Merge 94bfcd0c31 into 025b6821e6

Add Insertunit provider

src/providers/all.ts

@@ -14,6 +14,7 @@ import { vidsrcembedScraper } from '@/providers/embeds/vidsrc';
 import { vTubeScraper } from '@/providers/embeds/vtube';
 import { flixhqScraper } from '@/providers/sources/flixhq/index';
 import { goMoviesScraper } from '@/providers/sources/gomovies/index';
+import { insertunitScraper } from '@/providers/sources/insertunit';
 import { kissAsianScraper } from '@/providers/sources/kissasian/index';
 import { lookmovieScraper } from '@/providers/sources/lookmovie';
 import { remotestreamScraper } from '@/providers/sources/remotestream';
@@ -40,6 +41,7 @@ import { nepuScraper } from './sources/nepu';
 import { primewireScraper } from './sources/primewire';
 import { ridooMoviesScraper } from './sources/ridomovies';
 import { smashyStreamScraper } from './sources/smashystream';
+import { soaperTvScraper } from './sources/soapertv';
 import { vidSrcToScraper } from './sources/vidsrcto';
 import { warezcdnScraper } from './sources/warezcdn';
 
@@ -62,6 +64,8 @@ export function gatherAllSources(): Array<Sourcerer> {
     hdRezkaScraper,
     primewireScraper,
     warezcdnScraper,
+    insertunitScraper,
+    soaperTvScraper,
   ];
 }
 

src/providers/embeds/warezcdn/common.ts

@@ -23,7 +23,7 @@ function decrypt(input: string) {
 }
 
 export async function getDecryptedId(ctx: EmbedScrapeContext) {
-  const page = await ctx.proxiedFetcher<string>(`/player.php?${new URLSearchParams({ id: ctx.url })}`, {
+  const page = await ctx.proxiedFetcher<string>(`/player.php`, {
     baseUrl: warezcdnPlayerBase,
     headers: {
       Referer: `${warezcdnPlayerBase}/getEmbed.php?${new URLSearchParams({
@@ -31,6 +31,9 @@ export async function getDecryptedId(ctx: EmbedScrapeContext) {
         sv: 'warezcdn',
       })}`,
     },
+    query: {
+      id: ctx.url,
+    },
   });
   const allowanceKey = page.match(/let allowanceKey = "(.*?)";/)?.[1];
   if (!allowanceKey) throw new NotFoundError('Failed to get allowanceKey');
@@ -53,5 +56,3 @@ export async function getDecryptedId(ctx: EmbedScrapeContext) {
 
   return decryptedId;
 }
-
-export const warezcdnWorkerProxy = 'https://workerproxy.warezcdn.workers.dev';

src/providers/embeds/warezcdn/hls.ts

@@ -21,7 +21,7 @@ async function getVideowlUrlStream(ctx: EmbedScrapeContext, decryptedId: string)
 export const warezcdnembedHlsScraper = makeEmbed({
   id: 'warezcdnembedhls', // WarezCDN is both a source and an embed host
   name: 'WarezCDN HLS',
-  rank: 82,
+  rank: 83,
   async scrape(ctx) {
     const decryptedId = await getDecryptedId(ctx);
 

src/providers/embeds/warezcdn/mp4.ts

@@ -1,8 +1,10 @@
+import { flags } from '@/entrypoint/utils/targets';
 import { makeEmbed } from '@/providers/base';
+import { warezcdnWorkerProxy } from '@/providers/sources/warezcdn/common';
 import { EmbedScrapeContext } from '@/utils/context';
 import { NotFoundError } from '@/utils/errors';
 
-import { getDecryptedId, warezcdnWorkerProxy } from './common';
+import { getDecryptedId } from './common';
 
 const cdnListing = [50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64];
 
