forked from 50n50/sources
fix: Update s.to source to support new site structure and improve episode extraction
This commit is contained in:
JMcrafter26
+197
-139
@@ -5,19 +5,71 @@
|
||||
async function searchResults(keyword) {
|
||||
try {
|
||||
const encodedKeyword = encodeURIComponent(keyword);
|
||||
const searchApiUrl = `https://s.to/ajax/seriesSearch?keyword=${encodedKeyword}`;
|
||||
const searchApiUrl = `https://s.to/suche?term=${encodedKeyword}`;
|
||||
const response = await soraFetch(searchApiUrl);
|
||||
const responseText = await response?.text() ?? response;
|
||||
const text = response.text ? await response.text() : await response;
|
||||
|
||||
const data = await JSON.parse(responseText);
|
||||
// parse html
|
||||
/* <div class="col-6 col-md-4 col-lg-2">
|
||||
<a href="https://s.to/serie/pluribus-glck-ist-ansteckend" class="text-decoration-none">
|
||||
<div class="card cover-card h-100 border-0 shadow-sm">
|
||||
<a href="https://s.to/serie/pluribus-glck-ist-ansteckend" class="d-block show-cover">
|
||||
<picture>
|
||||
|
||||
const transformedResults = data.map(serie => ({
|
||||
title: serie.name,
|
||||
image: `https://s.to${serie.cover}`,
|
||||
href: `https://s.to/serie/stream/${serie.link}`
|
||||
}));
|
||||
<source type="image/avif" srcset="
|
||||
https://s.to/media/images/channel/mobile/pluribus-glck-ist-ansteckend-tombd2cv?format=avif 375w,
|
||||
https://s.to/media/images/channel/tablet/pluribus-glck-ist-ansteckend-tombd2cv?format=avif 768w,
|
||||
https://s.to/media/images/channel/desktop/pluribus-glck-ist-ansteckend-tombd2cv?format=avif 1024w
|
||||
" sizes="(max-width: 600px) 375px,
|
||||
(max-width: 992px) 768px,
|
||||
1024px">
|
||||
|
||||
return JSON.stringify(transformedResults);
|
||||
|
||||
<source type="image/webp" srcset="
|
||||
https://s.to/media/images/channel/mobile/pluribus-glck-ist-ansteckend-tombd2cv?format=webp 375w,
|
||||
https://s.to/media/images/channel/tablet/pluribus-glck-ist-ansteckend-tombd2cv?format=webp 768w,
|
||||
https://s.to/media/images/channel/desktop/pluribus-glck-ist-ansteckend-tombd2cv?format=webp 1024w
|
||||
" sizes="(max-width: 600px) 375px,
|
||||
(max-width: 992px) 768px,
|
||||
1024px">
|
||||
|
||||
|
||||
<img src="https://s.to/media/images/channel/desktop/pluribus-glck-ist-ansteckend-tombd2cv?format=jpg"
|
||||
srcset="
|
||||
https://s.to/media/images/channel/desktop/pluribus-glck-ist-ansteckend-tombd2cv?format=jpg 1x,
|
||||
https://s.to/media/images/channel/2x-desktop/pluribus-glck-ist-ansteckend-tombd2cv?format=jpg 2x
|
||||
" alt="Pluribus - Glück ist ansteckend" class="img-fluid w-100">
|
||||
</picture>
|
||||
|
||||
|
||||
|
||||
</a>
|
||||
<div class="card-body py-2 p-1">
|
||||
<h6 class="show-title mb-0 small" title="Pluribus - Glück ist ansteckend">Pluribus - Glück ist
|
||||
ansteckend</h6>
|
||||
</div>
|
||||
</div>
|
||||
</a>
|
||||
</div>
|
||||
...
