ALLOWED],
+          flags: [],
           captions: await getSubtitles(ctx, id, firstStream.fid, type as MediaTypes, season, episode),
           playlist: `https://www.febbox.com/hls/main/${firstStream.oss_fid}.m3u8`,
         },

src/providers/embeds/febbox/qualities.ts

@@ -4,24 +4,35 @@ import { ScrapeContext } from '@/utils/context';
 
 const allowedQualities = ['360', '480', '720', '1080', '4k'];
 
-export async function getStreamQualities(ctx: ScrapeContext, apiQuery: object) {
-  const mediaRes: { list: { path: string; quality: string; fid?: number }[] } = (await sendRequest(ctx, apiQuery)).data;
+interface FebboxQuality {
+  path: string;
+  real_quality: string;
+  fid?: number;
+}
 
-  const qualityMap = mediaRes.list
-    .filter((file) => allowedQualities.includes(file.quality.replace('p', '')))
-    .map((file) => ({
-      url: file.path,
-      quality: file.quality.replace('p', ''),
-    }));
+function mapToQuality(quality: FebboxQuality): FebboxQuality | null {
+  const q = quality.real_quality.replace('p', '').toLowerCase();
+  if (!allowedQualities.includes(q)) return null;
+  return {
+    real_quality: q,
+    path: quality.path,
+    fid: quality.fid,
+  };
+}
+
+export async function getStreamQualities(ctx: ScrapeContext, apiQuery: object) {
+  const mediaRes: { list: FebboxQuality[] } = (await sendRequest(ctx, apiQuery)).data;
+
+  const qualityMap = mediaRes.list.map((v) => mapToQuality(v)).filter((v): v is FebboxQuality => !!v);
 
   const qualities: Record<string, StreamFile> = {};
 
   allowedQualities.forEach((quality) => {
-    const foundQuality = qualityMap.find((q) => q.quality === quality);
-    if (foundQuality && foundQuality.url) {
+    const foundQuality = qualityMap.find((q) => q.real_quality === quality && q.path);
+    if (foundQuality) {
       qualities[quality] = {
         type: 'mp4',
-        url: foundQuality.url,
+        url: foundQuality.path,
       };
     }
   });

src/providers/embeds/febbox/subtitles.ts

@@ -37,22 +37,28 @@ export async function getSubtitles(
   const subResult = (await sendRequest(ctx, subtitleApiQuery)) as CaptionApiResponse;
   const subtitleList = subResult.data.list;
   const output: Caption[] = [];
+  const languagesAdded: Record<string, true> = {};
 
   subtitleList.forEach((sub) => {
     const subtitle = sub.subtitles.sort((a, b) => b.order - a.order)[0];
     if (!subtitle) return;
+
     const subtitleFilePath = subtitle.file_path
       .replace(captionsDomains[0], captionsDomains[1])
       .replace(/\s/g, '+')
       .replace(/[()]/g, (c) => {
         return `%${c.charCodeAt(0).toString(16)}`;
       });
+
     const subtitleType = getCaptionTypeFromUrl(subtitleFilePath);
     if (!subtitleType) return;
 
     const validCode = isValidLanguageCode(subtitle.lang);
     if (!validCode) return;
 
+    if (languagesAdded[subtitle.lang]) return;
+    languagesAdded[subtitle.lang] = true;
+
     output.push({
       id: subtitleFilePath,
       language: subtitle.lang,

