tools/knightcrawler
1
0
Fork 0
mirror of https://github.com/knightcrawler-stremio/knightcrawler.git synced 2024-12-20 03:29:51 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[scraper] check if episode imdbid fro eztv

Browse Source
This commit is contained in:
TheBeastLT
2020-10-02 14:06:51 +02:00
parent 5426707dd9
commit 31e3b0bf5f
2 changed files with 17 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
scraper/lib/metadata.js
View File

@@ -104,7 +104,7 @@ async function getImdbId(info, type) {
return cacheWrapImdbId(key, return cacheWrapImdbId(key,
() => new Promise((resolve, reject) => { () => new Promise((resolve, reject) => {
nameToImdb({ name, year, type }, function (err, res) { nameToImdb({ name, year, type }, function (err, res) {
if (res) { if (res && !info.date) {
resolve(res); resolve(res);
} else { } else {
reject(err || new Error('failed imdbId search')); reject(err || new Error('failed imdbId search'));
@@ -112,7 +112,7 @@ async function getImdbId(info, type) {
}); });
}).catch(() => googleIt({ query, userAgent: getRandomUserAgent(), disableConsole: true }) }).catch(() => googleIt({ query, userAgent: getRandomUserAgent(), disableConsole: true })
.then(results => results.length ? results : Promise.reject('No results')) .then(results => results.length ? results : Promise.reject('No results'))
.catch(() => bing.web(query)) // .catch(() => bing.web(query))
.then(results => results .then(results => results
.map(result => result.link) .map(result => result.link)
.find(result => result.includes('imdb.com/title/'))) .find(result => result.includes('imdb.com/title/')))
@@ -139,4 +139,13 @@ async function getKitsuId(info) {
})); }));
} }
module.exports = { getMetadata, getImdbId, getKitsuId, escapeHTML, escapeTitle }; async function isEpisodeImdbId(imdbId) {
if (!imdbId) {
return false;
}
return needle('get', `https://www.imdb.com/title/${imdbId}/`, { open_timeout: 10000, follow: 2 })
.then(response => !!(response.body && response.body.includes('video.episode')))
.catch((err) => false);
}
module.exports = { getMetadata, getImdbId, getKitsuId, isEpisodeImdbId, escapeHTML, escapeTitle };

6
scraper/scrapers/eztv/eztv_scraper.js
View File

@@ -5,6 +5,7 @@ const eztv = require('./eztv_api');
const { Type } = require('../../lib/types'); const { Type } = require('../../lib/types');
const repository = require('../../lib/repository'); const repository = require('../../lib/repository');
const { createTorrentEntry, checkAndUpdateTorrent } = require('../../lib/torrentEntries'); const { createTorrentEntry, checkAndUpdateTorrent } = require('../../lib/torrentEntries');
const { isEpisodeImdbId } = require('../../lib/metadata');
const NAME = 'EZTV'; const NAME = 'EZTV';
const UNTIL_PAGE = 10; const UNTIL_PAGE = 10;
@@ -63,6 +64,9 @@ async function processTorrentRecord(record) {
// imdb id for talk shows is usually incorrect on eztv // imdb id for talk shows is usually incorrect on eztv
const parsedTitle = parse(record.name); const parsedTitle = parse(record.name);
const dateEpisode = !parsedTitle.season && parsedTitle.date; const dateEpisode = !parsedTitle.season && parsedTitle.date;
if (dateEpisode && await isEpisodeImdbId(record.imdbId)) {
delete record.imdbId;
}
const torrent = { const torrent = {
infoHash: record.infoHash, infoHash: record.infoHash,
@@ -73,7 +77,7 @@ async function processTorrentRecord(record) {
size: record.size, size: record.size,
seeders: record.seeders, seeders: record.seeders,
uploadDate: record.uploadDate, uploadDate: record.uploadDate,
imdbId: !dateEpisode && record.imdbId, imdbId: record.imdbId,
}; };
return createTorrentEntry(torrent).then(() => torrent); return createTorrentEntry(torrent).then(() => torrent);