mirror of
https://github.com/knightcrawler-stremio/knightcrawler.git
synced 2024-12-20 03:29:51 +00:00
moves scraper to a subpackage
This commit is contained in:
TheBeastLT
174
scraper/scrapers/1337x/1337x_api.js
Normal file
174
scraper/scrapers/1337x/1337x_api.js
Normal file
@@ -0,0 +1,174 @@
|
||||
const cheerio = require('cheerio');
|
||||
const needle = require('needle');
|
||||
const Sugar = require('sugar-date');
|
||||
const decode = require('magnet-uri');
|
||||
|
||||
const defaultProxies = [
|
||||
'https://1337x.to'
|
||||
];
|
||||
const defaultTimeout = 10000;
|
||||
|
||||
const Categories = {
|
||||
MOVIE: 'Movies',
|
||||
TV: 'TV',
|
||||
ANIME: 'Anime',
|
||||
DOCUMENTARIES: 'Documentaries',
|
||||
APPS: 'Apps',
|
||||
GAMES: 'Games',
|
||||
MUSIC: 'Music',
|
||||
PORN: 'XXX',
|
||||
OTHER: 'Other',
|
||||
};
|
||||
|
||||
function torrent(torrentId, config = {}, retries = 2) {
|
||||
if (!torrentId || retries === 0) {
|
||||
return Promise.reject(new Error(`Failed ${torrentId} query`));
|
||||
}
|
||||
const proxyList = config.proxyList || defaultProxies;
|
||||
const slug = torrentId.startsWith('/torrent/') ? torrentId.replace('/torrent/', '') : torrentId;
|
||||
|
||||
return raceFirstSuccessful(proxyList
|
||||
.map((proxyUrl) => singleRequest(`${proxyUrl}/torrent/${slug}`, config)))
|
||||
.then((body) => parseTorrentPage(body))
|
||||
.then((torrent) => ({ torrentId: slug, ...torrent }))
|
||||
.catch((err) => torrent(slug, config, retries - 1));
|
||||
}
|
||||
|
||||
function search(keyword, config = {}, retries = 2) {
|
||||
if (!keyword || retries === 0) {
|
||||
return Promise.reject(new Error(`Failed ${keyword} search`));
|
||||
}
|
||||
const proxyList = config.proxyList || defaultProxies;
|
||||
const page = config.page || 1;
|
||||
|
||||
return raceFirstSuccessful(proxyList
|
||||
.map((proxyUrl) => singleRequest(`${proxyUrl}/search/${keyword}/${page}/`, config)))
|
||||
.then((body) => parseTableBody(body))
|
||||
.catch((err) => search(keyword, config, retries - 1));
|
||||
}
|
||||
|
||||
function browse(config = {}, retries = 2) {
|
||||
if (retries === 0) {
|
||||
return Promise.reject(new Error(`Failed browse request`));
|
||||
}
|
||||
const proxyList = config.proxyList || defaultProxies;
|
||||
const page = config.page || 1;
|
||||
const category = config.category;
|
||||
|
||||
return raceFirstSuccessful(proxyList
|
||||
.map((proxyUrl) => singleRequest(`${proxyUrl}/cat/${category}/${page}/`, config)))
|
||||
.then((body) => parseTableBody(body))
|
||||
.catch((err) => browse(config, retries - 1));
|
||||
}
|
||||
|
||||
function singleRequest(requestUrl, config = {}) {
|
||||
const timeout = config.timeout || defaultTimeout;
|
||||
|
||||
return needle('get', requestUrl, { open_timeout: timeout, follow: 2 })
|
||||
.then((response) => {
|
||||
const body = response.body;
|
||||
if (!body) {
|
||||
throw new Error(`No body: ${requestUrl}`);
|
||||
} else if (body.includes('502: Bad gateway') ||
|
||||
body.includes('403 Forbidden') ||
|
||||
!(body.includes('1337x</title>'))) {
|
||||
throw new Error(`Invalid body contents: ${requestUrl}`);
|
||||
}
|
||||
return body;
|
||||
});
|
||||
