better-ani-scraped 1.5.1 → 1.6.0

package/DOCUMENTATION.md

@@ -27,7 +27,7 @@ const crunchyroll = new AnimeScraper('crunchyroll') //for Crunchyroll
 
 ## `AnimeScraper("animesama")` methods
 
-- [searchAnime](#animesamasearchanimequery-limit--10-wantedlanguages--vostfr-vf-vastfr-wantedtypes--anime-film)
+- [searchAnime](#animesamasearchanimequery-limit--10-wantedlanguages--vostfr-vf-vastfr-wantedtypes--anime-film-page--null)
 - [getSeasons](#animesamagetseasonsanimeurl-language--vostfr)
 - [getEpisodeTitles](#animesamagetepisodetitlesseasonurl-customchromiumpath)
 - [getEmbed](#animesamagetembedseasonurl-hostpriority--sibnet-vidmoly)
@@ -37,7 +37,7 @@ const crunchyroll = new AnimeScraper('crunchyroll') //for Crunchyroll
 - [getLatestEpisodes](#animesamagetlatestepisodeslanguagefilter--null)
 - [getRandomAnime](#animesamagetrandomanimewantedlanguages--vostfr-vf-vastfr-wantedtypes--anime-film-maxattempts--null-attempt--0)
 
-### `animesama.searchAnime(query, limit = 10, wantedLanguages = ["vostfr", "vf", "vastfr"], wantedTypes = ["Anime", "Film"])`
+### `animesama.searchAnime(query, limit = 10, wantedLanguages = ["vostfr", "vf", "vastfr"], wantedTypes = ["Anime", "Film"], page = null)`
 Searches for anime titles that match the given query.
 