|
||||
*/
|
||||
const searchRegex = /<a\s+href="([^"]+)"\s+class="d-block\s+show-cover"[\s\S]*?<img\s+src="([^"]+)"[\s\S]*?class="show-title[^"]*"[^>]*>([\s\S]*?)<\//g;
|
||||
const results = [];
|
||||
let match;
|
||||
while ((match = searchRegex.exec(text)) !== null) {
|
||||
const [_, href, image, title] = match;
|
||||
// check if href already exists in results
|
||||
if (results.some(result => result.href === href.trim())) {
|
||||
continue;
|
||||
}
|
||||
|
||||
results.push({ title: title.trim(), image: image.trim(), href: href.trim() });
|
||||
}
|
||||
|
||||
|
||||
|
||||
console.log("Search Results: " + JSON.stringify(results));
|
||||
return JSON.stringify(results);
|
||||
|
||||
} catch (error) {
|
||||
sendLog('Fetch error:' + error);
|
||||
@@ -29,31 +81,49 @@ async function extractDetails(url) {
|
||||
try {
|
||||
const fetchUrl = `${url}`;
|
||||
const response = await soraFetch(fetchUrl);
|
||||
const text = response.text ? await response.text() : response;
|
||||
const text = response.text ? await response.text() : await response;
|
||||
|
||||
// get description <span class="description-text">
|
||||
const descriptionRegex = /<span class="description-text"[^>]*>([\s\S]*?)<\/span>/;
|
||||
const descriptionMatch = descriptionRegex.exec(text);
|
||||
let description = descriptionMatch ? descriptionMatch[1].trim() : 'No description available';
|
||||
description = description.replace(/</g, '<').replace(/>/g, '>').replace(/&/g, '&').replace(/"/g, '"').replace(/'/g, "'");
|
||||
|
||||
const descriptionRegex = /<p\s+class="seri_des"\s+itemprop="accessibilitySummary"\s+data-description-type="review"\s+data-full-description="([^"]*)".*?>(.*?)<\/p>/s;
|
||||
const aliasesRegex = /<h1\b[^>]*\bdata-alternativetitles="([^"]+)"[^>]*>/i;
|
||||
// get year (airdate) <a class="small text-muted" href="https://s.to/jahr/2025">2025</a>
|
||||
const yearRegex = /<a class="small text-muted" href="https:\/\/s\.to\/jahr\/\d{4}">(\d{4})<\/a>/;
|
||||
const yearMatch = yearRegex.exec(text);
|
||||
const airdateMatch = yearMatch ? `${yearMatch[1]}` : 'Unknown Year';
|
||||
|
||||
const aliasesMatch = aliasesRegex.exec(text);
|
||||
let aliasesArray = [];
|
||||
if (aliasesMatch) {
|
||||
aliasesArray = aliasesMatch[1].split(',').map(a => a.trim());
|
||||
|
||||
// get genres
|
||||
/* <li class="series-group">
|
||||
<strong class="me-1">Genre:</strong>
|
||||
|
||||
|
||||
<a href="https://s.to/genre/science-fiction" class="link-light">Science Fiction</a>, <a href="https://s.to/genre/comedy" class="link-light">Comedy</a>, <a href="https://s.to/genre/drama" class="link-light">Drama</a>
|
||||
|
||||
</li>
|
||||
*/
|
||||
const genresRegex = /<li class="series-group">\s*<strong class="me-1">Genre:<\/strong>([\s\S]*?)<\/li>/;
|
||||
const genresMatch = genresRegex.exec(text);
|
||||
let genres = '';
|
||||
if (genresMatch) {
|
||||
const genreLinksRegex = /<a href="https:\/\/s\.to\/genre\/[^"]+" class="link-light">([^<]+)<\/a>/g;
|
||||
let genreMatch;
|
||||
while ((genreMatch = genreLinksRegex.exec(genresMatch[1])) !== null) {
|
||||
genres += genreMatch[1] + ', ';
|
||||
}
|
||||
genres = genres.replace(/, $/, '');
|
||||
}
|
||||
|
||||
const descriptionMatch = descriptionRegex.exec(text) || [];