}
|
||||
|
||||
function parseTableBody(body) {
|
||||
return new Promise((resolve, reject) => {
|
||||
const $ = cheerio.load(body);
|
||||
|
||||
if (!$) {
|
||||
reject(new Error('Failed loading body'));
|
||||
}
|
||||
|
||||
const torrents = [];
|
||||
|
||||
$('.table > tbody > tr').each((i, element) => {
|
||||
const row = $(element);
|
||||
torrents.push({
|
||||
name: row.find('a').eq(1).text(),
|
||||
torrentId: row.find('a').eq(1).attr('href').replace('/torrent/', ''),
|
||||
seeders: parseInt(row.children('td.coll-2').text()),
|
||||
leechers: parseInt(row.children('td.coll-3').text()),
|
||||
size: parseSize(row.children('td.coll-4').text())
|
||||
});
|
||||
});
|
||||
|
||||
resolve(torrents);
|
||||
});
|
||||
}
|
||||
|
||||
function parseTorrentPage(body) {
|
||||
return new Promise((resolve, reject) => {
|
||||
const $ = cheerio.load(body);
|
||||
|
||||
if (!$) {
|
||||
reject(new Error('Failed loading body'));
|
||||
}
|
||||
|
||||
const details = $('.torrent-detail-page');
|
||||
const magnetLink = details.find('a:contains(\'Magnet Download\')').attr('href');
|
||||
const imdbIdMatch = details.find('div[id=\'description\']').html().match(/imdb\.com\/title\/tt(\d+)/i);
|
||||
|
||||
const torrent = {
|
||||
name: decode(magnetLink).name.replace(/\+/g, ' '),
|
||||
infoHash: decode(magnetLink).infoHash,
|
||||
magnetLink: magnetLink,
|
||||
seeders: parseInt(details.find('strong:contains(\'Seeders\')').next().text(), 10),
|
||||
leechers: parseInt(details.find('strong:contains(\'Leechers\')').next().text(), 10),
|
||||
category: details.find('strong:contains(\'Category\')').next().text(),
|
||||
language: details.find('strong:contains(\'Language\')').next().text(),
|
||||
size: parseSize(details.find('strong:contains(\'Total size\')').next().text()),
|
||||
uploadDate: Sugar.Date.create(details.find('strong:contains(\'Date uploaded\')').next().text()),
|
||||
imdbId: imdbIdMatch && `tt${imdbIdMatch[1].padStart(7, '0')}`,
|
||||
files: details.find('div[id=\'files\']').first().find('li')
|
||||
.map((i, elem) => $(elem).text())
|
||||
.map((i, text) => ({
|
||||
fileIndex: i,
|
||||
name: text.match(/^(.+)\s\(.+\)$/)[1].replace(/^.+\//g, ''),
|
||||
path: text.match(/^(.+)\s\(.+\)$/)[1],
|
||||
size: parseSize(text.match(/^.+\s\((.+)\)$/)[1])
|
||||
})).get()
|
||||
};
|
||||
resolve(torrent);
|
||||
});
|
||||
}
|
||||
|
||||
function parseSize(sizeText) {
|
||||
if (!sizeText) {
|
||||
return undefined;
|
||||
}
|
||||
let scale = 1;
|
||||
if (sizeText.includes('GB')) {
|
||||
scale = 1024 * 1024 * 1024
|
||||
} else if (sizeText.includes('MB')) {
|
||||
scale = 1024 * 1024;
|
||||
} else if (sizeText.includes('KB')) {
|
||||
scale = 1024;
|
||||
}
|
||||
return Math.floor(parseFloat(sizeText) * scale);
|
||||
}
|
||||
|
||||
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 = { torrent, search, browse, Categories };
|
||||
89
scraper/scrapers/1337x/1337x_scraper.js
Normal file
89
scraper/scrapers/1337x/1337x_scraper.js
Normal file
@@ -0,0 +1,89 @@
|
||||
const moment = require('moment');
|
||||
const Bottleneck = require('bottleneck');
|
||||
const leetx = require('./1337x_api');
|
||||
