updates the package structure and updates initial horriblesubs scraper WIP

This commit is contained in:
TheBeastLT
2020-01-07 13:33:46 +01:00
parent 643917939b
commit 051c50de3f
12 changed files with 264 additions and 280 deletions

View File

@@ -5,8 +5,14 @@ const { Type } = require('./types');
const MIN_SIZE = 20 * 1024 * 1024; // 20 MB
async function parseTorrentFiles(torrent, imdbId) {
async function parseTorrentFiles(torrent, imdbId, kitsuId) {
const parsedTorrentName = parse(torrent.title);
parsedTorrentName.hasMovies = parsedTorrentName.complete || !!torrent.title.match(/movies?(?:\W|$)/);
const metadata = await getMetadata(kitsuId || imdbId, torrent.type || Type.MOVIE).catch(() => undefined);
if (metadata && metadata.type !== torrent.type && torrent.type !== Type.ANIME) {
throw new Error(`Mismatching entry type for ${torrent.name}: ${torrent.type}!=${metadata.type}`);
}
if (torrent.type === Type.MOVIE) {
if (parsedTorrentName.complete) {
@@ -27,31 +33,20 @@ async function parseTorrentFiles(torrent, imdbId) {
});
}
return [{
return [ {
infoHash: torrent.infoHash,
title: torrent.title,
size: torrent.size,
imdbId: imdbId,
}];
imdbId: imdbId || metadata && metadata.imdb_id,
kitsuId: kitsuId || metadata && metadata.kitsu_id
} ];
}
if (parsedTorrentName.season && parsedTorrentName.episode) {
return [{
infoHash: torrent.infoHash,
title: torrent.title,
size: torrent.size,
imdbId: imdbId,
imdbSeason: parsedTorrentName.season,
imdbEpisode: parsedTorrentName.episode
}];
}
parsedTorrentName.hasMovies = parsedTorrentName.complete || !!torrent.title.match(/movies?(?:\W|$)/);
return torrentFiles(torrent)
return getSeriesFiles(torrent, parsedTorrentName)
.then((files) => files
.filter((file) => file.size > MIN_SIZE)
.map((file) => parseSeriesFile(file, parsedTorrentName)))
.then((files) => decomposeAbsoluteEpisodes(files, torrent, imdbId))
.then((files) => decomposeAbsoluteEpisodes(files, metadata))
.then((files) => Promise.all(files.map(file => file.isMovie
? mapSeriesMovie(file, torrent.infoHash)
: mapSeriesEpisode(file, torrent.infoHash, imdbId))))
@@ -62,6 +57,18 @@ async function parseTorrentFiles(torrent, imdbId) {
});
}
async function getSeriesFiles(torrent, parsedTorrentName) {
if (parsedTorrentName.episode || parsedTorrentName.date) {
return [ {
name: torrent.title,
path: torrent.title,
size: torrent.size
} ];
}
return torrentFiles(torrent);
}
async function mapSeriesEpisode(file, infoHash, imdbId) {
if (!file.episodes) {
return Promise.resolve([]);
@@ -69,21 +76,22 @@ async function mapSeriesEpisode(file, infoHash, imdbId) {
return Promise.resolve(file.episodes.map(episode => ({
infoHash: infoHash,
fileIndex: file.fileIndex,
title: file.name,
title: file.path || file.name,
size: file.size,
imdbId: imdbId,
imdbSeason: file.season,
imdbEpisode: episode})))
imdbEpisode: episode
})))
}
async function mapSeriesMovie(file, infoHash) {
return findMovieImdbId(file).then((imdbId) => [{
return findMovieImdbId(file).then((imdbId) => [ {
infoHash: infoHash,
fileIndex: file.fileIndex,
title: file.name,
size: file.size,
imdbId: imdbId
}])
} ])
}
function parseSeriesFile(file, parsedTorrentName) {
@@ -96,7 +104,8 @@ function parseSeriesFile(file, parsedTorrentName) {
const pathInfo = parse(folders[folders.length - 2]);
fileInfo.season = pathInfo.season;
}
fileInfo.isMovie = parsedTorrentName.hasMovies && !fileInfo.season && !fileInfo.episodes || !!fileInfo.year;
fileInfo.isMovie = parsedTorrentName.hasMovies && !fileInfo.season &&
(!fileInfo.episodes || !!fileInfo.year || !!file.name.match(/\b(?:\d+[ .]movie|movie[ .]\d+)\b/i));
return { ...file, ...fileInfo };
}
@@ -111,12 +120,11 @@ function findMovieImdbId(title) {
return getImdbId(searchQuery).catch((error) => undefined);
}
async function decomposeAbsoluteEpisodes(files, torrent, imdbId) {
async function decomposeAbsoluteEpisodes(files, metadata) {
if (files.every((file) => !file.episodes || file.episodes.every((ep) => ep < 100))) {
return files; // nothing to decompose
}
const metadata = await getMetadata(imdbId, torrent.type || Type.MOVIE);
// decompose if season is inside path, but individual files are concatenated ex. 101 (S01E01)
files
.filter(file => file.season && metadata.episodeCount[file.season] < 100)