|
||||
// sanitize description by removing HTML tags
|
||||
let description = descriptionMatch[1] || '';
|
||||
description = description.replace(/<[^>]+>/g, '').trim();
|
||||
|
||||
|
||||
const airdateMatch = "Unknown"; // TODO: Implement airdate extraction
|
||||
|
||||
const transformedResults = [{
|
||||
description: description || 'No description available',
|
||||
aliases: aliasesArray[0] || 'No aliases available',
|
||||
aliases: genres || '',
|
||||
airdate: airdateMatch
|
||||
}];
|
||||
|
||||
|
||||
return JSON.stringify(transformedResults);
|
||||
} catch (error) {
|
||||
sendLog('Details error:' + error);
|
||||
@@ -77,15 +147,11 @@ async function extractEpisodes(url) {
|
||||
console.log("Season Links: " + JSON.stringify(seasonLinks));
|
||||
|
||||
for (const seasonLink of seasonLinks) {
|
||||
const seasonEpisodes = await fetchSeasonEpisodes(`${baseUrl}${seasonLink}`);
|
||||
const seasonEpisodes = await fetchSeasonEpisodes(`${seasonLink}`);
|
||||
finishedList.push(...seasonEpisodes);
|
||||
}
|
||||
console.log("Finished Episode List: " + JSON.stringify(finishedList));
|
||||
|
||||
// Replace the field "number" with the current index of each item, starting from 1
|
||||
finishedList.forEach((item, index) => {
|
||||
item.number = index + 1;
|
||||
});
|
||||
|
||||
return JSON.stringify(finishedList);
|
||||
|
||||
@@ -99,54 +165,19 @@ async function extractEpisodes(url) {
|
||||
|
||||
async function extractStreamUrl(url) {
|
||||
try {
|
||||
const baseUrl = 'https://s.to';
|
||||
const language = [2, 4, 3]; // Englisch Dub, Eng-Sub, Ger-Sub
|
||||
|
||||
const fetchUrl = `${url}`;
|
||||
const response = await soraFetch(fetchUrl);
|
||||
if (!_0xCheck()) return 'https://files.catbox.moe/avolvc.mp4';
|
||||
const text = response.text ? await response.text() : response;
|
||||
|
||||
const finishedList = [];
|
||||
const languageList = getAvailableLanguages(text);
|
||||
const videoLinks = getVideoLinks(text);
|
||||
if (!_0xCheck()) return 'https://files.catbox.moe/avolvc.mp4';
|
||||
sendLog("Video Links: " + JSON.stringify(videoLinks));
|
||||
|
||||
for (const videoLink of videoLinks) {
|
||||
const language = languageList.find(
|
||||
(l) => l.langKey === videoLink.langKey
|
||||
);
|
||||
if (language) {
|
||||
finishedList.push({
|
||||
provider: videoLink.provider,
|
||||
href: `${baseUrl}${videoLink.href}`,
|
||||
language: language.title,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// Select the hoster
|
||||
let providerArray = selectHoster(finishedList);
|
||||
let newProviderArray = {};
|
||||
let providerArray = selectHoster(videoLinks, language);
|
||||
|
||||
for (const [key, value] of Object.entries(providerArray)) {
|
||||
const providerLink = key;
|
||||
const providerName = value;
|
||||
|
||||
// fetch the provider link and extract the stream URL
|
||||
const streamUrl = await soraFetch(providerLink);
|
||||
console.log("Stream URL: " + streamUrl);
|
||||
const winLocRegex = /window\.location\.href\s*=\s*['"]([^'"]+)['"]/;
|
||||
const winLocMatch = await winLocRegex.exec(streamUrl);
|
||||
let winLocUrl = null;
|
||||
if (!winLocMatch) {
|
||||
winLocUrl = providerLink;
|
||||
} else {
|
||||
winLocUrl = winLocMatch[1];
|
||||
}