const { Type } = require('../../lib/types');
|
||||
const repository = require('../../lib/repository');
|
||||
const {
|
||||
createTorrentEntry,
|
||||
createSkipTorrentEntry,
|
||||
getStoredTorrentEntry,
|
||||
updateTorrentSeeders
|
||||
} = require('../../lib/torrentEntries');
|
||||
|
||||
const NAME = '1337x';
|
||||
const UNTIL_PAGE = 1;
|
||||
const TYPE_MAPPING = typeMapping();
|
||||
|
||||
const limiter = new Bottleneck({ maxConcurrent: 40 });
|
||||
|
||||
async function scrape() {
|
||||
const scrapeStart = moment();
|
||||
const lastScrape = await repository.getProvider({ name: NAME });
|
||||
console.log(`[${scrapeStart}] starting ${NAME} scrape...`);
|
||||
|
||||
const latestTorrents = await getLatestTorrents();
|
||||
return Promise.all(latestTorrents.map(torrent => limiter.schedule(() => processTorrentRecord(torrent))))
|
||||
.then(() => {
|
||||
lastScrape.lastScraped = scrapeStart;
|
||||
lastScrape.lastScrapedId = latestTorrents.length && latestTorrents[latestTorrents.length - 1].torrentId;
|
||||
return repository.updateProvider(lastScrape);
|
||||
})
|
||||
.then(() => console.log(`[${moment()}] finished ${NAME} scrape`));
|
||||
}
|
||||
|
||||
async function getLatestTorrents() {
|
||||
const allowedCategories = [
|
||||
leetx.Categories.MOVIE,
|
||||
leetx.Categories.TV,
|
||||
leetx.Categories.ANIME,
|
||||
leetx.Categories.DOCUMENTARIES
|
||||
];
|
||||
|
||||
return Promise.all(allowedCategories.map(category => getLatestTorrentsForCategory(category)))
|
||||
.then(entries => entries.reduce((a, b) => a.concat(b), []));
|
||||
}
|
||||
|
||||
async function getLatestTorrentsForCategory(category, page = 1) {
|
||||
return leetx.browse(({ category: category, page: page }))
|
||||
.then(torrents => torrents.length && page < UNTIL_PAGE
|
||||
? getLatestTorrents(category, page + 1).then(nextTorrents => torrents.concat(nextTorrents))
|
||||
: torrents)
|
||||
.catch(() => []);
|
||||
}
|
||||
|
||||
async function processTorrentRecord(record) {
|
||||
if (await getStoredTorrentEntry(record)) {
|
||||
return updateTorrentSeeders(record);
|
||||
}
|
||||
|
||||
const torrentFound = await leetx.torrent(record.torrentId).catch(() => undefined);
|
||||
|
||||
if (!torrentFound || !TYPE_MAPPING[torrentFound.category]) {
|
||||
return createSkipTorrentEntry(record);
|
||||
}
|
||||
|
||||
const torrent = {
|
||||
infoHash: torrentFound.infoHash,
|
||||
provider: NAME,
|
||||
torrentId: torrentFound.torrentId,
|
||||
title: torrentFound.name.replace(/\t|\s+/g, ' '),
|
||||
seeders: torrentFound.seeders,
|
||||
size: torrentFound.size,
|
||||
type: TYPE_MAPPING[torrentFound.category],
|
||||
uploadDate: torrentFound.uploadDate,
|
||||
imdbId: torrentFound.imdbId,
|
||||
};
|
||||
|
||||
return createTorrentEntry(torrent);
|
||||
}
|
||||
|
||||
function typeMapping() {
|
||||
const mapping = {};
|
||||
mapping[leetx.Categories.MOVIE] = Type.MOVIE;
|
||||
mapping[leetx.Categories.DOCUMENTARIES] = Type.MOVIE;
|
||||
mapping[leetx.Categories.TV] = Type.SERIES;
|
||||
mapping[leetx.Categories.ANIME] = Type.ANIME;
|
||||
return mapping;
|
||||
}
|
||||
|
||||
module.exports = { scrape };
|
||||
Reference in New Issue
Block a user