src/providers/embeds/streambucket.ts

@@ -0,0 +1,101 @@
+import { flags } from '@/entrypoint/utils/targets';
+import { makeEmbed } from '@/providers/base';
+
+// StreamBucket makes use of https://github.com/nicxlau/hunter-php-javascript-obfuscator
+
+const hunterRegex = /eval\(function\(h,u,n,t,e,r\).*?\("(.*?)",\d*?,"(.*?)",(\d*?),(\d*?),\d*?\)\)/;
+const linkRegex = /file:"(.*?)"/;
+
+// This is a much more simple and optimized version of the "h,u,n,t,e,r"
+// obfuscation algorithm. It's just basic chunked+mask encoding.
+// I have seen this same encoding used on some sites under the name
+// "p,l,a,y,e,r" as well
+function decodeHunter(encoded: string, mask: string, charCodeOffset: number, delimiterOffset: number) {
+  // The encoded string is made up of 'n' number of chunks.
+  // Each chunk is separated by a delimiter inside the mask.
+  // This offset is also used as the exponentiation base in
+  // the charCode calculations
+  const delimiter = mask[delimiterOffset];
+
+  // Split the 'encoded' string into chunks using the delimiter,
+  // and filter out any empty chunks.
+  const chunks = encoded.split(delimiter).filter((chunk) => chunk);
+
+  // Decode each chunk and concatenate the results to form the final 'decoded' string.
+  const decoded = chunks
+    .map((chunk) => {
+      // Chunks are in reverse order. 'reduceRight' removes the
+      // need to 'reverse' the array first
+      const charCode = chunk.split('').reduceRight((c, value, index) => {
+        // Calculate the character code for each character in the chunk.
+        // This involves finding the index of 'value' in the 'mask' and
+        // multiplying it by (delimiterOffset^position).
+        return c + mask.indexOf(value) * delimiterOffset ** (chunk.length - 1 - index);
+      }, 0);
+
+      // The actual character code is offset by the given amount
+      return String.fromCharCode(charCode - charCodeOffset);
+    })
+    .join('');
+
+  return decoded;
+}
+
+export const streambucketScraper = makeEmbed({
+  id: 'streambucket',
+  name: 'StreamBucket',
+  rank: 196,
+  // TODO - Disabled until ctx.fetcher and ctx.proxiedFetcher don't trigger bot detection
+  disabled: true,
+  async scrape(ctx) {
+    // Using the context fetchers make the site return just the string "No bots please!"?
+    // TODO - Fix this. Native fetch does not trigger this. No idea why right now
+    const response = await fetch(ctx.url);
+    const html = await response.text();
+
+    // This is different than the above mentioned bot detection
+    if (html.includes('captcha-checkbox')) {
+      // TODO - This doesn't use recaptcha, just really basic "image match". Maybe could automate?
+      throw new Error('StreamBucket got captchaed');
+    }
+
+    let regexResult = html.match(hunterRegex);
+
+    if (!regexResult) {
+      throw new Error('Failed to find StreamBucket hunter JavaScript');
+    }
+
+    const encoded = regexResult[1];
+    const mask = regexResult[2];
+    const charCodeOffset = Number(regexResult[3]);
+    const delimiterOffset = Number(regexResult[4]);
+
+    if (Number.isNaN(charCodeOffset)) {
+      throw new Error('StreamBucket hunter JavaScript charCodeOffset is not a valid number');
+    }
+
+    if (Number.isNaN(delimiterOffset)) {
+      throw new Error('StreamBucket hunter JavaScript delimiterOffset is not a valid number');
+    }
+
+    const decoded = decodeHunter(encoded, mask, charCodeOffset, delimiterOffset);
+
+    regexResult = decoded.match(linkRegex);
+
+    if (!regexResult) {
+      throw new Error('Failed to find StreamBucket HLS link');
+    }
+
+    return {
+      stream: [
+        {
+          id: 'primary',
+          type: 'hls',
+          playlist: regexResult[1],
+          flags: [flags.CORS_ALLOWED],
+          captions: [],
+        },
+      ],
+    };
+  },
+});

