Initial commit

scrapers/api/horriblesubs.js

@@ -0,0 +1,42 @@
+const cheerio = require('cheerio');
+const needle = require('needle');
+const moment = require('moment');
+
+const defaultUrl = 'https://horriblesubs.info';
+const defaultTimeout = 5000;
+
+function _getContent(url, config = {},) {
+  const baseUrl = config.proxyUrl || defaultUrl;
+  const timeout = config.timeout || defaultTimeout;
+
+  return needle('get', `${baseUrl}${url}`, { open_timeout: timeout, follow: 2 })
+      .then((response) => response.body)
+      .then((body) => cheerio.load(body))
+}
+
+function _getAnimeId(showInfo) {
+  return _getContent(showInfo.url).then($ => {
+    const text = $('div.entry-content').find('script').html();
+    showInfo.id = text.match(/var hs_showid = (\d+)/)[1];
+    return showInfo
+  })
+}
+
+function allShows(config = {}) {
+  return _getContent('/shows', config)
+      .then(($) =>  $('div[class=\'ind-show\']')
+          .map((index, element) => $(element).children('a'))
+          .map((index, element) => ({
+            title: element.attr('title'),
+            url: `${config.proxyUrl || defaultUrl}${element.attr('href')}`
+          })).get());
+}
+
+function showData(showInfo) {
+  return _getAnimeId(showInfo)
+      .then((showInfo) => )
+
+}
+
+module.exports = { allShows };
+

scrapers/api/thepiratebay.js

@@ -0,0 +1,179 @@
+const cheerio = require('cheerio');
+const needle = require('needle');
+const moment = require('moment');
+
+const defaultProxies = ['https://pirateproxy.sh', 'https://thepiratebay.org'];
+const dumpUrl = '/static/dump/csv/';
+const defaultTimeout = 5000;
+
+const errors = {
+  REQUEST_ERROR: { code: 'REQUEST_ERROR' },
+  PARSER_ERROR: { code: 'PARSER_ERROR' }
+};
+
+Categories = {
+  AUDIO: {
+    ALL: 100,
+    MUSIC: 101,
+    AUDIO_BOOKS: 102,
+    SOUND_CLIPS: 103,
+    FLAC: 104,
+    OTHER: 199
+  },
+  VIDEO: {
+    ALL: 200,
+    MOVIES: 201,
+    MOVIES_DVDR: 202,
+    MUSIC_VIDEOS: 203,
+    MOVIE_CLIPS: 204,
+    TV_SHOWS: 205,
+    HANDHELD: 206,
+    MOVIES_HD: 207,
+    TV_SHOWS_HD: 208,
+    MOVIES_3D: 209,
+    OTHER: 299
+  },
+  APPS: {
+    ALL: 300,
+    WINDOWS: 301,
+    MAC: 302,
+    UNIX: 303,
+    HANDHELD: 304,
+    IOS: 305,
+    ANDROID: 306,
+    OTHER_OS: 399
+  },
+  GAMES: {
+    ALL: 400,
+    PC: 401,
+    MAC: 402,
+    PSx: 403,
+    XBOX360: 404,
+    Wii: 405,
+    HANDHELD: 406,
+    IOS: 407,
+    ANDROID: 408,
+    OTHER: 499
+  },
+  PORN: {
+    ALL: 500,
+    MOVIES: 501,
+    MOVIES_DVDR: 502,
+    PICTURES: 503,
+    GAMES: 504,
+    MOVIES_HD: 505,
+    MOVIE_CLIPS: 506,
+    OTHER: 599
+  },
+  OTHER: {
+    ALL: 600,
+    E_BOOKS: 601,
+    COMICS: 602,
+    PICTURES: 603,
+    COVERS: 604,
+    PHYSIBLES: 605,
+    OTHER: 699
+  }
+};
+
+function search(keyword, config = {}, retries = 2) {
+  if (!keyword || retries === 0) {
+    return Promise.reject(new Error(`Failed ${keyword} search`));
+  }
+  const proxyList = config.proxyList || defaultProxies;
+  const page = config.page || 0;
+  const category = config.cat || 0;
+
+  return raceFirstSuccessful(proxyList
+      .map((proxyUrl) => singleRequest(`${proxyUrl}/search/${keyword}/${page}/99/${category}`, config)))
+      .then((body) => parseBody(body))
+      .catch(() => search(keyword, config, retries - 1));