@@ -23,7 +25,7 @@ async function checkUrls(ctx: EmbedScrapeContext, fileId: string) {
 export const warezcdnembedMp4Scraper = makeEmbed({
   id: 'warezcdnembedmp4', // WarezCDN is both a source and an embed host
   name: 'WarezCDN MP4',
-  rank: 83,
+  rank: 82,
   disabled: false,
   async scrape(ctx) {
     const decryptedId = await getDecryptedId(ctx);
@@ -48,7 +50,7 @@ export const warezcdnembedMp4Scraper = makeEmbed({
             },
           },
           type: 'file',
-          flags: [],
+          flags: [flags.CORS_ALLOWED],
         },
       ],
     };

src/providers/sources/insertunit/captions.ts

@@ -0,0 +1,30 @@
+import { Caption, removeDuplicatedLanguages } from '@/providers/captions';
+
+import { Subtitle } from './types';
+
+export async function getCaptions(data: Subtitle[]) {
+  let captions: Caption[] = [];
+  for (const subtitle of data) {
+    let language = '';
+
+    if (subtitle.name.includes('Рус')) {
+      language = 'ru';
+    } else if (subtitle.name.includes('Укр')) {
+      language = 'uk';
+    } else if (subtitle.name.includes('Eng')) {
+      language = 'en';
+    } else {
+      continue;
+    }
+
+    captions.push({
+      id: subtitle.url,
+      url: subtitle.url,
+      language,
+      type: 'vtt',
+      hasCorsRestrictions: false,
+    });
+  }
+  captions = removeDuplicatedLanguages(captions);
+  return captions;
+}

src/providers/sources/insertunit/index.ts

@@ -0,0 +1,103 @@
+import { flags } from '@/entrypoint/utils/targets';
+import { makeSourcerer } from '@/providers/base';
+import { Caption } from '@/providers/captions';
+import { NotFoundError } from '@/utils/errors';
+
+import { getCaptions } from './captions';
+import { Season } from './types';
+
+const insertUnitBase = 'https://api.insertunit.ws/';
+
+export const insertunitScraper = makeSourcerer({
+  id: 'insertunit',
+  name: 'Insertunit',
+  disabled: false,
+  rank: 60,
+  flags: [flags.CORS_ALLOWED],
+  async scrapeShow(ctx) {
+    const playerData = await ctx.fetcher<string>(`/embed/imdb/${ctx.media.imdbId}`, {
+      baseUrl: insertUnitBase,
+    });
+    ctx.progress(30);
+
+    const seasonDataJSONregex = /seasons:(.*)/;
+    const seasonData = seasonDataJSONregex.exec(playerData);
+
+    if (seasonData === null || seasonData[1] === null) {
+      throw new NotFoundError('No result found');
+    }
+    ctx.progress(60);
+
+    const seasonTable: Season[] = JSON.parse(seasonData[1]) as Season[];
+
+    const currentSeason = seasonTable.find(
+      (seasonElement) => seasonElement.season === ctx.media.season.number && !seasonElement.blocked,
+    );
+
+    const currentEpisode = currentSeason?.episodes.find((episodeElement) =>
+      episodeElement.episode.includes(ctx.media.episode.number.toString()),
+    );
+
+    if (!currentEpisode?.hls) throw new NotFoundError('No result found');
+
+    let captions: Caption[] = [];
+
+    if (currentEpisode.cc != null) {
+      captions = await getCaptions(currentEpisode.cc);
+    }
+
+    ctx.progress(95);
+
+    return {
+      embeds: [],
+      stream: [
+        {
+          id: 'primary',
+          playlist: currentEpisode.hls,
+          type: 'hls',
+          flags: [flags.CORS_ALLOWED],
+          captions,
+        },
+      ],
+    };
+  },
+  async scrapeMovie(ctx) {
+    const playerData = await ctx.fetcher<string>(`/embed/imdb/${ctx.media.imdbId}`, {
+      baseUrl: insertUnitBase,
+    });
+    ctx.progress(35);
+
+    const streamRegex = /hls: "([^"]*)/;
+    const streamData = streamRegex.exec(playerData);
+
+    if (streamData === null || streamData[1] === null) {
+      throw new NotFoundError('No result found');
+    }
+    ctx.progress(75);
+
+    const subtitleRegex = /cc: (.*)/;
+    const subtitleJSONData = subtitleRegex.exec(playerData);
+
+    let captions: Caption[] = [];
+
+    if (subtitleJSONData != null && subtitleJSONData[1] != null) {
+      const subtitleData = JSON.parse(subtitleJSONData[1]);
+      captions = await getCaptions(subtitleData);
+    }
+
+    ctx.progress(90);
+
+    return {
+      embeds: [],
+      stream: [
+        {
+          id: 'primary',
+          type: 'hls',
+          playlist: streamData[1],
+          flags: [flags.CORS_ALLOWED],
+          captions,
+        },
+      ],
+    };
+  },
+});