 - **Parameters:**
@@ -45,6 +45,7 @@ Searches for anime titles that match the given query.
   - `limit` *(number)*: Maximum number of results to return (default: 10).
   - `wantedLanguages` *(string[])*: Array of wanted languages.
   - `wantedTypes` *(string[])*: Array of wanted types.
+  - `page` *(number)*: The catalog page number.
 - **Returns:**  
   An array of anime objects:
   ```js
@@ -315,10 +316,14 @@ Extracts information from all episodes of a season of an anime.
 Retrieves the video URL of the source's embed.
 
 - **Parameters:**
-  - `source` *(string)*: The embed source (only "sibnet" available at the moment)
+  - `source` *(string)*: The embed source (only "sibnet", "sendvid", "vidmoly" and "oneupload" available at the moment)
   - `embedUrl` *(string)*: The embed url of the given source.
 - **Returns:**  
-  A video URL as a string.
+  A video URL as a string :
+  - `sibnet`: mp4
+  - `sendvid`: mp4
+  - `vidmoly`: m3u8
+  - `oneupload`: m3u8
 
 ---
 ---

package/examples/animesama/example_usage_searchAnime.js

@@ -3,7 +3,7 @@ import { AnimeScraper } from "../../index.js"; // REPLACE BY "from 'better-ani-s
 const main = async () => {
   const animesama = new AnimeScraper('animesama');
 
-  const search = await animesama.searchAnime("86", 3, ["vostfr", "vf", "vastfr"], ["Anime", "Film"]);
+  const search = await animesama.searchAnime("a", 100, ["vostfr", "vf", "vastfr"], ["Anime", "Film"], 2);
   console.log("Search Results:", search);
 };
 

package/examples/utility-functions/example_usage_getVideoUrlFromEmbed.js

@@ -1,11 +1,22 @@
 import { getVideoUrlFromEmbed } from "../../index.js"; // REPLACE BY "from 'better-ani-scraped';"
 
 const main = async () => {
-  const embedUrl = "https://video.sibnet.ru/shell.php?videoid=4291083";
-  
-  const videoUrl = await getVideoUrlFromEmbed("sibnet", embedUrl)
-  console.log("Video URL:", videoUrl);
+  const embedUrlSibnet = "https://video.sibnet.ru/shell.php?videoid=4291083";
+  const embedUrlSendvid = "https://sendvid.com/embed/4vzpcb0q";
+  const embedUrlVidmoly = "https://vidmoly.to/embed-vt374ef2joph.html";
+  const embedUrlOneupload = "https://oneupload.net/embed-axdrxh1y3p37.html";
+
+  const videoUrlSibnet = await getVideoUrlFromEmbed("sibnet", embedUrlSibnet)
+  console.log("Video URL Sibnet:", videoUrlSibnet);
 
+  const videoUrlSendvid = await getVideoUrlFromEmbed("sendvid", embedUrlSendvid)
+  console.log("Video URL Sendvid:", videoUrlSendvid);
+
+  const videoUrlVidmoly = await getVideoUrlFromEmbed("vidmoly", embedUrlVidmoly)
+  console.log("Video URL Vidmoly:", videoUrlVidmoly);
+  
+  const videoUrlOneupload = await getVideoUrlFromEmbed("oneupload", embedUrlOneupload)
+  console.log("Video URL Oneupload:", videoUrlOneupload);
 };
 
 main().catch(console.error);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "better-ani-scraped",
-  "version": "1.5.1",
+  "version": "1.6.0",
   "description": "Scrape anime data from different sources (only anime-sama.fr for the moment)",
   "main": "index.js",
   "scripts": {
@@ -21,7 +21,7 @@
     "axios": "^1.8.4",
     "cheerio": "^1.0.0",
     "playwright": "^1.52.0",
-    "puppeteer": "^24.7.2",
+    "puppeteer": "^24.8.1",
     "puppeteer-extra": "^3.3.6",
     "puppeteer-extra-plugin-stealth": "^2.11.2"
   },

package/scrapers/animesama.js

@@ -47,67 +47,73 @@ export async function searchAnime(
   query,
   limit = 10,
   wantedLanguages = ["vostfr", "vf", "vastfr"],
-  wantedTypes = ["Anime", "Film"]
+  wantedTypes = ["Anime", "Film"],
+  page = null
 ) {
-  const url = `${CATALOGUE_URL}/?search=${encodeURIComponent(
-    query
-  )}`;
   const isWanted = (text, list) =>
     list.some(item => text.toLowerCase().includes(item.toLowerCase()));
-  const res = await axios.get(url, { headers: getHeaders(CATALOGUE_URL) });
-  const $ = cheerio.load(res.data);
+
   const results = [];
 
-  $("a.flex.divide-x").each((i, el) => {
-    if (i >= limit) return false;
+  const fetchPage = async (pageNum) => {
+    const url =
+      pageNum === 1
+        ? `${CATALOGUE_URL}/?search=${encodeURIComponent(query)}`
+        : `${CATALOGUE_URL}/?search=${encodeURIComponent(query)}&page=${pageNum}`;
 
-    const anchor = $(el);
-    const link = anchor.attr("href");
-    const title = anchor.find("h1").first().text().trim();
-    const altRaw = anchor
-      .find("p.text-xs.opacity-40.italic")
-      .first()
-      .text()
-      .trim();
-    const cover = anchor.find("img").first().attr("src");
+    const res = await axios.get(url, { headers: getHeaders(CATALOGUE_URL) });
+    const $ = cheerio.load(res.data);
 
-    const tagText = anchor.find("p").filter((_, p) =>
-      isWanted($(p).text(), wantedTypes)
-    ).first().text();
+    const containers = $("a.flex.divide-x");
 
-    const languageText = anchor.find("p").filter((_, p) =>
-      isWanted($(p).text(), wantedLanguages)
-    ).first().text();
+    containers.each((_, el) => {
+      if (results.length >= limit) return false;
 
-    const altTitles = altRaw
-      ? altRaw
-          .split(",")
-          .map((t) => t.trim())
-          .filter(Boolean)
-      : [];
+      const anchor = $(el);
+      const link = anchor.attr("href");
+      const title = anchor.find("h1").first().text().trim();
+      const altRaw = anchor.find("p.text-xs.opacity-40.italic").first().text().trim();
+      const cover = anchor.find("img").first().attr("src");
 
-    const genreRaw = anchor
-      .find("p.text-xs.font-medium.text-gray-300")
-      .first()
-      .text()
-      .trim();
-    const genres = genreRaw
-      ? genreRaw
-          .split(",")
-          .map((g) => g.trim())
-          .filter(Boolean)
-      : [];
+      const tagText = anchor.find("p").filter((_, p) =>
+        isWanted($(p).text(), wantedTypes)
+      ).first().text();
 