src/providers/embeds/vidsrc.ts

@@ -0,0 +1,55 @@
+import { flags } from '@/entrypoint/utils/targets';
+import { makeEmbed } from '@/providers/base';
+
+const hlsURLRegex = /file:"(.*?)"/;
+const setPassRegex = /var pass_path = "(.*set_pass\.php.*)";/;
+
+export const vidsrcembedScraper = makeEmbed({
+  id: 'vidsrcembed', // VidSrc is both a source and an embed host
+  name: 'VidSrc',
+  rank: 197,
+  async scrape(ctx) {
+    const html = await ctx.proxiedFetcher<string>(ctx.url, {
+      headers: {
+        referer: ctx.url,
+      },
+    });
+
+    const match = html
+      .match(hlsURLRegex)?.[1]
+      ?.replace(/(\/\/\S+?=)/g, '')
+      .replace('#2', '');
+    if (!match) throw new Error('Unable to find HLS playlist');
+    const finalUrl = atob(match);
+
+    if (!finalUrl.includes('.m3u8')) throw new Error('Unable to find HLS playlist');
+
+    let setPassLink = html.match(setPassRegex)?.[1];
+    if (!setPassLink) throw new Error('Unable to find set_pass.php link');
+
+    if (setPassLink.startsWith('//')) {
+      setPassLink = `https:${setPassLink}`;
+    }
+
+    // VidSrc uses a password endpoint to temporarily whitelist the user's IP. This is called in an interval by the player.
+    // It currently has no effect on the player itself, the content plays fine without it.
+    // In the future we might have to introduce hooks for the frontend to call this endpoint.
+    await ctx.proxiedFetcher(setPassLink, {
+      headers: {
+        referer: ctx.url,
+      },
+    });
+
+    return {
+      stream: [
+        {
+          id: 'primary',
+          type: 'hls',
+          playlist: finalUrl,
+          flags: [flags.CORS_ALLOWED],
+          captions: [],
+        },
+      ],
+    };
+  },
+});

src/providers/sources/lookmovie/index.ts

@@ -10,8 +10,8 @@ async function universalScraper(ctx: MovieScrapeContext | ShowScrapeContext): Pr
   if (!lookmovieData) throw new NotFoundError('Media not found');
 
   ctx.progress(30);
-  const videoUrl = await scrape(ctx, ctx.media, lookmovieData);
-  if (!videoUrl) throw new NotFoundError('No video found');
+  const video = await scrape(ctx, ctx.media, lookmovieData);
+  if (!video.playlist) throw new NotFoundError('No video found');
 
   ctx.progress(60);
 
@@ -20,10 +20,10 @@ async function universalScraper(ctx: MovieScrapeContext | ShowScrapeContext): Pr
     stream: [
       {
         id: 'primary',
-        playlist: videoUrl,
+        playlist: video.playlist,
         type: 'hls',
         flags: [flags.IP_LOCKED],
-        captions: [],
+        captions: video.captions,
       },
     ],
   };
@@ -33,6 +33,7 @@ export const lookmovieScraper = makeSourcerer({
   id: 'lookmovie',
   name: 'LookMovie',
   rank: 1,
+  disabled: true,
   flags: [flags.IP_LOCKED],
   scrapeShow: universalScraper,
   scrapeMovie: universalScraper,

src/providers/sources/lookmovie/type.ts

@@ -39,8 +39,17 @@ interface VideoSources {
   [key: string]: string;
 }
 
+interface VideoSubtitles {
+  id?: number;
+  id_movie?: number;
+  url: string;
+  language: string;
+  shard?: string;
+}
+
 export interface StreamsDataResult {
   streams: VideoSources;
+  subtitles: VideoSubtitles[];
 }
 
 export interface ResultItem {

src/providers/sources/lookmovie/util.ts

@@ -4,7 +4,9 @@ import { ScrapeContext } from '@/utils/context';
 import { NotFoundError } from '@/utils/errors';
 
 import { Result, ResultItem, ShowDataResult, episodeObj } from './type';
-import { getVideoUrl } from './video';
+import { getVideo } from './video';
+
+export const baseUrl = 'https://lmscript.xyz';
 
 export async function searchAndFindMedia(
   ctx: ScrapeContext,
@@ -12,7 +14,7 @@ export async function searchAndFindMedia(
 ): Promise<ResultItem | undefined> {
   if (media.type === 'show') {
     const searchRes = await ctx.fetcher<Result>(`/v1/shows`, {
-      baseUrl: 'https://lmscript.xyz',
+      baseUrl,
       query: { 'filters[q]': media.title },
     });
 