src/providers/sources/insertunit/types.ts

@@ -0,0 +1,30 @@
+export interface Subtitle {
+  url: string;
+  name: string;
+}
+
+export interface Episode {
+  episode: string;
+  id: number;
+  videoKey: string;
+  hls: string;
+  audio: {
+    names: string[];
+    order: number[];
+  };
+  cc: Subtitle[];
+  duration: number;
+  title: string;
+  download: string;
+  sections: string[];
+  poster: string;
+  preview: {
+    src: string;
+  };
+}
+
+export interface Season {
+  season: number;
+  blocked: boolean;
+  episodes: Episode[];
+}

src/providers/sources/soapertv/index.ts

@@ -0,0 +1,120 @@
+import { load } from 'cheerio';
+
+import { flags } from '@/entrypoint/utils/targets';
+import { Caption, labelToLanguageCode } from '@/providers/captions';
+import { MovieScrapeContext, ShowScrapeContext } from '@/utils/context';
+import { NotFoundError } from '@/utils/errors';
+
+import { InfoResponse } from './types';
+import { SourcererOutput, makeSourcerer } from '../../base';
+
+const baseUrl = 'https://soaper.tv';
+
+const universalScraper = async (ctx: MovieScrapeContext | ShowScrapeContext): Promise<SourcererOutput> => {
+  const searchResult = await ctx.proxiedFetcher('/search.html', {
+    baseUrl,
+    query: {
+      keyword: ctx.media.title,
+    },
+  });
+  const searchResult$ = load(searchResult);
+  let showLink = searchResult$('a')
+    .filter((_, el) => searchResult$(el).text() === ctx.media.title)
+    .attr('href');
+  if (!showLink) throw new NotFoundError('Content not found');
+
+  if (ctx.media.type === 'show') {
+    const seasonNumber = ctx.media.season.number;
+    const episodeNumber = ctx.media.episode.number;
+    const showPage = await ctx.proxiedFetcher(showLink, { baseUrl });
+    const showPage$ = load(showPage);
+    const seasonBlock = showPage$('h4')
+      .filter((_, el) => showPage$(el).text().trim().split(':')[0].trim() === `Season${seasonNumber}`)
+      .parent();
+    const episodes = seasonBlock.find('a').toArray();
+    showLink = showPage$(
+      episodes.find((el) => parseInt(showPage$(el).text().split('.')[0], 10) === episodeNumber),
+    ).attr('href');
+  }
+  if (!showLink) throw new NotFoundError('Content not found');
+  const contentPage = await ctx.proxiedFetcher(showLink, { baseUrl });
+  const contentPage$ = load(contentPage);
+
+  const pass = contentPage$('#hId').attr('value');
+  const param = contentPage$('#divU').text();
+
+  if (!pass || !param) throw new NotFoundError('Content not found');
+
+  const formData = new URLSearchParams();
+  formData.append('pass', pass);
+  formData.append('param', param);
+  formData.append('e2', '0');
+  formData.append('server', '0');
+
+  const infoEndpoint = ctx.media.type === 'show' ? '/home/index/getEInfoAjax' : '/home/index/getMInfoAjax';
+  const streamRes = await ctx.proxiedFetcher<string>(infoEndpoint, {
+    baseUrl,
+    method: 'POST',
+    body: formData,
+    headers: {
+      referer: `${baseUrl}${showLink}`,
+    },
+  });
+
+  const streamResJson: InfoResponse = JSON.parse(streamRes);
+
+  const captions: Caption[] = [];
+  for (const sub of streamResJson.subs) {
+    // Some subtitles are named <Language>.srt, some are named <LanguageCode>:hi, or just <LanguageCode>
+    let language: string | null = '';
+    if (sub.name.includes('.srt')) {
+      language = labelToLanguageCode(sub.name.split('.srt')[0]);
+    } else if (sub.name.includes(':')) {
+      language = sub.name.split(':')[0];
+    } else {
+      language = sub.name;
+    }
+    if (!language) continue;
+
+    captions.push({
+      id: sub.path,
+      url: sub.path,
+      type: 'srt',
+      hasCorsRestrictions: false,
+      language,
+    });
+  }
+
+  return {
+    embeds: [],
+    stream: [
+      {
+        id: 'primary',
+        playlist: streamResJson.val,
+        type: 'hls',
+        flags: [flags.IP_LOCKED],
+        captions,
+      },
+      ...(streamResJson.val_bak
+        ? [
+            {
+              id: 'backup',
+              playlist: streamResJson.val_bak,
+              type: 'hls' as const,
+              flags: [flags.IP_LOCKED],
+              captions,
+            },
+          ]
+        : []),
+    ],
+  };
+};
+
+export const soaperTvScraper = makeSourcerer({
+  id: 'soapertv',
+  name: 'SoaperTV',
+  rank: 115,
+  flags: [flags.IP_LOCKED],
+  scrapeMovie: universalScraper,
+  scrapeShow: universalScraper,
+});