|
||||
|
||||
newProviderArray[winLocUrl] = providerName;
|
||||
}
|
||||
|
||||
sendLog("Provider List: " + JSON.stringify(newProviderArray));
|
||||
sendLog("Provider List: " + JSON.stringify(providerArray));
|
||||
|
||||
// Call the multiExtractor function with the new provider array
|
||||
// let streams = [];
|
||||
@@ -159,7 +190,7 @@ async function extractStreamUrl(url) {
|
||||
|
||||
try {
|
||||
// Inside extractStreamUrl function
|
||||
let streams = await multiExtractor(newProviderArray);
|
||||
let streams = await multiExtractor(providerArray);
|
||||
let returnedStreams = {
|
||||
streams: streams,
|
||||
};
|
||||
@@ -194,8 +225,14 @@ async function extractStreamUrl(url) {
|
||||
/////////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
// Helper function to select the hoster
|
||||
function selectHoster(finishedList) {
|
||||
function selectHoster(finishedList, preferredLang) {
|
||||
let provider = {};
|
||||
const languages = {
|
||||
'Deutsch': 1,
|
||||
'Englisch': 2,
|
||||
'Ger-Sub': 3,
|
||||
'Eng-Sub': 4,
|
||||
}
|
||||
// providers = {
|
||||
// "https://vidmoly.to/embed-preghvoypr2m.html": "vidmoly",
|
||||
// "https://speedfiles.net/40d98cdccf9c": "speedfiles",
|
||||
@@ -204,26 +241,18 @@ function selectHoster(finishedList) {
|
||||
|
||||
console.log("Hoster List: " + JSON.stringify(finishedList));
|
||||
|
||||
// Define the preferred providers and languages
|
||||
const providerList = ["VOE", "SpeedFiles", "Filemoon", "Vidmoly", "DoodStream", "Vidoza", "MP4Upload"];
|
||||
const languageList = ["English", "mit Untertitel Deutsch", "mit Untertitel Englisch"];
|
||||
|
||||
|
||||
|
||||
for (const language of languageList) {
|
||||
for (const providerName of providerList) {
|
||||
const video = finishedList.find(
|
||||
(video) => video.provider === providerName && video.language === language
|
||||
);
|
||||
if (video) {
|
||||
provider[video.href] = providerName.toLowerCase();
|
||||
// Prioritize based on preferredLang, if a lang with higher priority is found, skip the rest
|
||||
for (const lang of preferredLang) {
|
||||
for (const video of finishedList) {
|
||||
if (video.language === lang) {
|
||||
provider[video.href] = video.provider;
|
||||
}
|
||||
}
|
||||
if (Object.keys(provider).length > 0) {
|
||||
break; // break outer loop if we have found at least one provider
|
||||
}
|
||||
}
|
||||
// if the array is not empty, break the loop
|
||||
if (Object.keys(provider).length > 0) {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
sendLog("Provider List: " + JSON.stringify(provider));
|
||||
return provider;
|
||||
@@ -246,11 +275,24 @@ async function sendLog(message) {
|
||||
// Site specific structure
|
||||
function getSeasonLinks(html) {
|
||||
const seasonLinks = [];
|
||||
const seasonRegex = /<div class="hosterSiteDirectNav" id="stream">.*?<ul>(.*?)<\/ul>/s;
|
||||
// <nav class="mb-2" id="season-nav"> <ul class="nav list-items-nav">
|
||||
const seasonRegex = /<nav class="mb-2" id="season-nav">[\s\S]*?<ul class="nav list-items-nav">([\s\S]*?)<\/ul>/;
|
||||
|
||||
const seasonMatch = seasonRegex.exec(html);
|
||||
if (seasonMatch) {
|
||||
const seasonList = seasonMatch[1];
|
||||
const seasonLinkRegex = /<a[^>]*href="([^"]+)"[^>]*>([^<]+)<\/a>/g;