@@ -23,7 +25,7 @@ export async function searchAndFindMedia(
   }
   if (media.type === 'movie') {
     const searchRes = await ctx.fetcher<Result>(`/v1/movies`, {
-      baseUrl: 'https://lmscript.xyz',
+      baseUrl,
       query: { 'filters[q]': media.title },
     });
 
@@ -40,7 +42,7 @@ export async function scrape(ctx: ScrapeContext, media: MovieMedia | ShowMedia,
     id = result.id_movie;
   } else if (media.type === 'show') {
     const data = await ctx.fetcher<ShowDataResult>(`/v1/shows`, {
-      baseUrl: 'https://lmscript.xyz',
+      baseUrl,
       query: { expand: 'episodes', id: result.id_show },
     });
 
@@ -54,6 +56,6 @@ export async function scrape(ctx: ScrapeContext, media: MovieMedia | ShowMedia,
   // Check ID
   if (id === null) throw new NotFoundError('Not found');
 
-  const videoUrl = await getVideoUrl(ctx, id, media);
-  return videoUrl;
+  const video = await getVideo(ctx, id, media);
+  return video;
 }

src/providers/sources/lookmovie/video.ts

@@ -1,7 +1,9 @@
 import { MovieMedia, ShowMedia } from '@/entrypoint/utils/media';
+import { Caption } from '@/providers/captions';
 import { ScrapeContext } from '@/utils/context';
 
 import { StreamsDataResult } from './type';
+import { baseUrl } from './util';
 
 export async function getVideoSources(
   ctx: ScrapeContext,
@@ -17,17 +19,17 @@ export async function getVideoSources(
     path = `/v1/movies/view`;
   }
   const data = await ctx.fetcher<StreamsDataResult>(path, {
-    baseUrl: 'https://lmscript.xyz',
-    query: { expand: 'streams', id },
+    baseUrl,
+    query: { expand: 'streams,subtitles', id },
   });
   return data;
 }
 
-export async function getVideoUrl(
+export async function getVideo(
   ctx: ScrapeContext,
   id: string,
   media: MovieMedia | ShowMedia,
-): Promise<string | null> {
+): Promise<{ playlist: string | null; captions: Caption[] }> {
   // Get sources
   const data = await getVideoSources(ctx, id, media);
   const videoSources = data.streams;
@@ -42,5 +44,16 @@ export async function getVideoUrl(
     }
   }
 
-  return videoUrl;
+  const captions: Caption[] = data.subtitles.map((sub) => ({
+    id: sub.url,
+    type: 'vtt',
+    url: `${baseUrl}${sub.url}`,
+    hasCorsRestrictions: false,
+    language: sub.language,
+  }));
+
+  return {
+    playlist: videoUrl,
+    captions,
+  };
 }

src/providers/sources/remotestream.ts

@@ -2,7 +2,7 @@ import { flags } from '@/entrypoint/utils/targets';
 import { makeSourcerer } from '@/providers/base';
 import { NotFoundError } from '@/utils/errors';
 