src/providers/sources/soapertv/types.ts

@@ -0,0 +1,15 @@
+export interface Subtitle {
+  path: string;
+  name: string;
+}
+
+export interface InfoResponse {
+  key: boolean;
+  val: string;
+  vtt: string;
+  val_bak: string;
+  pos: number;
+  type: string;
+  subs: Subtitle[];
+  ip: string;
+}

src/providers/sources/warezcdn/common.ts

@@ -1,3 +1,4 @@
 export const warezcdnBase = 'https://embed.warezcdn.com';
 export const warezcdnApiBase = 'https://warezcdn.com/embed';
 export const warezcdnPlayerBase = 'https://warezcdn.com/player';
+export const warezcdnWorkerProxy = 'https://workerproxy.warezcdn.workers.dev';

src/providers/sources/warezcdn/index.ts

@@ -1,6 +1,7 @@
 import { load } from 'cheerio';
 
-import { SourcererEmbed, SourcererOutput, makeSourcerer } from '@/providers/base';
+import { flags } from '@/entrypoint/utils/targets';
+import { SourcererEmbed, makeSourcerer } from '@/providers/base';
 import { mixdropScraper } from '@/providers/embeds/mixdrop';
 import { warezcdnembedHlsScraper } from '@/providers/embeds/warezcdn/hls';
 import { warezcdnembedMp4Scraper } from '@/providers/embeds/warezcdn/mp4';
@@ -30,15 +31,16 @@ const universalScraper = async (ctx: MovieScrapeContext | ShowScrapeContext) =>
     const embedUrl = $(element).attr('data-load-embed')!;
 
     if (embedHost === 'mixdrop') {
-      const params = new URLSearchParams({
+      const params = {
         id: embedUrl,
         sv: 'mixdrop',
-      });
-      const realUrl = await ctx.proxiedFetcher<string>(`/getPlay.php?${params}`, {
+      };
+      const realUrl = await ctx.proxiedFetcher<string>(`/getPlay.php`, {
         baseUrl: warezcdnApiBase,
         headers: {
-          Referer: `${warezcdnApiBase}/getEmbed.php?${params}`,
+          Referer: `${warezcdnApiBase}/getEmbed.php?${new URLSearchParams(params)}`,
         },
+        query: params,
       });
 
       const realEmbedUrl = realUrl.match(/window\.location\.href="([^"]*)";/);
@@ -63,14 +65,14 @@ const universalScraper = async (ctx: MovieScrapeContext | ShowScrapeContext) =>
 
   return {
     embeds,
-  } as SourcererOutput;
+  };
 };
 
