remove scraper module

This commit is contained in:
TheBeastLT
2022-06-16 17:44:38 +03:00
parent a253e8e0b0
commit 554c07d636
69 changed files with 0 additions and 61771 deletions

View File

@@ -1,163 +0,0 @@
const axios = require('axios');
const moment = require("moment")
const cheerio = require("cheerio");
const decode = require('magnet-uri');
const { escapeHTML } = require('../../lib/metadata');
const { getRandomUserAgent } = require('../../lib/requestHelper');
const { isPtDubbed, sanitizePtName, sanitizePtLanguages, sanitizePtOriginalName } = require('../scraperHelper')
const defaultTimeout = 30000;
const maxSearchPage = 50
const baseUrl = 'https://comando.to';
const Categories = {
MOVIE: 'filmes',
TV: 'series',
ANIME: 'animes',
DOCUMENTARIES: 'documentario'
};
function torrent(torrentId, config = {}, retries = 2) {
if (!torrentId || retries === 0) {
return Promise.reject(new Error(`Failed ${torrentId} query`));
}
const slug = torrentId.split("/")[3];
return singleRequest(`${baseUrl}/${slug}`, config)
.then((body) => parseTorrentPage(body))
.then((torrent) => torrent.map(el => ({ torrentId: slug, ...el })))
.catch((err) => {
console.warn(`Failed Comando ${slug} request: `, err);
return torrent(torrentId, config, retries - 1)
});
}
function search(keyword, config = {}, retries = 2) {
if (!keyword || retries === 0) {
return Promise.reject(new Error(`Failed ${keyword} search`));
}
const page = config.page || 1;
const extendToPage = Math.min(maxSearchPage, (config.extendToPage || 1))
return singleRequest(`${baseUrl}/page/${page}/?s=${keyword}`, config)
.then(body => parseTableBody(body))
.then(torrents => torrents.length === 40 && page < extendToPage
? search(keyword, { ...config, page: page + 1 }).catch(() => [])
.then(nextTorrents => torrents.concat(nextTorrents))
: torrents)
.catch((err) => search(keyword, config, retries - 1));
}
function browse(config = {}, retries = 2) {
if (retries === 0) {
return Promise.reject(new Error(`Failed browse request`));
}
const page = config.page || 1;
const category = config.category;
return singleRequest(`${baseUrl}/category/${category}/page/${page}/`, config)
.then((body) => parseTableBody(body))
.catch((err) => browse(config, retries - 1));
}
function singleRequest(requestUrl, config = {}) {
const timeout = config.timeout || defaultTimeout;
const options = { headers: { 'User-Agent': getRandomUserAgent() }, timeout: timeout };
return axios.get(requestUrl, options)
.then((response) => {
const body = response.data;
if (!body) {
throw new Error(`No body: ${requestUrl}`);
} else if (body.includes('502: Bad gateway') ||
body.includes('403 Forbidden')) {
throw new Error(`Invalid body contents: ${requestUrl}`);
}
return body;
})
.catch(error => Promise.reject(error.message || error));
}
function parseTableBody(body) {
return new Promise((resolve, reject) => {
const $ = cheerio.load(body);
if (!$) {
reject(new Error('Failed loading body'));
}
const torrents = [];
$('article').each((i, element) => {
const row = $(element);
torrents.push({
name: row.find("h2 > a").text(),
torrentId: row.find("h2 > a").attr("href")
});
});
resolve(torrents);
});
}
function parseTorrentPage(body) {
return new Promise((resolve, reject) => {
const $ = cheerio.load(body);
if (!$) {
reject(new Error('Failed loading body'));
}
const magnets = $('h2 > strong')
.filter((i, elem) => isPtDubbed($(elem).text())).parent()
.map((i, elem) => $(elem).nextUntil('h2, hr'))
.map((i, elem) => $(elem).find('a[href^="magnet"]'))
.map((i, section) => $(section).attr("href")).get();
const details = $('strong, b').filter((i, elem) => $(elem).text().match(/Servidor|Orig(?:\.|inal)/)).parent();
const imdbIdMatch = details.find('a[href*="imdb.com"]').attr('href')
const torrents = magnets.map(magnetLink => {
const decodedMagnet = decode(magnetLink);
const originalNameElem = details.find('strong, b')
.filter((i, elem) => $(elem).text().match(/Baixar|Orig(?:\.|inal)|^Título:/));
const languagesElem = details.find('strong, b')
.filter((i, elem) => $(elem).text().match(/^\s*([IÍ]dioma|[AÁ]udio)/));
const originalName = parseOriginalName(originalNameElem);
const title = decodedMagnet.name && escapeHTML(decodedMagnet.name.replace(/\+/g, ' '));
return {
title: title ? sanitizePtName(title) : originalName,
originalName: sanitizePtOriginalName(originalName),
year: details.find('a[href*="comando.to/category/"]').text(),
infoHash: decodedMagnet.infoHash,
magnetLink: magnetLink,
category: parseCategory($('div.entry-categories').html()),
uploadDate: new Date(moment($('a.updated').text(), 'LL', 'pt-br').format()),
imdbId: imdbIdMatch ? imdbIdMatch.split('/')[4] : null,
languages: sanitizePtLanguages(languagesElem[0].nextSibling.nodeValue)
}
});
resolve(torrents.filter((x) => x));
});
}
function parseOriginalName(originalNameElem) {
if (!originalNameElem[0]) {
return '';
}
const originalName = originalNameElem.next().text()
|| originalNameElem[0].nextSibling.nodeValue
|| originalNameElem.text();
return originalName.replace(/[^:]*: ?/, '').trim();
}
function parseCategory(categorys) {
const $ = cheerio.load(categorys)
if ($('a:contains(\'animes\')').text()) {
return Categories.ANIME
}
if ($('a:contains(\'Filmes\')').text()) {
return Categories.MOVIE
}
if ($('a:contains(\'Series\')').text()) {
return Categories.TV
}
}
module.exports = { torrent, search, browse, Categories };