-const remotestreamBase = `https://fsa.remotestre.am`;
+const remotestreamBase = atob('aHR0cHM6Ly9mc2IuOG1ldDNkdGpmcmNxY2hjb25xcGtsd3hzeGIyb2N1bWMuc3RyZWFt');
 
 export const remotestreamScraper = makeSourcerer({
   id: 'remotestream',
@@ -16,8 +16,12 @@ export const remotestreamScraper = makeSourcerer({
     const playlistLink = `${remotestreamBase}/Shows/${ctx.media.tmdbId}/${seasonNumber}/${episodeNumber}/${episodeNumber}.m3u8`;
 
     ctx.progress(30);
-    const streamRes = await ctx.fetcher<Blob>(playlistLink); // TODO support blobs in fetchers
-    if (streamRes.type !== 'application/x-mpegurl') throw new NotFoundError('No watchable item found');
+    const streamRes = await ctx.fetcher.full(playlistLink, {
+      method: 'HEAD',
+      readHeaders: ['content-type'],
+    });
+    if (!streamRes.headers.get('content-type')?.toLowerCase().includes('application/x-mpegurl'))
+      throw new NotFoundError('No watchable item found');
     ctx.progress(90);
 
     return {
@@ -37,8 +41,12 @@ export const remotestreamScraper = makeSourcerer({
     const playlistLink = `${remotestreamBase}/Movies/${ctx.media.tmdbId}/${ctx.media.tmdbId}.m3u8`;
 
     ctx.progress(30);
-    const streamRes = await ctx.fetcher<Blob>(playlistLink);
-    if (streamRes.type !== 'application/x-mpegurl') throw new NotFoundError('No watchable item found');
+    const streamRes = await ctx.fetcher.full(playlistLink, {
+      method: 'HEAD',
+      readHeaders: ['content-type'],
+    });
+    if (!streamRes.headers.get('content-type')?.toLowerCase().includes('application/x-mpegurl'))
+      throw new NotFoundError('No watchable item found');
     ctx.progress(90);
 
     return {

src/providers/sources/showbox/index.ts

@@ -1,6 +1,5 @@
 import { flags } from '@/entrypoint/utils/targets';
 import { SourcererOutput, makeSourcerer } from '@/providers/base';
-import { febboxHlsScraper } from '@/providers/embeds/febbox/hls';
 import { febboxMp4Scraper } from '@/providers/embeds/febbox/mp4';
 import { compareTitle } from '@/utils/compare';
 import { MovieScrapeContext, ShowScrapeContext } from '@/utils/context';
@@ -31,10 +30,6 @@ async function comboScraper(ctx: ShowScrapeContext | MovieScrapeContext): Promis
 
   return {
     embeds: [
-      {
-        embedId: febboxHlsScraper.id,
-        url: `/${ctx.media.type}/${id}/${season}/${episode}`,
-      },
       {
         embedId: febboxMp4Scraper.id,
         url: `/${ctx.media.type}/${id}/${season}/${episode}`,

src/providers/sources/vidsrc/common.ts

@@ -0,0 +1,2 @@
+export const vidsrcBase = 'https://vidsrc.me';
+export const vidsrcRCPBase = 'https://rcp.vidsrc.me';

src/providers/sources/vidsrc/index.ts

@@ -0,0 +1,13 @@
+import { flags } from '@/entrypoint/utils/targets';
+import { makeSourcerer } from '@/providers/base';
+import { scrapeMovie } from '@/providers/sources/vidsrc/scrape-movie';
+import { scrapeShow } from '@/providers/sources/vidsrc/scrape-show';
+
+export const vidsrcScraper = makeSourcerer({
+  id: 'vidsrc',
+  name: 'VidSrc',
+  rank: 120,
+  flags: [flags.CORS_ALLOWED],
+  scrapeMovie,
+  scrapeShow,
+});

src/providers/sources/vidsrc/scrape-movie.ts

@@ -0,0 +1,8 @@
+import { getVidSrcMovieSources } from '@/providers/sources/vidsrc/scrape';
+import { MovieScrapeContext } from '@/utils/context';
+
+export async function scrapeMovie(ctx: MovieScrapeContext) {
+  return {
+    embeds: await getVidSrcMovieSources(ctx),
+  };
+}