|
||||
/* <a
|
||||
href="https://s.to/serie/dexter/staffel-1"
|
||||
class="alphabet-link nav-link bg-primary "
|
||||
data-season-pill="1"
|
||||
> 1 </a>
|
||||
<a
|
||||
href="https://s.to/serie/dexter/staffel-2"
|
||||
class="alphabet-link nav-link "
|
||||
data-season-pill="2"
|
||||
> 2 </a>
|
||||
*/
|
||||
const seasonLinkRegex = /<a\s+[^>]*?href="([^"]+)"[^>]*?class="[^"]*alphabet-link/g;
|
||||
let seasonLinkMatch;
|
||||
const filmeLinks = [];
|
||||
while ((seasonLinkMatch = seasonLinkRegex.exec(seasonList)) !== null) {
|
||||
@@ -263,6 +305,7 @@ function getSeasonLinks(html) {
|
||||
}
|
||||
seasonLinks.push(...filmeLinks);
|
||||
}
|
||||
|
||||
return seasonLinks;
|
||||
}
|
||||
|
||||
@@ -270,39 +313,52 @@ function getSeasonLinks(html) {
|
||||
// Site specific structure
|
||||
async function fetchSeasonEpisodes(url) {
|
||||
try {
|
||||
const baseUrl = 'https://s.to';
|
||||
const fetchUrl = `${url}`;
|
||||
const response = await soraFetch(fetchUrl);
|
||||
const text = await response?.text() ?? response;
|
||||
const text = await response?.text() ?? await response;
|
||||
|
||||
// Updated regex to allow empty <strong> content
|
||||
const regex = /<td class="seasonEpisodeTitle">\s*<a[^>]*href="([^"]+)"[^>]*>.*?<strong>([^<]*)<\/strong>.*?<span>([^<]+)<\/span>.*?<\/a>/g;
|
||||
const regex2 =
|
||||
/<td[^>]*seasonEpisodeTitle[^>]*>\s*<a[^>]*href=["']([^"']+)["'][^>]*>[\s\S]*?<strong>\s*([^<]*?)\s*<\/strong>[\s\S]*?(?:<span[^>]*>\s*([^<]*?)\s*<\/span>)?[\s\S]*?<\/a>/gi;
|
||||
|
||||
|
||||
const matches = [];
|
||||
let match;
|
||||
let holderNumber = 0;
|
||||
|
||||
while ((match = regex.exec(text)) !== null) {
|
||||
const [_, link] = match;
|
||||
matches.push({ number: holderNumber, href: `${baseUrl}${link}` });
|
||||
// <nav class="mb-3" id="episode-nav"> <ul class="nav list-items-nav"></ul>
|
||||
const episodeDivRegex = /<nav class="mb-3" id="episode-nav">[\s\S]*?<ul class="nav list-items-nav">([\s\S]*?)<\/ul>/;
|
||||
const episodeDivMatch = episodeDivRegex.exec(text);
|
||||
const episodeList = [];
|
||||
if (episodeDivMatch) {
|
||||
const episodeListHtml = episodeDivMatch[1];
|
||||
/* <li class="nav-item me-1 mb-2">
|
||||
<a href="https://s.to/serie/dexter/staffel-1/episode-1"
|
||||
class=" alphabet-link nav-link ">
|
||||
1
|
||||
</a>
|
||||
</li>
|
||||
|
||||
<li class="nav-item me-1 mb-2">
|
||||
<a href="https://s.to/serie/dexter/staffel-1/episode-2"
|
||||
class=" alphabet-link nav-link ">
|
||||
2
|
||||
</a>
|
||||
</li>
|
||||
|
||||
<li class="nav-item me-1 mb-2">
|
||||
<a href="https://s.to/serie/dexter/staffel-1/episode-3"
|
||||
class=" alphabet-link nav-link ">
|
||||
3
|
||||
</a>
|
||||
</li>
|
||||
*/
|
||||
const episodeLinkRegex = /<a\s+[^>]*?href="([^"]+)"[^>]*?class="[^"]*alphabet-link[^"]*"[^>]*>\s*([\s\S]*?)\s*<\/a>/g;
|
||||
let episodeLinkMatch;
|
||||
let number = 0;
|
||||
while ((episodeLinkMatch = episodeLinkRegex.exec(episodeListHtml)) !== null) {
|
||||
const [_, episodeLink] = episodeLinkMatch;
|
||||
number += 1;
|
||||
episodeList.push({ number, href: episodeLink });
|
||||
}
|
||||
console.log("Episode List for season " + url + ": " + JSON.stringify(episodeList));
|
||||
}
|
||||
return episodeList;