View File

@@ -1,112 +0,0 @@
const moment = require("moment");
const Bottleneck = require("bottleneck");
const comando = require("./comando_api");
const { Type } = require("../../lib/types");
const repository = require("../../lib/repository");
const Promises = require("../../lib/promises");
const { updateCurrentSeeders, updateTorrentSize } = require("../../lib/torrent");
const { createTorrentEntry, checkAndUpdateTorrent } = require("../../lib/torrentEntries");
const { getImdbId } = require("../../lib/metadata");
const NAME = "Comando";
const UNTIL_PAGE = 5;
const TYPE_MAPPING = typeMapping();
const limiter = new Bottleneck({ maxConcurrent: 5 });
async function scrape() {
const scrapeStart = moment();
const lastScrape = await repository.getProvider({ name: NAME });
console.log(`[${scrapeStart}] starting ${NAME} scrape...`);
return scrapeLatestTorrents()
.then(() => {
lastScrape.lastScraped = scrapeStart;
return lastScrape.save();
})
.then(() => console.log(`[${moment()}] finished ${NAME} scrape`));
}
async function updateSeeders(torrent) {
return limiter.schedule(() => comando.torrent(torrent.torrentId));
}
async function scrapeLatestTorrents() {
const allowedCategories = [
comando.Categories.MOVIE,
comando.Categories.TV
];
return Promises.sequence(allowedCategories
.map((category) => () => scrapeLatestTorrentsForCategory(category)))
.then((entries) => entries.reduce((a, b) => a.concat(b), []));
}
async function scrapeLatestTorrentsForCategory(category, page = 1) {
console.log(`Scrapping ${NAME} ${category} category page ${page}`);
return comando.browse({ category, page })
.catch((error) => {
console.warn(`Failed ${NAME} scrapping for [${page}] ${category} due: `, error);
return Promise.resolve([]);
})
.then((torrents) => Promise.all(torrents.map((torrent) => limiter.schedule(() => processEntry(torrent)))))
.then((resolved) => resolved.length > 0 && page < untilPage(category)
? scrapeLatestTorrentsForCategory(category, page + 1)
: Promise.resolve());
}
async function processEntry(entry) {
return comando.torrent(entry.torrentId)
.then(records => Promises.sequence(records.map(record => () => processTorrentRecord(record))))
.catch(() => undefined);
}
async function processTorrentRecord(foundTorrent) {
if (await checkAndUpdateTorrent({ provider: NAME, ...foundTorrent })) {
return foundTorrent;
}
if (!foundTorrent.size) {
await updateTorrentSize(foundTorrent);
}
if (!Number.isInteger(foundTorrent.seeders)) {
await updateCurrentSeeders(foundTorrent);
}
if (!foundTorrent.imdbId && foundTorrent.originalName) {
const info = { title: foundTorrent.originalName, year: foundTorrent.year };
foundTorrent.imdbId = await getImdbId(info, TYPE_MAPPING[foundTorrent.category]).catch(() => undefined);
}
const torrent = {
infoHash: foundTorrent.infoHash,
provider: NAME,
torrentId: foundTorrent.torrentId,
title: foundTorrent.title,
type: TYPE_MAPPING[foundTorrent.category],
imdbId: foundTorrent.imdbId,
uploadDate: foundTorrent.uploadDate,
seeders: foundTorrent.seeders,
size: foundTorrent.size,
files: foundTorrent.files,
languages: foundTorrent.languages
};
return createTorrentEntry(torrent);
}
function typeMapping() {
const mapping = {};
mapping[comando.Categories.MOVIE] = Type.MOVIE;
mapping[comando.Categories.DOCUMENTARIES] = Type.SERIES;
mapping[comando.Categories.TV] = Type.SERIES;
mapping[comando.Categories.ANIME] = Type.ANIME;
return mapping;
}
function untilPage(category) {
if (comando.Categories.TV === category) {
return 5;
}
return UNTIL_PAGE;
}
module.exports = { scrape, updateSeeders, NAME };