src/providers/sources/vidsrc/scrape-show.ts

@@ -0,0 +1,8 @@
+import { getVidSrcShowSources } from '@/providers/sources/vidsrc/scrape';
+import { ShowScrapeContext } from '@/utils/context';
+
+export async function scrapeShow(ctx: ShowScrapeContext) {
+  return {
+    embeds: await getVidSrcShowSources(ctx),
+  };
+}

src/providers/sources/vidsrc/scrape.ts

@@ -0,0 +1,133 @@
+import { load } from 'cheerio';
+
+import { SourcererEmbed } from '@/providers/base';
+import { streambucketScraper } from '@/providers/embeds/streambucket';
+import { vidsrcembedScraper } from '@/providers/embeds/vidsrc';
+import { vidsrcBase, vidsrcRCPBase } from '@/providers/sources/vidsrc/common';
+import { MovieScrapeContext, ShowScrapeContext } from '@/utils/context';
+
+function decodeSrc(encoded: string, seed: string) {
+  let decoded = '';
+  const seedLength = seed.length;
+
+  for (let i = 0; i < encoded.length; i += 2) {
+    const byte = parseInt(encoded.substr(i, 2), 16);
+    const seedChar = seed.charCodeAt((i / 2) % seedLength);
+    decoded += String.fromCharCode(byte ^ seedChar);
+  }
+
+  return decoded;
+}
+
+async function getVidSrcEmbeds(ctx: MovieScrapeContext | ShowScrapeContext, startingURL: string) {
+  // VidSrc works by using hashes and a redirect system.
+  // The hashes are stored in the html, and VidSrc will
+  // make requests to their servers with the hash. This
+  // will trigger a 302 response with a Location header
+  // sending the user to the correct embed. To get the
+  // real embed links, we must do the same. Slow, but
+  // required
+
+  const embeds: SourcererEmbed[] = [];
+
+  let html = await ctx.proxiedFetcher<string>(startingURL, {
+    baseUrl: vidsrcBase,
+  });
+
+  let $ = load(html);
+
+  const sourceHashes = $('.server[data-hash]')
+    .toArray()
+    .map((el) => $(el).attr('data-hash'))
+    .filter((hash) => hash !== undefined);
+
+  for (const hash of sourceHashes) {
+    html = await ctx.proxiedFetcher<string>(`/rcp/${hash}`, {
+      baseUrl: vidsrcRCPBase,
+      headers: {
+        referer: vidsrcBase,
+      },
+    });
+
+    $ = load(html);
+    const encoded = $('#hidden').attr('data-h');
+    const seed = $('body').attr('data-i');
+
+    if (!encoded || !seed) {
+      throw new Error('Failed to find encoded iframe src');
+    }
+
+    let redirectURL = decodeSrc(encoded, seed);
+    if (redirectURL.startsWith('//')) {
+      redirectURL = `https:${redirectURL}`;
+    }
+
+    const { finalUrl } = await ctx.proxiedFetcher.full(redirectURL, {
+      method: 'HEAD',
+      headers: {
+        referer: vidsrcBase,
+      },
+    });
+
+    const embed: SourcererEmbed = {
+      embedId: '',
+      url: finalUrl,
+    };
+
+    const parsedUrl = new URL(finalUrl);
+
+    switch (parsedUrl.host) {
+      case 'vidsrc.stream':
+        embed.embedId = vidsrcembedScraper.id;
+        break;
+      case 'streambucket.net':
+        embed.embedId = streambucketScraper.id;
+        break;
+      case '2embed.cc':
+      case 'www.2embed.cc':
+        // Just ignore this. This embed just sources from other embeds we can scrape as a 'source'
+        break;
+      case 'player-cdn.com':
+        // Just ignore this. This embed streams video over a custom WebSocket connection
+        break;
+      default:
+        throw new Error(`Failed to find VidSrc embed source for ${finalUrl}`);
+    }
+
+    // Since some embeds are ignored on purpose, check if a valid one was found
+    if (embed.embedId !== '') {
+      embeds.push(embed);
+    }
+  }
+
+  return embeds;
+}
+
+export async function getVidSrcMovieSources(ctx: MovieScrapeContext) {
+  return getVidSrcEmbeds(ctx, `/embed/${ctx.media.tmdbId}`);
+}
+
+export async function getVidSrcShowSources(ctx: ShowScrapeContext) {
+  // VidSrc will always default to season 1 episode 1
+  // no matter what embed URL is used. It sends back
+  // a list of ALL the shows episodes, in order, for
+  // all seasons. To get the real embed URL, have to
+  // parse this from the response
+  const html = await ctx.proxiedFetcher<string>(`/embed/${ctx.media.tmdbId}`, {
+    baseUrl: vidsrcBase,
+  });
+
+  const $ = load(html);
+
+  const episodeElement = $(`.ep[data-s="${ctx.media.season.number}"][data-e="${ctx.media.episode.number}"]`).first();
+  if (episodeElement.length === 0) {
+    throw new Error('failed to find episode element');
+  }
+
+  const startingURL = episodeElement.attr('data-iframe');
+  if (!startingURL) {
+    throw new Error('failed to find episode starting URL');
+  }
+
+  return getVidSrcEmbeds(ctx, startingURL);
+}