+}
+
+function dumps(config = {}, retries = 2) {
+  if (retries === 0) {
+    return Promise.reject(new Error(`Failed dump search`));
+  }
+  const proxyList = config.proxyList || defaultProxies;
+
+  return raceFirstSuccessful(proxyList
+      .map((proxyUrl) => singleRequest(`${proxyUrl}${dumpUrl}`, config)
+          .then((body) => body.match(/(<a href="[^"]+">[^<]+<\/a>.+\d)/g)
+              .map((group) => ({
+                url: `${proxyUrl}${dumpUrl}` + group.match(/<a href="([^"]+)">/)[1],
+                updatedAt: moment(group.match(/\s+([\w-]+\s+[\d:]+)\s+\d+$/)[1], 'DD-MMM-YYYY HH:mm').toDate()
+              })))))
+      .catch(() => dumps(config, retries - 1));
+}
+
+function singleRequest(requestUrl, config = {}) {
+  const timeout = config.timeout || defaultTimeout;
+
+  return new Promise(((resolve, reject) => {
+    needle.get(requestUrl,
+        { open_timeout: timeout, follow: 2 },
+        (err, res, body) => {
+          if (err || !body) {
+            reject(err || errors.REQUEST_ERROR);
+          } else if (body.includes('Access Denied') && !body.includes('<title>The Pirate Bay')) {
+            console.log(`Access Denied: ${url}`);
+            reject(new Error(`Access Denied: ${url}`));
+          } else if (body.includes('502: Bad gateway') ||
+            body.includes('403 Forbidden') ||
+            body.includes('Database maintenance') ||
+            body.includes('Origin DNS error') ||
+            !body.includes('<title>The Pirate Bay')) {
+            reject(errors.REQUEST_ERROR);
+          }
+
+          resolve(body);
+        });
+  }));
+}
+
+function parseBody(body) {
+  return new Promise((resolve, reject) => {
+    const $ = cheerio.load(body);
+
+    if (!$) {
+      reject(new Error(errors.PARSER_ERROR));
+    }
+
+    const torrents = [];
+
+    $('table[id=\'searchResult\'] tr').each(function() {
+      const name = $(this).find('.detLink').text();
+      if (!name) {
+        return;
+      }
+      torrents.push({
+        name: name,
+        seeders: parseInt($(this).find('td[align=\'right\']').eq(0).text(), 10),
+        leechers: parseInt($(this).find('td[align=\'right\']').eq(1).text(), 10),
+        magnetLink: $(this).find('a[title=\'Download this torrent using magnet\']').attr('href'),
+        category: parseInt($(this).find('a[title=\'More from this category\']').eq(0).attr('href').match(/\d+$/)[0], 10),
+        subcategory: parseInt($(this).find('a[title=\'More from this category\']').eq(1).attr('href').match(/\d+$/)[0], 10)
+      });
+    });
+    resolve(torrents);
+  });
+}
+
+function raceFirstSuccessful(promises) {
+  return Promise.all(promises.map((p) => {
+    // If a request fails, count that as a resolution so it will keep
+    // waiting for other possible successes. If a request succeeds,
+    // treat it as a rejection so Promise.all immediately bails out.
+    return p.then(
+        (val) => Promise.reject(val),
+        (err) => Promise.resolve(err)
+    );
+  })).then(
+      // If '.all' resolved, we've just got an array of errors.
+      (errors) => Promise.reject(errors),
+      // If '.all' rejected, we've got the result we wanted.
+      (val) => Promise.resolve(val)
+  );
+}
+
+module.exports = { search, dumps, Categories };