 export const warezcdnScraper = makeSourcerer({
   id: 'warezcdn',
   name: 'WarezCDN',
   rank: 81,
-  flags: [],
+  flags: [flags.CORS_ALLOWED],
   scrapeMovie: universalScraper,
   scrapeShow: universalScraper,
 });

src/runners/individualRunner.ts

@@ -71,7 +71,7 @@ export async function scrapeInvidualSource(
 
   // only check for playable streams if there are streams, and if there are no embeds
   if (output.stream && output.stream.length > 0 && output.embeds.length === 0) {
-    const playableStreams = await validatePlayableStreams(output.stream, ops);
+    const playableStreams = await validatePlayableStreams(output.stream, ops, sourceScraper.id);
     if (playableStreams.length === 0) throw new NotFoundError('No playable streams found');
     output.stream = playableStreams;
   }
@@ -112,7 +112,7 @@ export async function scrapeIndividualEmbed(
     .filter((stream) => flagsAllowedInFeatures(ops.features, stream.flags));
   if (output.stream.length === 0) throw new NotFoundError('No streams found');
 
-  const playableStreams = await validatePlayableStreams(output.stream, ops);
+  const playableStreams = await validatePlayableStreams(output.stream, ops, embedScraper.id);
   if (playableStreams.length === 0) throw new NotFoundError('No playable streams found');
   output.stream = playableStreams;
 

src/runners/runner.ts

@@ -104,7 +104,7 @@ export async function runAllProviders(list: ProviderList, ops: ProviderRunnerOpt
 
     // return stream is there are any
     if (output.stream?.[0]) {
-      const playableStream = await validatePlayableStream(output.stream[0], ops);
+      const playableStream = await validatePlayableStream(output.stream[0], ops, source.id);
       if (!playableStream) throw new NotFoundError('No streams found');
       return {
         sourceId: source.id,
@@ -151,7 +151,7 @@ export async function runAllProviders(list: ProviderList, ops: ProviderRunnerOpt
         if (embedOutput.stream.length === 0) {
           throw new NotFoundError('No streams found');
         }
-        const playableStream = await validatePlayableStream(embedOutput.stream[0], ops);
+        const playableStream = await validatePlayableStream(embedOutput.stream[0], ops, embed.embedId);
         if (!playableStream) throw new NotFoundError('No streams found');
         embedOutput.stream = [playableStream];
       } catch (error) {

src/utils/valid.ts

@@ -1,7 +1,10 @@
+import { warezcdnembedMp4Scraper } from '@/providers/embeds/warezcdn/mp4';
 import { Stream } from '@/providers/streams';
 import { IndividualEmbedRunnerOptions } from '@/runners/individualRunner';
 import { ProviderRunnerOptions } from '@/runners/runner';
 
+const SKIP_VALIDATION_CHECK_IDS = [warezcdnembedMp4Scraper.id];
+
 export function isValidStream(stream: Stream | undefined): boolean {
   if (!stream) return false;
   if (stream.type === 'hls') {
@@ -21,7 +24,10 @@ export function isValidStream(stream: Stream | undefined): boolean {
 export async function validatePlayableStream(
   stream: Stream,
   ops: ProviderRunnerOptions | IndividualEmbedRunnerOptions,
+  sourcererId: string,
 ): Promise<Stream | null> {
+  if (SKIP_VALIDATION_CHECK_IDS.includes(sourcererId)) return stream;
+
   if (stream.type === 'hls') {
     const result = await ops.proxiedFetcher.full(stream.playlist, {
       method: 'GET',
@@ -63,8 +69,11 @@ export async function validatePlayableStream(
 export async function validatePlayableStreams(
   streams: Stream[],
   ops: ProviderRunnerOptions | IndividualEmbedRunnerOptions,
+  sourcererId: string,
 ): Promise<Stream[]> {
-  return (await Promise.all(streams.map((stream) => validatePlayableStream(stream, ops)))).filter(
+  if (SKIP_VALIDATION_CHECK_IDS.includes(sourcererId)) return streams;
+
+  return (await Promise.all(streams.map((stream) => validatePlayableStream(stream, ops, sourcererId)))).filter(
     (v) => v !== null,
   ) as Stream[];
 }