src/providers/sources/zoechip/common.ts

@@ -38,7 +38,7 @@ export async function formatSource(
         embed.embedId = mixdropScraper.id;
         break;
       default:
-        throw new Error(`Failed to find ZoeChip embed source for ${link}`);
+        return null;
     }
 
     return embed;

src/providers/streams.ts

@@ -4,7 +4,6 @@ import { Caption } from '@/providers/captions';
 export type StreamFile = {
   type: 'mp4';
   url: string;
-  headers?: Record<string, string>;
 };
 
 export type Qualities = 'unknown' | '360' | '480' | '720' | '1080' | '4k';

src/runners/runner.ts

@@ -116,9 +116,12 @@ export async function runAllProviders(list: ProviderList, ops: ProviderRunnerOpt
       };
     }
 
-    if (output.embeds.length > 0) {
+    // run embed scrapers on listed embeds
+    const sortedEmbeds = output.embeds.sort((a, b) => embedIds.indexOf(a.embedId) - embedIds.indexOf(b.embedId));
+
+    if (sortedEmbeds.length > 0) {
       ops.events?.discoverEmbeds?.({
-        embeds: output.embeds.map((v, i) => ({
+        embeds: sortedEmbeds.map((v, i) => ({
           id: [s.id, i].join('-'),
           embedScraperId: v.embedId,
         })),
@@ -126,10 +129,6 @@ export async function runAllProviders(list: ProviderList, ops: ProviderRunnerOpt
       });
     }
 
-    // run embed scrapers on listed embeds
-    const sortedEmbeds = output.embeds;
-    sortedEmbeds.sort((a, b) => embedIds.indexOf(a.embedId) - embedIds.indexOf(b.embedId));
-
     for (const ind in sortedEmbeds) {
       if (!Object.prototype.hasOwnProperty.call(sortedEmbeds, ind)) continue;
       const e = sortedEmbeds[ind];

src/utils/context.ts

@@ -2,8 +2,8 @@ import { MovieMedia, ShowMedia } from '@/entrypoint/utils/media';
 import { UseableFetcher } from '@/fetchers/types';
 
 export type ScrapeContext = {
-  proxiedFetcher: <T>(...params: Parameters<UseableFetcher<T>>) => ReturnType<UseableFetcher<T>>;
-  fetcher: <T>(...params: Parameters<UseableFetcher<T>>) => ReturnType<UseableFetcher<T>>;
+  proxiedFetcher: UseableFetcher;
+  fetcher: UseableFetcher;
   progress(val: number): void;
 };