scrapers/piratebay_dump.js

@@ -0,0 +1,167 @@
+const moment = require('moment');
+const needle = require('needle');
+const Bottleneck = require('bottleneck');
+const { ungzip } = require('node-gzip');
+const LineByLineReader = require('line-by-line');
+const fs = require('fs');
+const { parse } = require('parse-torrent-title');
+const pirata = require('./api/thepiratebay');
+const { torrentFiles } = require('../lib/torrent');
+const repository = require('../lib/repository');
+const { getImdbId } = require('../lib/metadata');
+
+const NAME = 'thepiratebay';
+const CSV_FILE_PATH = '/tmp/tpb_dump.csv';
+
+const limiter = new Bottleneck({maxConcurrent: 40});
+
+async function scrape() {
+  const title = 'Я'
+      + '+(2014)_1280x720-raroch.mp4'
+      .replace(/^"|"$/g, '')
+      .normalize('NFKD') // normalize non-ASCII characters
+      .replace(/[\u0300-\u036F]/g, '')
+      .replace(/&\w{2,6};/g, ' ')
+      .replace(/\s+/g, ' ')
+      .replace(/[\W\s]+/, ' ');
+  const titleInfo = parse(title);
+  const imdbId = await getImdbId({
+    name: titleInfo.title.toLowerCase(),
+    year: titleInfo.year
+  });
+
+
+  const lastScraped = await repository.getProvider({ name: NAME });
+  const lastDump = await pirata.dumps().then((dumps) => dumps.sort((a, b) => b.updatedAt - a.updatedAt)[0]);
+
+  if (!lastScraped.lastScraped || lastScraped.lastScraped < lastDump.updatedAt) {
+    console.log(`starting to scrape tpb dump: ${JSON.stringify(lastDump)}`);
+    //await downloadDump(lastDump);
+
+    const lr = new LineByLineReader(CSV_FILE_PATH);
+    lr.on('line', (line) => {
+      if (line.includes("#ADDED")) {
+        return;
+      }
+      const row = line.match(/(?<=^|;)(".*"|[^;]+)(?=;|$)/g);
+      const torrent = {
+        uploadDate: moment(row[0], 'YYYY-MMM-DD HH:mm:ss').toDate(),
+        infoHash: Buffer.from(row[1], 'base64').toString('hex'),
+        title: row[2]
+            .replace(/^"|"$/g, '')
+            .replace(/&\w{2,6};/g, ' ')
+            .replace(/\s+/g, ' '),
+        size: parseInt(row[3], 10)
+      };
+
+      if (!limiter.empty()) {
+        lr.pause()
+      }
+
+      limiter.schedule(() => processTorrentRecord(torrent)
+            .catch((error) => console.log(`failed ${torrent.title} due: ${error}`)))
+            .then(() => limiter.empty())
+            .then((empty) => empty && lr.resume());
+    });
+    lr.on('error', (err) => {
+        console.log(err);
+    });
+    lr.on('end', () => {
+        fs.unlink(CSV_FILE_PATH);
+      updateProvider({ name: NAME, lastScraped: lastDump.updatedAt.toDate() });
+        console.log(`finished to scrape tpb dump: ${JSON.stringify(lastDump)}!`);
+    });
+  }
+}
+const allowedCategories = [
+  pirata.Categories.VIDEO.MOVIES,
+  pirata.Categories.VIDEO.MOVIES_HD,
+  pirata.Categories.VIDEO.MOVIES_DVDR,
+  pirata.Categories.VIDEO.MOVIES_3D,
+  pirata.Categories.VIDEO.TV_SHOWS,
+  pirata.Categories.VIDEO.TV_SHOWS_HD
+];
+const seriesCategories = [
+  pirata.Categories.VIDEO.TV_SHOWS,
+  pirata.Categories.VIDEO.TV_SHOWS_HD
+];
+async function processTorrentRecord(record) {
+  const persisted = await repository.getSkipTorrent(record)
+      .catch(() => repository.getTorrent(record)).catch(() => undefined);
+  if (persisted) {
+     return;
+  }
+
+  let page = 0;
+  let torrentFound;
+  while (!torrentFound && page < 5) {
+    const torrents = await pirata.search(record.title.replace(/[\W\s]+/, ' '), { page: page });
+    torrentFound = torrents.
+    filter(torrent => torrent.magnetLink.toLowerCase().includes(record.infoHash))[0];
+    page = torrents.length === 0 ? 1000 : page + 1;
+  }
+
+  if (!torrentFound) {
+    console.log(`not found: ${JSON.stringify(record)}`);
+    repository.createSkipTorrent(record);
+    return;
+  }
+  if (!allowedCategories.includes(torrentFound.subcategory)) {
+    console.log(`wrong category: ${torrentFound.name}`);
+    repository.createSkipTorrent(record);
+    return;
+  }
+
+  const type = seriesCategories.includes(torrentFound.subcategory) ? 'series' : 'movie';
+  console.log(`imdbId search: ${torrentFound.name}`);
+  const titleInfo = parse(torrentFound.name);
+  const imdbId = await getImdbId({
+    name: titleInfo.title.toLowerCase(),
+    year: titleInfo.year,
+    type: type
+  }).catch(() => undefined);
+
+  if (!imdbId) {
+    console.log(`imdbId not found: ${torrentFound.name}`);
+    repository.createFailedImdbTorrent(record);
+    return;
+  }
+
+  if (type === 'movie' || titleInfo.episode) {
+    repository.updateTorrent({
+      infoHash: record.infoHash,
+      provider: NAME,
+      title: torrentFound.name,
+      imdbId: imdbId,
+      uploadDate: record.uploadDate,
+      seeders: torrentFound.seeders,
+    });
+    return;
+  }
+
+  const files = await torrentFiles(record).catch(() => []);
+  if (!files || !files.length) {
+    console.log(`no video files found: ${torrentFound.name}`);
+    return;
+  }
+
+  repository.updateTorrent({
+    infoHash: record.infoHash,
+    provider: NAME,
+    title: torrentFound.name,
+    imdbId: imdbId,
+    uploadDate: record.uploadDate,
+    seeders: torrentFound.seeders,
+    files: files
+  })
+}
+
+function downloadDump(dump) {
+  console.log('downloading dump file...');
+  return needle('get', dump.url, { open_timeout: 2000, output: '/home/paulius/Downloads/tpb_dump.gz' })
+      .then((response) => response.body)
+      .then((body) => { console.log('unzipping dump file...'); return ungzip(body); })
+      .then((unzipped) => { console.log('writing dump file...'); return fs.promises.writeFile(CSV_FILE_PATH, unzipped); })
+}
+
+module.exports = { scrape };