Initial commit

.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

.gitignore

@@ -0,0 +1,130 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+# Comment in the public line in if your project uses Gatsby and not Next.js
+# https://nextjs.org/blog/next-9-1#public-directory-support
+# public
+
+# vuepress build output
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+.temp
+.cache
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v2
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*

README.md

@@ -0,0 +1,32 @@
+## Installation
+
+Once you downloaded the Project, open the "index.js" file.
+
+You will find the following variables:
+
+```bash
+  const course_url = '';
+  const subtitle_lang = 'en';
+  const cookies;
+  const _credentials_ = "";
+```
+
+The course_url is just the full URL of the course you want to download. For example:
+
+https://www.domestika.org/en/courses/3086-creating-animated-stories-with-after-effects/course
+
+IMPORTANT: you have to be on the "content" page. You know you are on the right site when at the end of the URL it says "/course".
+
+To get the _domestika_session and the \_credentials_ you will need to install a chrome extension called Cookie-Editor.
+
+After you installed the extension, log into domestika and open the extension.
+
+In the window popup, look for "\_domestika_session", click to open it and copy the contents of the Value field into the value field under cookies.
+
+then look for the "_credentials_" cookie, copy the value of that into the "_credentials_" variable.
+
+If you want to change the subtitles that will be downloaded, just put the preferred language into the "subtitle_lang" variable. But make sure the language is avaiable first.
+
+After you have done that, just open a terminal and start the script with "npm run start".
+
+All the courses will be downloaded in a folder called "domestika_courses/{coursename}/".

index.js

@@ -0,0 +1,133 @@
+const puppeteer = require('puppeteer');
+const cheerio = require('cheerio');
+const util = require('util');
+const exec = util.promisify(require('child_process').exec);
+const m3u8ToMp4 = require('m3u8-to-mp4');
+const fs = require('fs');
+const converter = new m3u8ToMp4();
+
+const course_url = '';
+const subtitle_lang = 'en';
+
+const cookies = [
+    {
+        name: '_domestika_session',
+        value: '',
+        domain: 'www.domestika.org',
+    },
+];
+
+const _credentials_ = '';
+
+scrapeSite();
+
+async function scrapeSite() {
+    const browser = await puppeteer.launch();
+    const page = await browser.newPage();
+    await page.setCookie(...cookies);
+    await page.goto(course_url);
+    const html = await page.content();
+    const $ = cheerio.load(html);
+
+    let allVideos = [];
+
+    let units = $('h4.h2.unit-item__title a');
+
+    let title = $('h1.course-header-new__title')
+        .text()
+        .trim()
+        .replace(/[/\\?%*:|"<>]/g, '-');
+
+    let totalVideos = 1;
+
+    for (let i = 0; i < units.length - 1; i++) {
+        let videoData = await getInitialProps($(units[i]).attr('href'));
+        allVideos.push({
+            title: $(units[i])
+                .text()
+                .trim()
+                .replace(/[/\\?%*:|"<>]/g, '-'),
+            videoData: videoData,
+        });
+
+        totalVideos += videoData.length;
+    }
+
+    let access_token = decodeURI(_credentials_);
+    let regex_token = /accessToken\":\"(.*?)\"/gm;
+    access_token = regex_token.exec(access_token)[1];
+
+    let regex_final = /courses\/(.*?)-/gm;
+    let final_project_id = regex_final.exec($(units[units.length - 1]).attr('href'))[1];
+    let final_data = await fetchFromApi(`https://api.domestika.org/api/courses/${final_project_id}/final-project?with_server_timing=true`, 'finalProject.v1', access_token);
+    final_project_id = final_data.data.relationships.video.data.id;
+    final_data = await fetchFromApi(`https://api.domestika.org/api/videos/${final_project_id}?with_server_timing=true`, 'video.v1', access_token);
+
+    allVideos.push({
+        title: 'Final project',
+        videoData: [{ playbackURL: final_data.data.attributes.playbackUrl, title: 'Final project' }],
+    });
+
+    let count = 0;
+    for (let i = 0; i < allVideos.length; i++) {
+        const unit = allVideos[i];
+        for (let a = 0; a < unit.videoData.length; a++) {
+            const vData = unit.videoData[a];
+
+            if (!fs.existsSync(`domestika_courses/${title}/${unit.title}/`)) {
+                fs.mkdirSync(`domestika_courses/${title}/${unit.title}/`, { recursive: true });
+            }
+
+            await exec(`yt-dlp --allow-u -f "bv*[height<=1080]" ${vData.playbackURL} -o "domestika_courses/${title}/${unit.title}/${vData.title}.%(ext)s"`);
+            await exec(`yt-dlp --write-subs --sub-langs ${subtitle_lang} --skip-download --convert-subtitles srt "${vData.playbackURL}" -o "domestika_courses/${title}/${unit.title}/${vData.title}"`);
+
+            count++;
+            console.log(`Download ${count}/${totalVideos} Downloaded`);
+        }
+    }
+
+    await browser.close();
+
+    console.log('All Videos Downloaded');
+}
+
+async function getInitialProps(url) {
+    const browser = await puppeteer.launch();
+    const page = await browser.newPage();
+    await page.setCookie(...cookies);
+    await page.goto(url);
+
+    const data = await page.evaluate(() => window.__INITIAL_PROPS__);
+
+    let videoData = [];
+
+    if (data && data != undefined) {
+        for (let i = 0; i < data.videos.length; i++) {
+            const el = data.videos[i];
+
+            videoData.push({
+                playbackURL: el.video.playbackURL,
+                title: el.video.title,
+            });
+        }
+    }
+
+    await browser.close();
+
+    return videoData;
+}
+
+async function fetchFromApi(apiURL, accept_version, access_token) {
+    const response = await fetch(apiURL, {
+        method: 'get',
+        headers: {
+            'Content-Type': 'application/vnd.api+json',
+            Accept: 'application/vnd.api+json',
+            'x-dmstk-accept-version': accept_version,
+            authorization: `Bearer ${access_token}`,
+        },
+    });
+    const data = await response.json();
+
+    return data;
+}