-    if (title && link && tagText && languageText) {
-      results.push({
-        title,
-        altTitles,
-        genres,
-        url: link.startsWith("http") ? link : `${CATALOGUE_URL}${link}`,
-        cover,
-      });
+      const languageText = anchor.find("p").filter((_, p) =>
+        isWanted($(p).text(), wantedLanguages)
+      ).first().text();
+
+      const altTitles = altRaw
+        ? altRaw.split(",").map((t) => t.trim()).filter(Boolean)
+        : [];
+
+      const genreRaw = anchor.find("p.text-xs.font-medium.text-gray-300").first().text().trim();
+      const genres = genreRaw
+        ? genreRaw.split(",").map((g) => g.trim()).filter(Boolean)
+        : [];
+
+      if (title && link && tagText && languageText) {
+        results.push({
+          title,
+          altTitles,
+          genres,
+          url: link.startsWith("http") ? link : `${CATALOGUE_URL}${link}`,
+          cover,
+        });
+      }
+    });
+
+    return containers.length > 0;
+  };
+
+  if (page) {
+    await fetchPage(page);
+  } else {
+    let currentPage = 1;
+    while (await fetchPage(currentPage++) && results.length < limit) {
+      await new Promise((res) => setTimeout(res, 300));
     }
-  });
+  }
 
   return results;
 }

package/utils/dispatcher.js

@@ -4,6 +4,12 @@ export async function getVideoUrlFromEmbed(source, embedUrl) {
   if (source === "sibnet") {
     return await extractor.getSibnetVideo(embedUrl);
   }
+  if (source === "sendvid") {
+    return await extractor.getSendvidVideo(embedUrl);
+  }
+  if (source === "vidmoly" || source === "oneupload" ) { 
+    return await extractor.getVidmolyOrOneuploadVideo(embedUrl);
+  }
 
   throw new Error(`Unsupported embed source: ${source}`);
 }

package/utils/extractVideoUrl.js

@@ -1,67 +1,74 @@
 import axios from "axios";
 import * as cheerio from "cheerio";
 
-export async function getSibnetVideo(embedUrl) {
-  let intermediaries = [];
-  let realUrl = "";
-
-  const getIntermediary = async () => {
-    try {
-      const { data } = await axios.get(embedUrl, { headers: getHeaders(embedUrl) });
-      const $ = cheerio.load(data);
-      const script = $("script")
-        .toArray()
-        .map((s) => $(s).html())
-        .find((s) => s.includes("player.src"));
-      const match = script?.match(/player\.src\(\[{src:\s*["']([^"']+)["']/);
-      if (match) intermediaries.push(`https://video.sibnet.ru${match[1]}`);
-      return !!match;
-    } catch {
-      return false;
-    }
-  };
 
-  const followRedirection = async () => {
-    if (!intermediaries.length) return false;
-    try {
-      const first = await axios.get(intermediaries[0], {
-        headers: getHeaders(embedUrl),
-        maxRedirects: 0,
-        validateStatus: (s) => s >= 200 && s < 303,
-      });
+const getHeaders = (referer) => ({
+  Accept: "*/*",
+  Referer: referer,
+  "User-Agent":
+    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+});
+export async function getSibnetVideo(embedUrl) {
+  try {
+    const { data } = await axios.get(embedUrl, {
+      headers: getHeaders(embedUrl),
+    });
+    const $ = cheerio.load(data);
+    const script = $("script")
+      .toArray()
+      .map((s) => $(s).html())
+      .find((s) => s.includes("player.src"));
+    const match = script?.match(/player\.src\(\[{src:\s*["']([^"']+)["']/);
+    if (!match || !match[1]) return null;
+    const intermediateUrl = `https://video.sibnet.ru${match[1]}`;
+    const res1 = await axios.get(intermediateUrl, {
+      headers: getHeaders(embedUrl),
+      maxRedirects: 0,
+      validateStatus: (s) => s >= 200 && s < 400, 
+    });
+    const redirectUrl = res1.headers.location;
+    if (!redirectUrl) return null;
+    const finalUrl = redirectUrl.startsWith("http")
+      ? redirectUrl
+      : `https:${redirectUrl}`;
+    return finalUrl;
+  } catch (err) {
+    console.error("Erreur getSibnetVideo:", err.message);
+    return null;
+  }
+}
 
-      const redirect1 = correct(first.headers.location);
-      intermediaries.push(redirect1);
+export async function getSendvidVideo(embedUrl) {
+  try {
+    const { data } = await axios.get(embedUrl, {
+      headers: getHeaders(embedUrl),
+    });
+    const $ = cheerio.load(data);
+    const sourceTag = $("video source[type='video/mp4']").attr("src");
+    return sourceTag || null;
+  } catch (err) {
+    return null;
+  }
+}
 
-      const second = await axios.get(redirect1, {
-        headers: getHeaders(intermediaries[0]),
-        maxRedirects: 0,
-        validateStatus: (s) => s >= 200 && s < 303,
-      });
+export async function getVidmolyOrOneuploadVideo(embedUrl) {
+  try {
+    const { data } = await axios.get(embedUrl, {
+      headers: getHeaders(embedUrl),
+    });
+    const $ = cheerio.load(data);
+    const scripts = $("script");
 
-      realUrl =
-        second.status === 302
-          ? correct(second.headers.location)
-          : second.status === 200
-          ? intermediaries.pop()
-          : "";
-      return !!realUrl;
-    } catch {
-      return false;
+    for (let i = 0; i < scripts.length; i++) {
+      const content = $(scripts[i]).html();
+      const match = content && content.match(/file\s*:\s*"(https[^"]+\.m3u8[^"]*)"/);
+      if (match && match[1]) {
+        return match[1];
+      }
     }
-  };
-
-  const correct = (url) => (url.startsWith("https:") ? url : `https:${url}`);
-
-  const getHeaders = (referer) => ({
-    Accept: "*/*",
-    Referer: referer,
-    Range: "bytes=0-",
-    "User-Agent":
-      "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
-  });
-
-  return (await getIntermediary()) && (await followRedirection())
-    ? realUrl
-    : null;
+    return null;
+  } catch (err) {
+    console.error("Erreur getVidmolyVideo:", err.message);
+    return null;
+  }
 }