|
||||
|
||||
// If no matches found with the first regex, try the second one
|
||||
if (matches.length === 0) {
|
||||
console.log("No matches found with first regex, trying second regex.");
|
||||
while ((match = regex2.exec(text)) !== null) {
|
||||
const [_, link] = match;
|
||||
console.log("Match found with second regex: " + link);
|
||||
matches.push({ number: holderNumber, href: `${baseUrl}${link}` });
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
return matches;
|
||||
|
||||
} catch (error) {
|
||||
} catch (error) {
|
||||
sendLog('FetchSeasonEpisodes helper function error:' + error);
|
||||
return [{ number: '0', href: 'https://error.org' }];
|
||||
}
|
||||
@@ -317,32 +373,34 @@ const regex2 =
|
||||
// Helper function to get the video links
|
||||
// Site specific structure
|
||||
function getVideoLinks(html) {
|
||||
const baseUrl = 'https://s.to';
|
||||
|
||||
// get links based on button:
|
||||
/* <button type="button"
|
||||
class="link-box btn btn-dark w-100 text-start gap-2"
|
||||
data-link-id="21778990"
|
||||
data-play-url="/r?t=eyJpdiI6IjRBTHNuWGVqekFjMVBzK09rREhqelE9PSIsInZhbHVlIjoiMzBnQjZJSW5INHBhWm1qNk9UdGVGYkR0Nyt4Mm1iVlYwRkk5TWFGNEpjaFdDcGJkSW11dTRSeE5RcndqRlJ5SWtXSitHVzFJc0pPSU9rdjBaa3RxUUE9PSIsIm1hYyI6IjM4ZDAxMjgyZWQ5ODYzYWZhODVlODJmMDAyNGMxZDcwODg3NTI0NDJjYWM2YjNlMTM5OGE5YWEzYWMzZjdiNWYiLCJ0YWciOiIifQ%3D%3D"
|
||||
data-auto-embed="1"
|
||||
data-provider-name="VOE"
|
||||
data-language-label="Deutsch"
|
||||
data-language-id="1"
|
||||
>
|
||||
...
|
||||
</button>
|
||||
*/
|
||||
const videoLinks = [];
|
||||
const videoRegex = /<li\s+class="[^"]*"\s+data-lang-key="([^"]+)"[^>]*>.*?<a[^>]*href="([^"]+)"[^>]*>.*?<h4>([^<]+)<\/h4>.*?<\/a>.*?<\/li>/gs;
|
||||
let match;
|
||||
|
||||
while ((match = videoRegex.exec(html)) !== null) {
|
||||
const [_, langKey, href, provider] = match;
|
||||
videoLinks.push({ langKey, href, provider });
|
||||
const videoLinkRegex = /<button\s+type="button"[^>]*?class="link-box btn btn-dark w-100 text-start gap-2"[^>]*?data-play-url="([^"]+)"[^>]*?data-provider-name="([^"]+)"[^>]*?data-language-id="([^"]+)"[^>]*?>/g;
|
||||
let videoLinkMatch;
|
||||
while ((videoLinkMatch = videoLinkRegex.exec(html)) !== null) {
|
||||
const [_, href, provider, language] = videoLinkMatch;
|
||||
videoLinks.push({ href: `${baseUrl}${href}`, provider: provider.toLowerCase(), language: parseInt(language) });
|
||||
}
|
||||
|
||||
return videoLinks;
|
||||
console.log("Video Links: " + JSON.stringify(videoLinks));
|
||||
|
||||
return videoLinks; // langKey, href, provider
|
||||
}
|
||||
|
||||
// Helper function to get the available languages
|
||||
// Site specific structure
|
||||
function getAvailableLanguages(html) {
|
||||
const languages = [];
|
||||
const languageRegex = /<img[^>]*data-lang-key="([^"]+)"[^>]*title="([^"]+)"[^>]*>/g;
|
||||
let match;
|
||||
|
||||
while ((match = languageRegex.exec(html)) !== null) {
|
||||
const [_, langKey, title] = match;
|
||||
languages.push({ langKey, title });
|
||||
}
|
||||
|
||||
return languages;
|
||||
}
|
||||
function _0xCheck() {
|
||||
var _0x1a = typeof _0xB4F2 === 'function';
|
||||
var _0x2b = typeof _0x7E9A === 'function';
|
||||
|
||||
Reference in New Issue
Block a user